Compressing multidimensional weather and climate data into neural networks
(In The Eleventh International Conference on Learning Representations, May 2023) Notable Top 5% (Oral)
Abstract
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 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.
Documents
download article: download slides:
Recorded talk (best effort)
BibTeX
@inproceedings{, author={Langwen Huang and Torsten Hoefler}, title={{Compressing multidimensional weather and climate data into neural networks}}, year={2023}, month={May}, booktitle={The Eleventh International Conference on Learning Representations}, source={http://www.unixer.de/~htor/publications/}, }
