In-Person Oral presentation / top 5% paper

Compressing multidimensional weather and climate data into neural networks

Langwen Huang · Torsten Hoefler

[ Abstract ] [ Livestream: Visit Oral 1 Track 2: Machine Learning for Sciences ]
Mon 1 May 1:20 a.m. — 1:30 a.m. PDT

Weather and climate simulations produce petabytes of high-resolution data that are later analyzed by researchers in order to understand climate change or severe weather. We propose a new method of compressing this multidimensional weather and climate data: a coordinate-based neural network is trained to overfit the data, and the resulting parameters are taken as a compact representation of the original grid-based data. While compression ratios range from 300x to more than 3,000x, our method outperforms the state-of-the-art compressor SZ3 in terms of weighted RMSE, MAE. It can faithfully preserve important large scale atmosphere structures and does not introduce significant artifacts.When using the resulting neural network as a 790x compressed dataloader to train the WeatherBench forecasting model, its RMSE increases by less than 2%. The three orders of magnitude compression democratizes access to high-resolution climate data and enables numerous new research directions.

Chat is not available.