SAR2Agri:基于纯 SAR 强度图像的自监督学习管道,作物类型制图 IoU 达 84.9%
提出首个纯SAR强度图像自监督学习管道，作物制图性能显著提升，对农业遥感监测有重要价值。
arXiv 8-11 上线论文提出首个仅使用 SAR 强度图像的农业应用自监督学习管道(SAR2Agri),作者:Moti Rattan Gupta、Anupam Sobti。通过改进的掩码+课程学习时间前置任务,从 SAR 数据中捕获物候特征。在 SICKLE 基准上,最终模型在作物类型制图上达到 84.9% IoU,优于光学基线 15.3 个百分点、优于现有 SAR 基线 2.2 个百分点,展示了 SAR 强度编码器对农业监测预训练的有效性。[预印本]
Abstract:Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring them is critical for ensuring food security. Synthetic Aperture Radar (SAR) satellites offer all-weather day-night imaging capability supporting key monitoring tasks including crop type mapping, yield prediction and phenological event detection. Existing multimodal remote sensing foundation models including TerraMind and CopernicusFM learn SAR representations by grounding them in optical imagery using joint encoding and contrastive learning techniques, while SAR-specific foundation models such as SAR-JEPA, SARMAE, and SAR-W-MixMAE primarily focus on target detection, flood mapping, and land cover classification applications. Recent work has introduced phenology inspired temporal pretext tasks with optical imagery which has shown strong performance on agricultural downstream tasks. In this work, we propose the first self-supervised learning pipeline focused on using only SAR intensity imagery for agricultural applications. We improve the temporal pretext tasks through masking and curriculum learning to enhance the pretraining pipeline's ability to capture phenological features from SAR. On the SICKLE benchmark, our final model achieves 84.9% IoU on crop type mapping, outperforming optical baselines (by 15.3 pt) and existing SAR baselines (by 2.2 pt), demonstrating the effectiveness of our proposed pipeline for pretraining SAR intensity encoders for agricultural monitoring.
Subjects:Computer Vision and Pattern Recognition (cs.CV)
Cite as:arXiv:2608.11142 [cs.CV]
(or arXiv:2608.11142v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2608.11142
arXiv-issued DOI via DataCite
Submission history
From: Moti Rattan Gupta [view email]
[v1] Tue, 11 Aug 2026 17:01:26 UTC (28,979 KB)