Panelists: Sara Beery (Google, MIT) Hannah Kerner (Arizona State University, NASA Harvest) Pierre Gentine (Columbia University) Marc Russwurm (EPFL) Sherrie Wang (MIT)

Moderator: TBA

Explainable artificial intelligence (XAI) methods shed light on the predictions of deep neural networks (DNNs). In the climate context, XAI has been applied to improve and validate deep learning (DL) methods while providing researchers with new insight into physical processes. However, the evaluation, validation and selection of XAI methods are challenging due to often lacking ground truth explanations.In this tutorial, we introduce the XAI evaluation package Quantus to the climate community. We start by providing the users with pre-processed input and output data alongside a convolutional neural network (CNN) trained to assign yearly temperature maps to classes according to their decade. We explain the network prediction of an example temperature map using five different explanation techniques Gradient GradientShap, IntegratedGradients, LRP-z and Occlusion. By visually analyzing each explanation method around the North Atlantic (NA) cooling patch 10-80W, 20-60N, we provide a motivating example that shows that different explanations may disagree in their explained evidence which subsequently can lead to different scientific interpretation and potentially, misleading conclusions. We continue by introducing Quantus including the explanation properties that can be evaluated such as robustness, faithfulness, complexity, localization and randomization. We guide the participants towards a practical understanding of XAI evaluation by demonstrating how metrics differ in their scoring and interpretation. Moreover, we teach the participants to compare and select an appropriate XAI method by performing a comprehensive XAI evaluation. Lastly, we return to the motivating example, highlighting how Quantus can facilitate well-founded XAI research in climate science.

To cope with climate change, the energy system is undergoing a massive transformation. With the electrification of all sectors, the power grid is facing high additional demand. As a result, the digitization of the grid is becoming more of a focus. The smart grid relies heavily on the increasing deployment of smart electricity meters around the world. The corresponding smart meter data is typically a time series of power or energy measurements with a resolution of 1s to 60 min. This data provides valuable insights and opportunities for monitoring and controlling activities in the power grid. In this tutorial, we therefore provide an overview of best practices for analyzing smart meter data. We focus on machine learning applications and low resolution (15-60 minutes) energy data in a residential setting. We only use real-world datasets and cover use-cases that are highly relevant for practical applications. Although this tutorial is specifically tailored to an audience from the energy domain, we believe that anyone from the data analytics and machine learning community can benefit from it, as many techniques are applicable to any time series data. Through our tutorial, we hope to foster new ideas, contribute to an interdisciplinary exchange between different research fields, and educate people about energy use.

Industrial air pollution has a direct health impact and is a major contributor to climate change. Small scale industries particularly bull-trench brick kilns are one of the major causes of air pollution in South Asia often creating hazardous levels of smog that is injurious to human health. To mitigate the climate and health impact of the kiln industry, fine-grained kiln localization at different geographic locations is needed. Kiln localization using multi-spectral remote sensing data such as vegetation index results in a noisy estimates whereas use of high-resolution imagery is infeasible due to cost and compute complexities. This paper proposes a fusion of spatio-temporal multi-spectral data with high-resolution imagery for detection of brick kilns within the "Brick-Kiln-Belt" of South Asia. We first perform classification using low-resolution spatio-temporal multi-spectral data from Sentinel-2 imagery by combining vegetation, burn, build up and moisture indices. Then orientation aware object detector: YOLOv3 (with theta value) is implemented for removal of false detections and fine-grained localization. Our proposed technique, when compared with other benchmarks, results in a 21 times improvement in speed with comparable or higher accuracy when tested over multiple countries.

Project Suncatcher estimates the solar potential of residential buildings usinghigh quality aerial data. That is, it estimates the potential solar energy (and associated financial savings) that can be captured by buildings if solar panels were to be installed on their roofs. Unfortunately its coverage is limited by the lackof high resolution digital surface map (DSM) data. We present a deep learningapproach that bridges this gap by enhancing widely available low-resolution data,thereby dramatically increasing the coverage of Suncatcher. We also present someongoing efforts to potentially improve accuracy even further by replacing certainalgorithmic components of Suncatcher’s processing pipeline with deep learning.

Understanding and properly estimating the impacts of environmental interventions is of critical importance as we work towards achieving global climate goals. Remote sensing has become an essential tool for evaluating when and where climate policies have positive impacts on factors like greenhouse gas emissions and carbon sequestration. However, when machine learning models trained to predict outcomes using remotely sensed data simply minimize a standard loss function, the predictions that they generate can produce biased estimates in downstream causal inference. If prediction error in the outcome variable is correlated with policy variables or important confounders, as is the case for many widely used remote sensing data sets, estimates of the causal impacts of policies can be biased. In this paper, we demonstrate how this bias can arise, and we propose the use of an adversarial debiasing model (Zhang, Lemoine, and Mitchell 2018) in order to correct the issue when using satellite data to generate machine learning predictions for use in causal inference. We apply this method to a case study of the relationship between roads and tree cover in West Africa, where our results indicate that adversarial debiasing can recover a much more accurate estimate of the parameter of interest compared to when the standard approach is used.

Carbon capture and storage (CCS) plays an essential role in global decarbonization. Scaling up CCS requires accurate and high-resolution modeling of the storage reservoir pressure buildup and the gaseous plume migration. However, such modeling is very challenging at scale due to the high computational costs of existing numerical methods. This challenge leads to significant uncertainty in evaluating storage opportunities which can delay the pace of global CCS deployments. We introduce a machine-learning approach for dynamic basin-scale modeling that speeds up flow prediction nearly 700,000 times compared to existing methods. Our framework, Nested Fourier Neural Operator (FNO), provides a general-purpose simulator alternative under diverse reservoir conditions, geological heterogeneity, and injection schemes. It enables unprecedented real-time high-fidelity modeling to support decision-making in basin-scale CCS projects.

Modern machine learning models have started to consume incredible amounts of energy, thus incurring large carbon footprints (Strubell et al., 2019). To address this issue, we have created an energy estimation pipeline, which allows practitioners to estimate the energy needs of their models in advance, without actually running or training them. We accomplished this, by collecting high-quality energy data and building a first baseline model, capable of predicting the energy consumption of DL models by accumulating their estimated layer-wise energies.

Cities represent both a fundamental contributor to greenhouse (GHG) emissions and a catalyst for climate action. Many global cities have outlined sustainability and climate change mitigation plans, focusing on energy efficiency, shifting away from fossil fuels, and prioritizing environmental and social justice. To achieve broad-based and equitable carbon emissions reductions and sustainability goals, new data-driven methodologies are needed to identify and target efficiency and carbon reduction opportunities in the built environment at the building, neighborhood, and city-scale. Our methodology integrates data from numerous data sources and develops data-driven and physical models of energy use and carbon emissions from buildings and transportation to generate a high spatiotemporal resolution model of urban greenhouse gas emissions. The method and data tool are designed to support city leaders and urban policymakers with an unprecedented view of localized carbon emissions to enable data-driven and evidenced-based climate action.

Panelists: Marc Manyifika (World Resources Institute) Abdinassir Sagar (UN-Habitat) Joseph Keller (Brookings Institution) Betsy Muriithi (Strathmore University)

Moderator: TBA

Recent data-driven approaches based on machine learning aim to directly solve a downstream forecasting or projection task by learning a data-driven functional mapping using deep neural networks. However, these networks are trained using curated and homogeneous climate datasets for specific spatiotemporal tasks, and thus lack the generality of currently used physics-informed numerical models for weather and climate modeling. We develop and demonstrate ClimaX, a flexible and generalizable deep learning model for weather and climate science that can be trained using heterogeneous datasets spanning different variables, spatiotemporal coverage, and physical groundings. ClimaX extends the Transformer architecture with novel encoding and aggregation blocks that allow effective use of available compute and data while maintaining general utility. ClimaX is pre-trained with a self-supervised learning objective on climate datasets derived from CMIP6. The pretrained ClimaX can then be fine-tuned to address a breadth of climate and weather tasks, including those that involve atmospheric variables and spatiotemporal scales unseen during pretraining. Compared to existing data-driven baselines, we show that this generality in ClimaX results in superior performance on benchmarks for weather forecasting and climate projections.

Planning optimization of gas networks under emission constraints prioritizes gas supply with the smallest emission footprint. As this problem includes complex gas flow physical laws, standard optimization solvers cannot guarantee convergence to a feasible solution, especially under strict emission constraints. To address this issue, we develop an input-convex neural network (ICNN) aided optimization routine which incorporates a set of trained ICNNs approximating the gas flow equations with high precision. Numerical tests on the Belgium gas network demonstrate that the ICNN-aided optimization dominates non-convex and relaxation-based solvers, with larger optimality gains pertaining to stricter emission targets.

Climate change is a major driver of biodiversity loss, changing the geographicrange and abundance of many species. However, there remain significant knowl-edge gaps about the distribution of species, due principally to the amount of effortand expertise required for traditional field monitoring. We propose an approachleveraging computer vision to improve species distribution modelling, combiningthe wide availability of remote sensing data with sparse on-ground citizen sciencedata from .We introduce a novel task and dataset for mapping US bird species totheir habitats by predicting species encounter rates from satellite images, alongwith baseline models which demonstrate the power of our approach. Our methodsopen up possibilities for scalably modelling ecosystems properties worldwide.

Subgrid parameterizations that represent physical processes occurring below the resolution of current climate models are an important component in producing accurate, long-term predictions for the climate. A variety of approaches have been tested to design these components, including deep learning methods. In this work, we evaluate a proof of concept illustrating a multiscale approach to this prediction problem. We train neural networks to predict subgrid forcing values on a testbed model and examine improvements in prediction accuracy which can be obtained by using additional information in both fine-to-coarse and coarse-to-fine directions.

The CityLearn Workshop will introduce the software tool CityLearn to model and analyze advanced control approaches in grid-interactive smart communities, e.g., demand response and load shaping in buildings. CityLearn is an open source OpenAI Gym environment targeted at the easy implementation and benchmarking of advanced control algorithms, i.e., model predictive control or deep reinforcement learning. Main applications to-date consist of controlling the charging and discharging of active storage systems i.e. battery and thermal storage tanks and heat pump power in the buildings to reduce electricity consumption, electricity cost, peak load and carbon emissions.The workshop will be in three parts. The first part will consist of an overview presentation of CityLearn. In the second part, we provide a walk-through tutorial on how to set up the environment using input data from residential building energy models in public End-Use Load Profiles (EULP) for the U.S. Building Stock database. Participants will be able to follow along using the provided Jupyter notebook. The notebook will provide a guide on how to use a simple rule-based control architecture, advanced soft-actor-critic methods, and the MARLISA multi-agent reinforcement learning control architecture. Finally, in the last part participants can optimize hyperparameters of algorithms and compare their findings against each other.CityLearn has been used in 2020--2022 editions of the CityLearn Challenge. The most recent CityLearn Challenge 2022 was hosted on the AICrowd platform (https://www.aicrowd.com/challenges/neurips-2022-citylearn-challenge). It has seen over 500 participants from 50+ countries and 1,500+ submission.

Explainable artificial intelligence (XAI) methods shed light on the predictions of deep neural networks (DNNs). In the climate context, XAI has been applied to improve and validate deep learning (DL) methods while providing researchers with new insight into physical processes. However, the evaluation, validation and selection of XAI methods are challenging due to often lacking ground truth explanations.In this tutorial, we introduce the XAI evaluation package Quantus to the climate community. We start by providing the users with pre-processed input and output data alongside a convolutional neural network (CNN) trained to assign yearly temperature maps to classes according to their decade. We explain the network prediction of an example temperature map using five different explanation techniques Gradient GradientShap, IntegratedGradients, LRP-z and Occlusion. By visually analyzing each explanation method around the North Atlantic (NA) cooling patch 10-80W, 20-60N, we provide a motivating example that shows that different explanations may disagree in their explained evidence which subsequently can lead to different scientific interpretation and potentially, misleading conclusions. We continue by introducing Quantus including the explanation properties that can be evaluated such as robustness, faithfulness, complexity, localization and randomization. We guide the participants towards a practical understanding of XAI evaluation by demonstrating how metrics differ in their scoring and interpretation. Moreover, we teach the participants to compare and select an appropriate XAI method by performing a comprehensive XAI evaluation. Lastly, we return to the motivating example, highlighting how Quantus can facilitate well-founded XAI research in climate science.

To cope with climate change, the energy system is undergoing a massive transformation. With the electrification of all sectors, the power grid is facing high additional demand. As a result, the digitization of the grid is becoming more of a focus. The smart grid relies heavily on the increasing deployment of smart electricity meters around the world. The corresponding smart meter data is typically a time series of power or energy measurements with a resolution of 1s to 60 min. This data provides valuable insights and opportunities for monitoring and controlling activities in the power grid. In this tutorial, we therefore provide an overview of best practices for analyzing smart meter data. We focus on machine learning applications and low resolution (15-60 minutes) energy data in a residential setting. We only use real-world datasets and cover use-cases that are highly relevant for practical applications. Although this tutorial is specifically tailored to an audience from the energy domain, we believe that anyone from the data analytics and machine learning community can benefit from it, as many techniques are applicable to any time series data. Through our tutorial, we hope to foster new ideas, contribute to an interdisciplinary exchange between different research fields, and educate people about energy use.

Flooding is one of the most destructive and costly natural disasters, and climatechanges would further increase risks globally. This work presents a novel mul-timodal machine learning approach for multi-year global flood risk prediction,combining geographical information and historical natural disaster dataset. Ourmultimodal framework employs state-of-the-art processing techniques to extractembeddings from each data modality, including text-based geographical data andtabular-based time-series data. Experiments demonstrate that a multimodal ap-proach, that is combining text and statistical data, outperforms a single-modalityapproach. Our most advanced architecture, employing embeddings extracted us-ing transfer learning upon DistilBert model, achieves 75%-77% ROCAUC scorein predicting the next 1-5 year flooding event in historically flooded locations.This work demonstrates the potentials of using machine learning for long-termplanning in natural disaster management

Precipitation extremes are expected to become stronger and more frequent in response to anthropogenic global warming. Accurately projecting the ecological and socioeconomic impacts is an urgent task. Impact models are developed and calibrated with observation-based data but rely on Earth system model (ESM) output for future scenarios. ESMs, however, exhibit significant biases in their output because they cannot fully resolve complex cross-scale interactions of processes that produce precipitation cannot. State-of-the-art bias correction methods only address errors in the simulated frequency distributions, locally at every individual grid cell. Improving unrealistic spatial patterns of the ESM output, which would require spatial context, has not been possible so far.Here we show that a post-processing method based on physically constrained generative adversarial networks (GANs) can correct biases of a state-of-the-art global ESM both in local frequency distributions and in the spatial patterns at once. While our method improves local frequency distributions similarly well to a gold-standard ESM bias-adjustment framework, it strongly outperforms existing methods in correcting spatial patterns. Our study highlights the importance of physical constraints in neural networks for out-of-sample predictions in the context of climate change.

High-efficiency retrofits can play a key role in reducing carbon emissions associated with buildings if processes can be scaled-up to reduce cost, time, and disruption. Here we demonstrate an artificial intelligence/computer vision (AI/CV)-enabled framework for converting exterior build scans and dimensional data directly into manufacturing and installation specifications for overclad panels. In our workflow point clouds associated with LiDAR-scanned buildings are segmented into a facade feature space, vectorized features are extracted using an iterative random-sampling consensus algorithm, and from this representation an optimal panel design plan satisfying manufacturing constraints is generated. This system and the corresponding construction process is demonstrated on a test facade structure constructed at the National Renewable Energy Laboratory (NREL). We also include a brief summary of a techno-economic study designed to estimate the potential energy and cost impact of this new system.

Due to climate change, thawing permafrost affects transportation infrastructure in northern regions. Tracking deformations over time of these structures can allow identifying the most vulnerable sections to permafrost degradation and implement climate adaptation strategies. The Sentinel-2 mission provides data well-suited for multitemporal analysis due to its high temporal resolution and multispectral coverage. However, the geometrical misalignment of Sentinel-2 imagery makes this analysis challenging. Towards the goal of estimating the deformation of linear infrastructure in northern Canada, we propose an automatic subpixel coregistration algorithm for satellite image time series based on the matching of binary masks of roads produced by a deep learning model. We demonstrate the feasibility of achieving subpixel coregistration through alignment of roads on a small dataset of high-resolution Sentinel-2 images from the region of Gillam in northern Canada. This is the first step towards training a road deformation prediction model.

To advance automated detection of extreme weather events, which are increasing in frequency and intensity with climate change, we explore modifications to a novel light-weight Context Guided convolutional neural network architecture trained for semantic segmentation of tropical cyclones and atmospheric rivers in climate data. Our primary focus is on tropical cyclones, the most destructive weather events, for which current models show limited performance. We investigate feature engineering, data augmentation, learning rate modifications, alternative loss functions, and architectural changes. In contrast to previous approaches optimizing for intersection over union, we specifically seek to improve recall to penalize under-counting and prioritize identification of tropical cyclones. We report success through the use of weighted loss functions to counter class imbalance for these rare events. We conclude with directions for future research on extreme weather events detection, a crucial task for prediction, mitigation, and equitable adaptation to the impacts of climate change.

Estimating the embodied carbon in products is a key step towards understanding their impact, and undertaking mitigation actions. Precise carbon attribution ischallenging at scale, requiring both domain expertise and granular supply chaindata. As a first-order approximation, standard reports use Economic Input-Outputbased Life Cycle Assessment (EIO-LCA) which estimates carbon emissions perdollar at an industry sector level using transactions between different parts of theeconomy. For EIO-LCA, an expert needs to map each product to one of upwardsof 1000 potential industry sectors. We present CaML, an algorithm to automateEIO-LCA using semantic text similarity matching by leveraging the text descriptions of the product and the industry sector. CaML outperforms the previous manually intensive method, yielding a MAPE of 22% with no domain labels.

The level of carbon dioxide (CO2) in our atmosphere is rapidly rising and is projected to double today‘s levels to reach 1,000 ppm by 2100 under certain scenarios, primarily driven by anthropogenic sources. Technology that can capture CO2 from anthropogenic sources, remove from atmosphere and sequester it at the gigaton scale by 2050 is required stop and reverse the impact of climate change. Metal-organic frameworks (MOFs) have been a promising technology in various applications including gas separation as well as CO2 capture from point-source flue gases or removal from the atmosphere. MOFs offer unmatched surface area through their highly porous crystalline structure and MOF technology has potential to become a leading adsorption-based CO2 separation technology providing high surface area, structure stability and chemical tunability. Due to its complex structure, MOF crystal structure (atoms and bonds) cannot be easily represented in tabular format for machine learning (ML) applications whereas graph neural networks (GNN) have already been explored in representation of simpler chemical molecules. In addition to difficulty in MOF data representation, an infinite number of combinations can be created for MOF crystals, which makes ML applications more suitable to alleviate dependency on subject matter experts (SME) than conventional computational methods. In this work, we propose training of GNNs in variational autoencoder (VAE) setting to create an end-to-end workflow for the generation of new MOF crystal structures directly from the data within the crystallographic information files (CIFs) and conditioned by additional CO2 performance values.

Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants. To measure the atmosphere’s ability to dilute air pollutants, Air Stagnation Index (ASI) has been introduced as an important meteorological index. Therefore, making long-lead ASI forecasts is vital to make plans in advance for air quality management. In this study, we found that autumn Niño indices derived from sea surface temperature (SST) anomalies show a negative correlation with wintertime ASI in southern China, offering prospects for a prewinter forecast. We developed an LSTM-based model to predict the future wintertime ASI. Results demonstrated that multivariate inputs (past ASI and Niño indices) achieve better forecast performance than univariate input (only past ASI). The model achieves a correlation coefficient of 0.778 between the actual and predicted ASI, exhibiting a high degree of consistency.

Streamflow forecasts are critical to guide water resource management, mitigate drought and flood effects, and develop climate-smart infrastructure and industries. Many global regions, however, have limited streamflow observations to guide evidence-based management strategies. In this paper, we propose an attention-based domain adaptation streamflow forecaster for data-sparse regions. Our approach leverages the hydrological characteristics of a data-rich source domain to induce effective 24h lead-time streamflow prediction in a limited target domain. Specifically, we employ a deep-learning framework leveraging domain adaptation techniques to simultaneously train streamflow predictions and discern between both domains using an adversarial method. Experiments against baseline cross-domain forecasting models show improved performance for 24h lead-time streamflow forecasting.

A higher share of cycling in cities can lead to a reduction in greenhouse gas emissions, a decrease in noise pollution, and personal health benefits. Data-driven approaches to planning new infrastructure to promote cycling are rare, mainly because data on cycling volume are only available selectively. By leveraging new and more granular data sources, we predict bicycle count measurements in Berlin, using data from free-floating bike-sharing systems in addition to weather, vacation, infrastructure, and socioeconomic indicators. To reach a high prediction accuracy given the diverse data, we make use of machine learning techniques. Our goal is to ultimately predict traffic volume on all streets beyond those with counters and to understand the variance in feature importance across time and space. Results indicate that bike-sharing data are valuable to improve the predictive performance, especially in cases with high outliers, and help generalize the models to new locations.

The Climate Model Intercomparison Project provides access to ensembles of model experiments that are widely used to better understand past, present, and future climate changes. In this study, we present an unsupervised machine learning framework to guide identification of models in the CMIP6 dataset that are best suited for specific modelling objectives. An example is discussed here that focuses on how CMIP6 models reproduce the physical properties of Antarctic Intermediate Water, a key feature of the global oceanic circulation and of the ocean-climate system, noting that the tools and methods introduced here can readily be extended to the analysis of other timescales, features and regions.

Carbon credit programs finance projects to reduce emissions, remove pollutants, improve livelihoods, and protect natural ecosystems. Ensuring the quality and integrity of such projects is essential to their success. One of the most important variables used in nature-based solutions to measure carbon sequestration is the diameter at breast height (DBH) of trees. In this paper, we propose an automatic mobile computer vision method to estimate the DBH of a tree using a single depth map on a smartphone, along with our created dataset DepthMapDBH2023. We successfully demonstrated that this dataset paired with a lightweight regression convolutional neural network is able to accurately estimate the DBH of trees distinct in appearance, shape, number of tree forks, tree density and crowding, and vine presence. Automation of these measurements will help crews in the field who are collecting data for forest inventories. Gathering as much on-the-ground data as possible is required to ensure the transparency of carbon credit projects. Access to high-quality datasets of manual measurements helps improve biomass models which are widely used in the field of ecological simulation. The code used in this paper will be publicly available on Github and the dataset on Kaggle.

Price-based demand response management (DR) enables households to provide the flexibility required in power grids with a high share of volatile renewable energy sources. Multi-agent reinforcement learning (MARL) offers a powerful, decentralized decision-making tool for autonomous agents participating in DR programs. Unfortunately, MARL algorithms do not naturally allow incorporating safety guarantees, preventing their real-world deployment. To meet safety constraints, we propose a safety layer which minimally adjusts each agent’s decisions. We investigate the influence of incentivizing the agents to minimize safety constraint violation by adding a scalar safety feedback to the reward. Results show that using the feedback during training improves both convergence speed and performance.

Today's fire projection modeling tools struggle to keep up with the rapid rate and increasing severity of climate change, leaving disaster managers dependent on tools which are increasingly unrepresentative of complex interactions between fire behavior, environmental conditions, and various mitigation options. This has consequences for equitably minimizing wildfire risks to life, property, ecology, cultural heritage, and public health. Fortunately, decades of data exist for fuel populations, weather conditions, and outcomes of significant fires in the American West and globally. The fire management community faces a lack of data standardization and validation among many competing fire models. Likewise, the machine learning community lacks curated datasets and benchmarks to develop solutions necessary to generate impact in this space. We present a novel dataset composed of 308 medium sized fires from the years 2018-2021, complete with both time series airborne based inference and ground operational estimation of fire extent, and operational mitigation data such as control line construction. As the first large wildfire dataset with mitigation information, Burn Mitigation Dataset (BurnMD) will help advance fire projection modeling, fire risk modeling, and AI generated land management policies.

Integration of variable renewable energy into the grid has posed challenges to system operators in achieving optimal trade-offs among energy availability, cost affordability, and pollution controllability. This paper proposes a multi-agent reinforcement learning framework for managing energy transactions in microgrids. The framework addresses the challenges above: it seeks to optimize the usage of available resources by minimizing the carbon footprint while benefiting all stakeholders. The proposed architecture consists of three layers of agents, each pursuing different objectives. The first layer, comprised of prosumers and consumers, minimizes the total energy cost. The other two layers control the energy price to decrease the carbon impact while balancing the consumption and production of both renewable and conventional energy. This framework also takes into account fluctuations in energy demand and supply.

Given the current context of climate change and the increasing population densities at coastal zones around the globe, there is an increasing need to be able to predict the development of our coasts. Recent advances in artificial intelligence allow for automatic analysis of observational data. Symbolic Regression (SR) is a type of Machine Learning algorithm that aims to find interpretable symbolic expressions that can explain relations in the data. In this work, we aim to study the problem of forecasting shoreline change using SR. We make use of Cartesian Genetic Programming (CGP) in order to encode and improve upon ShoreFor, a physical shoreline prediction model. During training, CGP individuals are evaluated and selected according to their predictive score at five different coastal sites. This work presents a comparison between a CGP-evolved model and the base ShoreFor model. In addition to evolution's ability to produce well-performing models, it demonstrates the usefulness of SR as a research tool to gain insight into the behaviors of shorelines in various geographical zones.

In the context of climate change, wildfires are becoming more frequent, intense, and prolonged in the western US, particularly in California. Wildfires cause catastrophic socio-economic losses and are projected to worsen in the near future. Inaccurate estimates of fire risk put further pressure on wildfire (re)insurance and cause many homes to lose wildfire insurance coverage. Efficient and effective prediction of fire ignition is one step towards better fire risk assessment. Here we present a simplified machine learning-based fire ignition model at yearly scale that is well suited to the use case of one-year term wildfire (re)insurance. Our model yields a recall, precision, and the area under the precision-recall curve of 0.69, 0.86 and 0.81, respectively, for California, and significantly higher values of 0.82, 0.90 and 0.90, respectively, for the populated area, indicating its good performance. In addition, our model feature analysis reveals that power line density, enhanced vegetation index (EVI), vegetation optical depth (VOD), and distance to the wildland-urban interface stand out as the most important features determining ignitions. The framework of this simplified ignition model could easily be applied to other regions or genesis of other perils like hurricane, and it paves the road to a broader and more affordable safety net for homeowners.

Satellite altimeter observations retrieved since 1993 show that the global mean sea level is rising at an unprecedented rate (3.4mm/year). With almost three decades of observations, we can now investigate the contributions of anthropogenic climate-change signals such as greenhouse gases, aerosols, and biomass burning in this rising sea level. We use machine learning (ML) to investigate future patterns of sea level change. To understand the extent of contributions from the climate-change signals, and to help in forecasting sea level change in the future, we turn to climate model simulations. This work presents a machine learning framework that exploits both satellite observations and climate model simulations to generate sea level rise projections at a 2-degree resolution spatial grid, 30 years into the future. We train fully connected neural networks (FCNNs) to predict altimeter values through a non-linear fusion of the climate model hindcasts (for 1993-2019). The learned FCNNs are then applied to future climate model projections to predict future sea level patterns. We propose segmenting our spatial dataset into meaningful clusters and show that spectral clustering helps to improve predictions of our ML model.

As the buildings sector represents over 70% of the total U.S. electricity consumption, it offers a great amount of untapped demand-side resources to tackle many critical grid-side problems and improve the overall energy system's efficiency. To help make buildings grid-interactive, this paper proposes a global-local policy search method to train a reinforcement learning (RL) based controller which optimizes building operation during both normal hours and demand response (DR) events. Experiments on a simulated five-zone commercial building demonstrate that by adding a local fine-tuning stage to the evolution strategy policy training process, the control costs can be further reduced by 7.55% in unseen testing scenarios. Baseline comparison also indicates that the learned RL controller outperforms a pragmatic linear model predictive controller (MPC), while not requiring intensive online computation.

Deep learning has experienced significant growth in recent years, resulting in increased energy consumption and carbon emission from the use of GPUs for training deep neural networks (DNNs). Answering the call for sustainability, conventional solutions have attempted to move training jobs to locations or time frames with lower carbon intensity. However, moving jobs to other locations may not always be feasible due to large dataset sizes or data regulations. Moreover, postponing training can negatively impact application service quality because the DNNs backing the service are not updated in a timely fashion. In this work, we present a practical solution that reduces the carbon footprint of DNN training without migrating or postponing jobs. Specifically, our solution observes real-time carbon intensity shifts during training and controls the energy consumption of GPUs, thereby reducing carbon footprint while maintaining training performance. Furthermore, in order to proactively adapt to shifting carbon intensity, we propose a lightweight machine learning algorithm that predicts the carbon intensity of the upcoming time frame. Our solution, Chase, reduces the total carbon footprint of training ResNet-50 on ImageNet by 13.6% while only increasing training time by 2.5%.

Maintaining the integrity of solar power plants is a vital component in dealingwith the current climate crisis. This process begins with analysts creating a de-tailed map of a plant with the coordinates of every solar panel, making it possibleto quickly locate and mitigate potential faulty solar panels. However, this taskis extremely tedious and is not scalable for the ever increasing capacity of so-lar power across the globe. Therefore, we propose an end-to-end deep learningframework for detecting individual solar panels using a rotated object detectionarchitecture. We evaluate our approach on a diverse dataset of solar power plantscollected from across the United States and report a mAP score of 83.3%.

The accelerated pace of environmental change due to anthropogenic activities makes it more important than ever to understand current and future ecosystem dynamics at a global scale. Species observations stemming from citizen science platforms are increasingly leveraged to gather information about the geographic distributions of many species. However, their usability is limited by the strong biases inherent to these community-driven efforts. These biases in the sampling effort are often treated as noise that has to be compensated for. In this project, we posit that better modelling the sampling effort (including the usage of the different platforms across countries, local accessibility, attractiveness of the location for platform users, affinity of different user groups for different species, etc.) is the key towards improving Species Distribution Models (SDM) using observations from citizen science platforms, thus opening up the possibility of leveraging them to monitor changes in species distributions and population densities.

Reaching net zero emissions requires rapid innovation and scale-up of clean tech. In this context, clean tech innovation networks (CTINs) can play a crucial role by pooling necessary resources and competences and enabling knowledge transfers between different actors. However, existing evidence on CTINs is limited due to a lack of comprehensive data. Here, we develop a machine learning framework to identify CTINs from announcements on social media to map the global CTIN landscape. Specifically, we classify the social media announcements regarding the type of technology (e.g., hydrogen, solar), interaction type (e.g., equity investment, R\&D collaboration), and status (e.g., commencement, update). We then extract referenced organizations via entity recognition. Thereby, we generate a large-scale dataset of CTINs across different technologies, countries, and over time. This allows us to compare characteristics of CTINs, such as the geographic proximity of actors, and to investigate the association between network evolution and technology innovation and diffusion. As a direct implication, our work helps policy makers to promote CTINs by identifying current barriers and needs.

Carbon offset programs are critical in the fight against climate change. One emerging threat to the long-term stability of offset credits is wildfires, which can destroy forest offset projects and associated credits. However, analysis of carbon offset fire risk is challenging because existing models for forecasting long-term fire risk are limited in resolution and skill. Therefore, we propose an interpretable deep learning model trained on millions of global satellite wildfire observations. Validation results suggest substantial potential for high resolution, enhanced accuracy projections of global wildfire risk, and the model outperforms the U.S. National Center for Atmospheric Research's leading fire model. Applied to a collection of active U.S. forest carbon projects, we find that fire exposure is projected to increase 64% [48-96%] by 2080 under a mid-range scenario. Our results indicate the large wildfire carbon credit losses seen in the past decade in the U.S. are likely to become more frequent as forests become hotter and drier. In response, we hope the model can support wildfire managers, policymakers, and carbon market analysts to quantify and mitigate long-term risks to forest carbon offsets.

Finding a balance between collaboration and competition is crucial for artificial agents in many real-world applications. We investigate this using a Multi-Agent Reinforcement Learning (MARL) setup with the ability to collaborate and communicate on the back of a high-impact problem. The accumulation and yearly growth of plastic in the ocean cause irreparable damage to many aspects of oceanic health and the marina system. To prevent further damage, we need to find ways to reduce macroplastics from known plastic patches in the ocean. Here we propose a Graph Neural Network (GNN) based communication mechanism that increases the agents' observation space. In our custom environment, an agent controls a macroplastics collecting vessel. Our communication mechanism allows vessels to share information on nearby macroplastics. While the goal of the agent collective is to clean up as much as possible, agents are rewarded for the individual amount of macroplastics collected. Hence agents have to learn to communicate effectively while maintaining high individual performance. We compare our proposed communication mechanism with a multi-agent baseline without the ability to communicate. Results show how communication enables collaboration and increases collective performance significantly. This ultimately means that agents have learned the importance of communication and found a high-performing balance between collaboration and competition.

Sub-seasonal to seasonal (S2S) weather forecasts are an important decision-making tool that informs economical and logistical planning in agriculture,energy management, and disaster mitigation. They are issued on time scalesof weeks to months and differ from short-term weather forecasts in twoimportant ways: (i) the dynamics of the atmosphere on these timescales canbe described only statistically and (ii) these dynamics are characterized bylarge-scale phenomena in both space and time. While deep learning (DL)has shown promising results in short-term weather forecasting, DL-basedS2S forecasts are challenged by comparatively small volumes of availabletraining data and large fluctuations in predictability due to atmosphericconditions. In order to develop more reliable S2S predictions that leveragecurrent advances in DL, we propose to utilize the masked auto-encoder(MAE) framework to learn generic representations of large-scale atmosphericphenomena from high resolution global data. Besides exploring the suitabilityof the learned representations for S2S forecasting, we will also examinewhether they account for climatic phenomena (e.g., the Madden-JulianOscillation) that are known to increase predictability on S2S timescales.

With the goal of understanding effective strategies to communicate about climate change, we build interpretable models to rank tweets related to climate change with respect to the engagement they generate. Our models are based on the Bradley-Terry model of pairwise comparison outcomes and use a combination of the tweets’ topic and metadata features to do the ranking. To remove confounding factors related to author popularity and minimise noise, they are trained on pairs of tweets that are from the same author and around the same time period and have a sufficiently large difference in engagement. The models achieve good accuracy on a held-out set of pairs. We show that we can interpret the parameters of the trained model to identify the topic and metadata features that contribute to high engagement. Among other observations, we see that topics related to climate projections, human cost and deaths tend to have low engagement while those related to mitigation and adaptation strategies have high engagement. We hope the insights gained from this study will help craft effective climate communication to promote engagement, thereby lending strength to efforts to tackle climate change.

Sea surface temperature (SST) forecasts help with managing the marine ecosystem and the aquaculture impacted by anthropogenic climate change. Numerical dynamical models are resource intensive for SST forecasts; machine learning (ML) models could reduce high computational requirements and have been in the focus of the research community recently. ML models normally require a large amount of data for training; environmental data are collected on regularly-spaced grids, so early work mainly used grid-based deep learning (DL) for prediction. However, both grid data and the corresponding DL approaches have inherent problems. As geometric DL has emerged, graphs as a more generalized data structure and graph neural networks (GNNs) have been introduced to the spatiotemporal domains. In this work, we preliminarily explored graph re-sampling and GNNs for global SST forecasts, and GNNs show better one month ahead SST prediction than the persistence model in most oceans in terms of root mean square errors.

This paper proposes an activity prediction framework for a multi-agent recommendation system to tackle the energy-efficiency problem in residential buildings. Our system generates an activity-shifting schedule based on the social practices from the users’ domestic life. We further provide a utility option for the recommender system to focus on saving CO2 emissions or energy costs, or both. The empirical results show that while focusing on the reduction of CO2 emissions, the system provides an average of 12% of emission savings and 7% of electricity cost savings. When concentrating on energy costs, 6% of emission savings and 20% of electricity cost savings are possible for the studied households.

The large-scale deployment of renewable energy is the key pillar to achieve carbon-neutral energy systems and as part of this transition, PV has a crucial role as an affordable, clean energy. To promote PV expansion, policy designs have been developed which rely on yield maximization to increase the total PV energy supply in energy systems. Focusing on yield maximization, however, ignores negative side-effects such as an increased variability due to similar-orientated PV systems at clustered regions. This paper introduces a data-driven method based on the well-studied findings from modern portfolio theory to derive mean-variability balanced PV portfolios with smartly orientated tilt and azimuth angles. The formulated non-convex optimization problem is solved based on automatically differentiating the physical PV conversion model subject to individual tilt and azimuth angles of representative grid points. To illustrate the performance of the proposed method, a case study is designed to derive efficient frontiers in the mean-variability spectrum of Germany's PV portfolio. The proposed method allows decision-makers to hedge between uncertainty and yield of PV portfolios making it attractive as a tool for policy design. This is the first study highlighting the problem of ignoring the uncertainty within yield maximization policy schemes and introduces a method how to tackle this issue using modern methods inspired by Machine Learning.

Earth System Models (ESMs) are essential tools for understanding the impact of human actions on Earth's climate. One key application of these models is studying extreme weather events, such as heat waves or dry spells, which have significant socioeconomic consequences. However, the computational demands of running a sufficient number of simulations to analyze the risks are often prohibitive. In this paper we demonstrate that diffusion models -- a class of generative deep learning models -- can effectively emulate the spatio-temporal trends of ESMs under previously unseen climate scenarios, while only requiring a small fraction of the computational resources. We present a diffusion model that is conditioned on monthly averages of temperature or precipitation on a 96x96 global grid, and produces daily values that are both realistic and consistent with those averages. Our results show that the output from our diffusion model closely matches the spatio-temporal behavior of the ESM it emulates in terms of the frequency of phenomena such as heat waves, dry spells, or rainfall intensity.

Recently, Deep Learning has emerged as a promising tool for statistical downscaling, the set of methods for generating high-resolution climate fields from coarse low-resolution variables. Nevertheless, their ability to generalize to climate change conditions remains questionable, mainly due to the stationarity assumption. We propose deep ensembles as a simple method to improve the uncertainty quantification of statistical downscaling models. Since no observational future data exists, we rely on a pseudo reality experiment to assess the suitability of deep ensembles for quantifying the uncertainty of climate change projections. Deep ensembles allow for a better risk assessment, highly demanded by sectoral applications to tackle climate change.

Severe hailstorms are responsible for some of the most costly insured weather events in Australia and can cause significant damage to homes, businesses, and agriculture. However their response to climate change remains uncertain, in large part due to the challenges of observing severe hailstorms. We propose a novel Bayesian approach which explicitly models known biases and uncertainties of current hail observations to produce more realistic estimates of severe hail risk. Training this model on data from south-east Queensland, Australia, suggests that previous analyses of severe hail that did not account for this uncertainty may produce poorly calibrated risk estimates. Evaluation on withheld data confirms that our model produces well-calibrated probabilities and is applicable out of sample. Whilst developed for hail, we highlight also the generality of our model and its potential applications to other severe weather phenomena and areas of climate change adaptation and mitigation.

Species distribution models (SDMs) relate species occurrence data with environmental variables and are used to understand and predict species distributions across landscapes. While some machine learning models have been adopted by the SDM community, recent advances in neural networks may have untapped potential in this field. In this work, we compare the performance of multi-layer perceptron (MLP) neural networks to well-established SDM methods on a benchmark dataset spanning 225 species in six geographical regions. We also compare the performance of MLPs trained separately for each species to an equivalent model trained on a set of species and performing multi-label classification. Our results show that MLP models achieve comparable results to state-of-the-art SDM methods, such as MaxEnt. We also find that multi-species MLPs perform slightly better than single-species MLPs. This study indicates that neural networks, along with all their convenient and valuable characteristics, are worth considering for SDMs.

Fourier Neural Operators (FNOs) have established themselves as an efficientmethod for learning resolution-independent operators in a wide range of scientificmachine learning applications. This can be attributed to their ability to effectivelymodel long-range dependencies in spatio-temporal data through computationally ef-ficient global convolutions. However, the use of discrete Fourier transforms (DFTs)in FNOs leads to spurious artifacts and pronounced dissipation when applied tospherical coordinates, due to the incorrect assumption of flat geometry. To ad-dress the issue, we introduce Spherical FNOs (SFNOs), which use the generalizedFourier transform for learning operators on spherical geometries. We demonstratethe effectiveness of the method for forecasting atmospheric dynamics, producingstable auto-regressive results for a simulated time of one year (1,460 steps) whileretaining physically plausible dynamics. This development has significant implica-tions for machine learning-based climate dynamics emulation, which could play acrucial role in accelerating our response to climate change.

The direct current open energy system (DCOES) enables the production, storage, and exchange of renewable energy within local communities, which is helpful, especially in isolated villages and islands where centralized power supply is unavailable or unstable. As solar and wind energy production varies in time and space depending on the weather and the energy usage patterns differ for different households, how to store and exchange energy is an important research issue. In this work, we explore the use of deep reinforcement learning (DRL) for adaptive control of energy storage in local batteries and energy sharing through local DC grids. We extend the Autonomous Power Interchange System (APIS) emulator from SONY to combine it with reinforcement learning algorithms in each house. We implemented deep Q-network (DQN) and prioritized DQN to dynamically set the parameters of the real-time energy exchange protocol of APIS and tested it using the actual data collected from the DCOES in the faculty houses of Okinawa Institute of Science and Technology (OIST). The simulation results showed that RL agents outperformed the hand-tuned control strategy. Sharing average energy production, storage, and usage within the local community further improved the efficiency.

We introduce REmap, a web-based data-mining visualization tool of the spatial and temporal variability of wind resources. It uses the latest open-access dataset of the daily wind capacity factor in 28 European countries between 1979 and 2019 and proposes several user-configurable visualizations of the temporal and spatial variations of the wind power capacity factor. The platform allows for a deep analysis of the distribution, the cross-country correlation, and the drivers of low wind power events. It offers an easy-to-use interface that makes it suitable for the needs of researchers and stakeholders. The tool is expected to be useful in identifying areas of high wind potential and possible challenges that may impact the large-scale deployment of wind turbines in Europe. Particular importance is given to the visualization of low wind power events and to the potential of cross-border cooperations in mitigating the variability of wind in the context of increasing reliance on weather-sensitive renewable energy sources.

Increases in drought frequency, intensity, and duration due to climate change are threatening forests around the world. Climate-driven tree mortality is associated with devastating ecological and societal consequences, including the loss of carbon sequestration, habitat provisioning, and water filtration services. A spatially fine-grained understanding of the site characteristics making forests more resilient to drought is still lacking. Furthermore, the complexity of drought effects on forests, which can be cumulative and delayed, demands investigation of the most appropriate drought indices. In this study, we aim to gain a better understanding of the temporal and spatial drivers of drought-induced changes in forest vitality using Shapley values, which allow for the relevance of predictors to be quantified locally. A better understanding of the contribution of meteorological and environmental factors to trees’ response to drought can support forest managers aiming to make forests more climate-resilient.

We propose a novel method for the bias adjustment and post-processing of gridded rainfall data products. Our method uses U-Net (a deep convolutional neural network) as a backbone, and a novel loss function given by the combination of a pixelwise bias component (Mean Absolute Error) and a spatial accuracy component (Fractions Skill Score). We evaluate the proposed approach by adjusting extreme rainfall from the popular ERA5 reanalysis dataset, using the multi-source observational dataset MSWEP as a target. We focus on a sample of extreme rainfall events induced by tropical cyclones and show that the proposed method significantly reduces both the MAE (by 16\%) and FSS (by 53\%) of ERA5.

Accurate wind turbine power curve models, which translate ambient conditions into turbine power output, are crucial for wind energy to scale and fulfill its proposed role in the global energy transition. While machine learning (ML) methods have shown significant advantages over parametric, physics-informed approaches, they are often criticized for being opaque "black boxes", which hinders their application in practice. We apply Shapley values, a popular explainable artificial intelligence (XAI) method, and the latest findings from XAI for regression models, to uncover the strategies ML models have learned from operational wind turbine data. Our findings reveal that the trend towards ever larger model architectures, driven by a focus on test set performance, can result in physically implausible model strategies. Therefore, we call for a more prominent role of XAI methods in model selection. Moreover, we propose a practical approach to utilize explanations for root cause analysis in the context of wind turbine performance monitoring. This can help to reduce downtime and increase the utilization of turbines in the field.

The world’s oceans are polluted with plastic waste and the detection of it is an important step toward removing it. Wolf et al. (2020) created a plastic waste dataset to develop a plastic detection system. Our work aims to improve the machine learning model by using Green Automated Machine Learning (AutoML). One aspect of Green-AutoML is to search for a machine learning pipeline while additionally minimizing the carbon footprint. In this work, we train five standard neural architectures for image classification on the aforementioned plastic waste dataset. Subsequently, their performance and carbon footprints are compared to an Efficient Neural Architecture Search as a well-known AutoML approach. We show the potential of Green-AutoML by outperforming the original plastic detection system by 1.1% in accuracy and using 33 times fewer floating point operations at inference, and only 28% of the carbon emissions of the best known baseline. This shows the large potential of AutoML on climate-change relevant applications and at the same time contributing to more efficient modern DL systems, saving substantial resources and reducing the carbon footprint.

Climate change is expected to have a dramatic impact on agricultural production; however, due to natural complexity, the exact avenues and relative strengths by which this will happen are still unknown. The development of accurate forecasting models is thus of great importance to enable policy makers to design effective interventions. To date, most machine learning methods aimed at tackling this problem lack a consideration of causal structure, thereby making them unreliable for the types of counterfactual analysis necessary when making policy decisions. Econometrics has developed robust techniques for estimating cause-effect relations in time-series, specifically through the use of cointegration analysis and Granger causality. However, these methods are frequently limited in flexibility, especially in the estimation of nonlinear relationships. In this work, we propose to integrate the non-linear function approximators with the robust causal estimation methods to ultimately develop an accurate agricultural forecasting model capable of robust counterfactual analysis. This method would be a valuable new asset for government and industrial stakeholders to understand how climate change impacts agricultural production.

Machine learning is one of the fastest growing services in modern hyperscale data centers. While AI’s exponential scaling has enabled unprecedented modeling capabilities across computer vision, natural language processing, protein modeling, personalized recommendation, it comes at the expense of significant energy and environmental footprints. This work aims to co-optimize machine learning models in terms of their accuracy, compute efficiency, and environmental sustainability by using multi-objective bayesian optimization. We aim to extend current multi-objective optimization frameworks, such as the openly available Ax (adaptive experimentation) platform to balance accuracy, efficiency, and environmental sustainability of deep neural networks. In order to optimize for environmental sustainability we will consider the impact across AI model life cycles (e.g., training, inference) and hardware life cycles (e.g., manufacturing, operational use). Given this is a research proposal, we expect to demonstrate that designing for sustainable AI models yields distinct optimal neural network architectures than ones designed for accuracy and efficiency given the external impacts of varying renewable energy and tradeoffs between compute and storage for embodied carbon overheads.

Rainfall data collected by various remote sensing instruments such as radars or satellites has different space-time resolutions. This study aims to improve the temporal resolution of radar rainfall products to help with more accurate climate change modeling and studies. In this direction, we introduce a solution based on EfficientNetV2, namely EfficientTempNet, to increase the temporal resolution of radar-based rainfall products from 10 minutes to 5 minutes. We tested EfficientRainNet over a dataset for the state of Iowa, US, and compared its performance to three different baselines to show that EfficientTempNet presents a viable option for better climate change monitoring.

Running climate simulations informs us of future climate change. However, it is computationally expensive to resolve complex climate processes numerically. As one way to speed up climate simulations, neural networks have been used to downscale climate variables from fast-running low-resolution simulations. So far, all neural network downscaling models can only downscale input samples with a pre-defined upsampling factor. In this work, we propose a Fourier neural operator downscaling model. It trains with data of a small upsampling factor and then can zero-shot downscale its input to arbitrary unseen high-resolutions. Evaluated on Navier-Stokes equation solution data and ERA5 water content data, our downscaling model demonstrates better performance than widely used convolutional and adversarial generative super-resolution models in both learned and zero-shot downscaling. Our model's performance is further boosted when a constraint layer is applied. In the end, we show that by combining our downscaling model with a low-resolution numerical PDE solver, the downscaled solution outperforms the solution of the state-of-the-art high-resolution data-driven solver. Our model can be used to cheaply and accurately generate arbitrarily high-resolution climate simulation data with fast-running low-resolution simulation as input.

Decision-making under uncertainty is an important problem that arises in many domains. Achieving robustness guarantees requires well-calibrated uncertainties, which can be difficult to achieve in high-capacity prediction models such as deep neural networks. This paper proposes an end-to-end approach for learning uncertainty-calibrated deep learning models that directly optimizes a downstream decision-making objective with provable robustness. We also propose two concrete applications in energy system operations, including a grid scheduling task as well as an energy storage arbitrage task. As renewable wind and solar generation increasingly proliferate and their variability penetrates the energy grid, learning uncertainty-aware predictive models becomes increasingly crucial for maintaining efficient and reliable grid operation.

The increased uptake of solar energy in the energy transition towards decarbonization has caused the issue of solar photovoltaic (PV) curtailments, resulting in significant economic losses and hindering the energy transition. To overcome this issue, battery energy storage systems (BESS) can serve as onsite backup sources for solar farms. However, the backup role of the BESS significantly limits its economic value, disincentivizing the BESS deployment due to high investment costs. Hence, it is essential to effectively reduce solar curtailment while ensuring viable operations of the BESS. To better understand the synergy of a co-located solar-BESS system in the real-time electricity market, we model the cooperative bidding processes of the solar farm and the BESS as a Markov game. We use a multi-agent deep reinforcement learning (MADRL) algorithm, known as multi-agent deep deterministic policy gradient, to concurrently maximize the overall revenue from the electricity market and reduce solar curtailments. We validate our MADRL-based strategy using data from a realistic solar farm operating in the Australian electricity market. The simulation results show that our MADRL-based coordinated bidding strategy outperforms both optimization-based and DRL-based benchmarks, generating higher revenue for the BESS and reducing more solar curtailments. Our work highlights the importance of coordination between the BESS and renewable generations for both economic benefits and progress towards net-zero transitions.

The climate penalty measures the effects of a changing climate on air quality due to the interaction of pollution with climate factors, independently of future changes in emissions. This work introduces a statistical framework for estimating the climate penalty on soot pollution (PM 2.5), which has been linked to respiratory and cardiovascular diseases and premature mortality. The framework is used to evaluate the disparities in future PM 2.5 exposure across racial/ethnic and income groups. The findings of this study have the potential to inform mitigation policy aiming to protect public health and promote environmental equity in addressing the effects of climate change. The proposed methodology significantly improves upon existing statistical-based methods for estimating the climate penalty. It will use higher-resolution climate inputs---which current statistical approaches cannot accommodate---using an expressive and scalable predictive model based on spatial deep learning with spatiotemporal trend estimation. It will also integrate additional predictive data sources such as demographics and geology. This approach allows us to consider regional dependencies and synoptic weather patterns that influence PM 2.5 and deconvolve them from the effects of exogenous factors, such as the trends in increasing air quality regulations and other sources of unmeasured spatial heterogeneity.

In this paper, we compare the improvement of probabilistic electricity demand forecasts for three specific coastal and island regions using raw and pre-computed meteorological features based on empirically-tested formulations drawn from climate science literature. Typically for the general task of time-series forecasting with strong weather/climate drivers, go-to models like the Autoregressive Integrated Moving Average (ARIMA) model are built with assumptions of how independent variables will affect a dependent one and are at best encoded with a handful of exogenous features with known impact. Depending on the geographical region and/or cultural practices of a population, such a selection process may yield a non-optimal feature set which would ultimately drive a weak impact on underline demand forecasts. The aim of this work is to assess the impact of a documented set of meteorological features on electricity demand using deep learning models in comparative studies. Leveraging the defining computational architecture of the Temporal Fusion Transformer (TFT), we discover the unimportance of weather features for improving probabilistic forecasts for the targeted regions. However, through experimentation, we discover that the more stable electricity demand of the coastal Mediterranean regions, the Ceuta and Melilla autonomous cities in Morocco, improved the forecast accuracy of the strongly tourist-driven electricity demand for the Balearic islands located in Spain during the time of travel restrictions (i.e., during COVID19 (2020))--a root mean squared error (RMSE) from ~0.090 to ~0.012 with a substantially improved 10th/90th quantile bounding.

Tropical cyclones (TC) in Bangladesh and other developing nations harm property and human lives. Theoretically, artificial intelligence (AI) can anticipate TC using tracking, intensity, and cyclone aftereffect phenomena. Although AI has a significant impact on predicting, poorer nations have struggled to adjust to its real-world applications. The interpretability of such a solution from an AI-based solution is the main factor in that situation, together with the infrastructure. Explainable AI has been extensively employed in the medical field because the outcome is so important. We believe that using explainable AI in TC forecasting is equally important as one large forecast can cause the thought of life loss. Additionally, it will improve the long-term viability of the AI-based weather forecasting system. To be more specific, we want to employ explainable AI in every way feasible in this study to address the problems of TC forecasting, intensity estimate, and tracking. We'll do this by using the graph neural network. The adoption of AI-based solutions in underdeveloped nations will be aided by this solution, which will boost their acceptance. With this effort, we also hope to tackle the challenge of sustainableAI in order to tackle the issue of climate change on a larger scale. However, Cyclone forecasting might be transformed by sustainable AI, guaranteeing precise and early predictions to lessen the effects of these deadly storms. The examination of vast volumes of meteorological data to increase forecasting accuracy is made possible by the combination of AI algorithms and cutting-edge technologies like machine learning and big data analytics. Improved accuracy is one of the main advantages of sustainable AI for cyclone prediction. To provide more preciseforecasts, AI systems can evaluate a lot of meteorological data, including satellite imagery and ocean temperature readings.

Industrial air pollution has a direct health impact and is a major contributor to climate change. Small scale industries particularly bull-trench brick kilns are one of the major causes of air pollution in South Asia often creating hazardous levels of smog that is injurious to human health. To mitigate the climate and health impact of the kiln industry, fine-grained kiln localization at different geographic locations is needed. Kiln localization using multi-spectral remote sensing data such as vegetation index results in a noisy estimates whereas use of high-resolution imagery is infeasible due to cost and compute complexities. This paper proposes a fusion of spatio-temporal multi-spectral data with high-resolution imagery for detection of brick kilns within the "Brick-Kiln-Belt" of South Asia. We first perform classification using low-resolution spatio-temporal multi-spectral data from Sentinel-2 imagery by combining vegetation, burn, build up and moisture indices. Then orientation aware object detector: YOLOv3 (with theta value) is implemented for removal of false detections and fine-grained localization. Our proposed technique, when compared with other benchmarks, results in a 21 times improvement in speed with comparable or higher accuracy when tested over multiple countries.

Project Suncatcher estimates the solar potential of residential buildings usinghigh quality aerial data. That is, it estimates the potential solar energy (and associated financial savings) that can be captured by buildings if solar panels were to be installed on their roofs. Unfortunately its coverage is limited by the lackof high resolution digital surface map (DSM) data. We present a deep learningapproach that bridges this gap by enhancing widely available low-resolution data,thereby dramatically increasing the coverage of Suncatcher. We also present someongoing efforts to potentially improve accuracy even further by replacing certainalgorithmic components of Suncatcher’s processing pipeline with deep learning.

Understanding and properly estimating the impacts of environmental interventions is of critical importance as we work towards achieving global climate goals. Remote sensing has become an essential tool for evaluating when and where climate policies have positive impacts on factors like greenhouse gas emissions and carbon sequestration. However, when machine learning models trained to predict outcomes using remotely sensed data simply minimize a standard loss function, the predictions that they generate can produce biased estimates in downstream causal inference. If prediction error in the outcome variable is correlated with policy variables or important confounders, as is the case for many widely used remote sensing data sets, estimates of the causal impacts of policies can be biased. In this paper, we demonstrate how this bias can arise, and we propose the use of an adversarial debiasing model (Zhang, Lemoine, and Mitchell 2018) in order to correct the issue when using satellite data to generate machine learning predictions for use in causal inference. We apply this method to a case study of the relationship between roads and tree cover in West Africa, where our results indicate that adversarial debiasing can recover a much more accurate estimate of the parameter of interest compared to when the standard approach is used.

Carbon capture and storage (CCS) plays an essential role in global decarbonization. Scaling up CCS requires accurate and high-resolution modeling of the storage reservoir pressure buildup and the gaseous plume migration. However, such modeling is very challenging at scale due to the high computational costs of existing numerical methods. This challenge leads to significant uncertainty in evaluating storage opportunities which can delay the pace of global CCS deployments. We introduce a machine-learning approach for dynamic basin-scale modeling that speeds up flow prediction nearly 700,000 times compared to existing methods. Our framework, Nested Fourier Neural Operator (FNO), provides a general-purpose simulator alternative under diverse reservoir conditions, geological heterogeneity, and injection schemes. It enables unprecedented real-time high-fidelity modeling to support decision-making in basin-scale CCS projects.

Modern machine learning models have started to consume incredible amounts of energy, thus incurring large carbon footprints (Strubell et al., 2019). To address this issue, we have created an energy estimation pipeline, which allows practitioners to estimate the energy needs of their models in advance, without actually running or training them. We accomplished this, by collecting high-quality energy data and building a first baseline model, capable of predicting the energy consumption of DL models by accumulating their estimated layer-wise energies.

Cities represent both a fundamental contributor to greenhouse (GHG) emissions and a catalyst for climate action. Many global cities have outlined sustainability and climate change mitigation plans, focusing on energy efficiency, shifting away from fossil fuels, and prioritizing environmental and social justice. To achieve broad-based and equitable carbon emissions reductions and sustainability goals, new data-driven methodologies are needed to identify and target efficiency and carbon reduction opportunities in the built environment at the building, neighborhood, and city-scale. Our methodology integrates data from numerous data sources and develops data-driven and physical models of energy use and carbon emissions from buildings and transportation to generate a high spatiotemporal resolution model of urban greenhouse gas emissions. The method and data tool are designed to support city leaders and urban policymakers with an unprecedented view of localized carbon emissions to enable data-driven and evidenced-based climate action.

Recent data-driven approaches based on machine learning aim to directly solve a downstream forecasting or projection task by learning a data-driven functional mapping using deep neural networks. However, these networks are trained using curated and homogeneous climate datasets for specific spatiotemporal tasks, and thus lack the generality of currently used physics-informed numerical models for weather and climate modeling. We develop and demonstrate ClimaX, a flexible and generalizable deep learning model for weather and climate science that can be trained using heterogeneous datasets spanning different variables, spatiotemporal coverage, and physical groundings. ClimaX extends the Transformer architecture with novel encoding and aggregation blocks that allow effective use of available compute and data while maintaining general utility. ClimaX is pre-trained with a self-supervised learning objective on climate datasets derived from CMIP6. The pretrained ClimaX can then be fine-tuned to address a breadth of climate and weather tasks, including those that involve atmospheric variables and spatiotemporal scales unseen during pretraining. Compared to existing data-driven baselines, we show that this generality in ClimaX results in superior performance on benchmarks for weather forecasting and climate projections.

Planning optimization of gas networks under emission constraints prioritizes gas supply with the smallest emission footprint. As this problem includes complex gas flow physical laws, standard optimization solvers cannot guarantee convergence to a feasible solution, especially under strict emission constraints. To address this issue, we develop an input-convex neural network (ICNN) aided optimization routine which incorporates a set of trained ICNNs approximating the gas flow equations with high precision. Numerical tests on the Belgium gas network demonstrate that the ICNN-aided optimization dominates non-convex and relaxation-based solvers, with larger optimality gains pertaining to stricter emission targets.

Climate change is a major driver of biodiversity loss, changing the geographicrange and abundance of many species. However, there remain significant knowl-edge gaps about the distribution of species, due principally to the amount of effortand expertise required for traditional field monitoring. We propose an approachleveraging computer vision to improve species distribution modelling, combiningthe wide availability of remote sensing data with sparse on-ground citizen sciencedata from .We introduce a novel task and dataset for mapping US bird species totheir habitats by predicting species encounter rates from satellite images, alongwith baseline models which demonstrate the power of our approach. Our methodsopen up possibilities for scalably modelling ecosystems properties worldwide.

Subgrid parameterizations that represent physical processes occurring below the resolution of current climate models are an important component in producing accurate, long-term predictions for the climate. A variety of approaches have been tested to design these components, including deep learning methods. In this work, we evaluate a proof of concept illustrating a multiscale approach to this prediction problem. We train neural networks to predict subgrid forcing values on a testbed model and examine improvements in prediction accuracy which can be obtained by using additional information in both fine-to-coarse and coarse-to-fine directions.

Electric grids are the conduit for renewable energy delivery and will play a crucial role in mitigating climate change. To do so successfully in resource-constrained low- and middle-income countries (LMICs), increasing operational efficiency is key. Such efficiency demands evolving knowledge of the grid’s state, of which topology---how points on the network are physically connected---is fundamental. In LMICs, knowledge of distribution topology is limited and established methods for topology estimation rely on expensive sensing infrastructure, such as smart meters or PMUs, that are inaccessible at scale. This paper lays the foundation for topology estimation from more accessible data: outlet-level voltage magnitude measurements. It presents a graph-based algorithm and explanatory visualization using the Fielder vector for estimating and communicating topological proximity from this data. We demonstrate the method on a real dataset collected in Accra, Ghana, thus opening the possibility of globally accessible, cutting-edge grid monitoring through non-traditional sensing strategies coupled with ML.

Heating and cooling comprise a significant fraction of the energy consumed by buildings, which in turn account for a significant fraction of society’s energy use. Most building heating, ventilation, and air conditioning (HVAC) systems use standard control schemes that meet basic operating constraints and comfort requirements but with suboptimal efficiency. Deep reinforcement learning (DRL) has shown immense potential for high-performing control in a variety of simulated settings, but has not been widely deployed for real-world control. Here we provide two contributions toward increasing the viability of real-world, DRL-based HVAC control, leveraging the EnergyPlus building simulator. First, we use the new EnergyPlus Python API to implement a first-of-its-kind, purely Python-based EnergyPlus DRL learning framework capable of generalizing to a wide variety of building configurations and weather scenarios. Second, we demonstrate an approach to constrained learning for this setting, removing the requirement to tune reward functions in order to maximize energy efficiency given temperature constraints. We tested our framework on realistic building models of a data center, an office building, and a secondary school. In each case, trained agents maintained temperature control while achieving energy savings relative to standard approaches.