Large Scale Masked Autoencoding for Reducing Label Requirements on SAR Data

TL;DR

This paper demonstrates that masked autoencoding pretraining on SAR data significantly reduces label requirements and improves the generalization of models for climate change monitoring tasks like vegetation and land cover classification.

Contribution

The study introduces a self-supervised masked autoencoding approach for SAR data, enabling effective pretraining that reduces labeling needs and enhances model generalization across regions.

Findings

Pretraining reduces label requirements by over tenfold.

Pretrained models generalize well across different geographic regions.

Performance improves when tuning on regions outside the pretraining set.

Abstract

Satellite-based remote sensing is instrumental in the monitoring and mitigation of the effects of anthropogenic climate change. Large scale, high resolution data derived from these sensors can be used to inform intervention and policy decision making, but the timeliness and accuracy of these interventions is limited by use of optical data, which cannot operate at night and is affected by adverse weather conditions. Synthetic Aperture Radar (SAR) offers a robust alternative to optical data, but its associated complexities limit the scope of labelled data generation for traditional deep learning. In this work, we apply a self-supervised pretraining scheme, masked autoencoding, to SAR amplitude data covering 8.7\% of the Earth's land surface area, and tune the pretrained weights on two downstream tasks crucial to monitoring climate change - vegetation cover prediction and land cover classification. We show that the use of this pretraining scheme reduces labelling requirements for the downstream tasks by more than an order of magnitude, and that this pretraining generalises geographically, with the performance gain increasing when tuned downstream on regions outside the pretraining set. Our findings significantly advance climate change mitigation by facilitating the development of task and region-specific SAR models, allowing local communities and organizations to deploy tailored solutions for rapid, accurate monitoring of climate change effects.