Machine Learning Techniques for Data Reduction of Climate Applications

TL;DR

This paper introduces a neural-network-based data reduction pipeline for climate simulations that adaptively compresses regions of interest with high accuracy, significantly reducing data size while preserving essential physical phenomena.

Contribution

The paper presents a novel pipeline combining neural networks and a Guaranteed Autoencoder for targeted, high-precision data compression in climate applications, outperforming existing methods.

Findings

Achieves high compression ratios with minimal loss of critical information.

Effectively detects and preserves regions of interest such as cyclones and atmospheric rivers.

Outperforms comparable data compression techniques in climate data scenarios.

Abstract

Scientists conduct large-scale simulations to compute derived quantities-of-interest (QoI) from primary data. Often, QoI are linked to specific features, regions, or time intervals, such that data can be adaptively reduced without compromising the integrity of QoI. For many spatiotemporal applications, these QoI are binary in nature and represent presence or absence of a physical phenomenon. We present a pipelined compression approach that first uses neural-network-based techniques to derive regions where QoI are highly likely to be present. Then, we employ a Guaranteed Autoencoder (GAE) to compress data with differential error bounds. GAE uses QoI information to apply low-error compression to only these regions. This results in overall high compression ratios while still achieving downstream goals of simulation or data collections. Experimental results are presented for climate data generated from the E3SM Simulation model for downstream quantities such as tropical cyclone and atmospheric river detection and tracking. These results show that our approach is superior to comparable methods in the literature.