Compressing high-resolution data through latent representation encoding for downscaling large-scale AI weather forecast model

TL;DR

This paper introduces a variational autoencoder-based method to compress high-resolution weather data, significantly reducing storage needs while maintaining data quality for accurate downscaling tasks.

Contribution

It presents a novel VAE framework for compressing large-scale weather datasets, enabling efficient storage and processing without sacrificing predictive accuracy.

Findings

Reduced data size from 8.61 TB to 204 GB

Maintained accuracy in downscaling tasks using compressed data

Demonstrated effectiveness on high-resolution Chinese weather data

Abstract

The rapid advancement of artificial intelligence (AI) in weather research has been driven by the ability to learn from large, high-dimensional datasets. However, this progress also poses significant challenges, particularly regarding the substantial costs associated with processing extensive data and the limitations of computational resources. Inspired by the Neural Image Compression (NIC) task in computer vision, this study seeks to compress weather data to address these challenges and enhance the efficiency of downstream applications. Specifically, we propose a variational autoencoder (VAE) framework tailored for compressing high-resolution datasets, specifically the High Resolution China Meteorological Administration Land Data Assimilation System (HRCLDAS) with a spatial resolution of 1 km. Our framework successfully reduced the storage size of 3 years of HRCLDAS data from 8.61 TB to just 204 GB, while preserving essential information. In addition, we demonstrated the utility of the compressed data through a downscaling task, where the model trained on the compressed dataset achieved accuracy comparable to that of the model trained on the original data. These results highlight the effectiveness and potential of the compressed data for future weather research.