Lossy Neural Compression for Geospatial Analytics: A Review

2025-03-03

AI Summary

Earth observation (EO) and Earth system model (ESM) data pose significant compression challenges due to their massive scale, lack of labels, and strong spatiotemporal correlations. Method: This paper presents a systematic review of lossy neural compression (NC) techniques tailored to geospatial data, introducing the first cross-domain mapping framework linking EO/ESM data with NC. It proposes a novel inter-machine communication paradigm based on transferable compressed feature representations and integrates deep learning, information theory, and self-supervised foundation models to accommodate multimodal data—including optical imagery, synthetic aperture radar (SAR), and high-resolution meteorological simulations. Contribution/Results: The work clarifies recent advances of NC across major EO modalities, identifies critical research gaps in ESM compression, and delivers a comprehensive technology roadmap balancing industrial deployment requirements with scientific applicability.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Over the past decades, there has been an explosion in the amount of available Earth Observation (EO) data. The unprecedented coverage of the Earth's surface and atmosphere by satellite imagery has resulted in large volumes of data that must be transmitted to ground stations, stored in data centers, and distributed to end users. Modern Earth System Models (ESMs) face similar challenges, operating at high spatial and temporal resolutions, producing petabytes of data per simulated day. Data compression has gained relevance over the past decade, with neural compression (NC) emerging from deep learning and information theory, making EO data and ESM outputs ideal candidates due to their abundance of unlabeled data. In this review, we outline recent developments in NC applied to geospatial data. We introduce the fundamental concepts of NC including seminal works in its traditional applications to image and video compression domains with focus on lossy compression. We discuss the unique characteristics of EO and ESM data, contrasting them with"natural images", and explain the additional challenges and opportunities they present. Moreover, we review current applications of NC across various EO modalities and explore the limited efforts in ESM compression to date. The advent of self-supervised learning (SSL) and foundation models (FM) has advanced methods to efficiently distill representations from vast unlabeled data. We connect these developments to NC for EO, highlighting the similarities between the two fields and elaborate on the potential of transferring compressed feature representations for machine--to--machine communication. Based on insights drawn from this review, we devise future directions relevant to applications in EO and ESM.

Problem

• Addressing challenges in compressing large Earth Observation data volumes.
• Exploring neural compression for geospatial and Earth System Models data.
• Leveraging self-supervised learning for efficient data representation and communication.

Innovation

• Neural compression for geospatial data handling
• Self-supervised learning enhances data compression
• Foundation models improve feature representation transfer