Agricultural Remote Sensing

Overview

Agricultural remote sensing turns satellite, aircraft, and UAV imagery into information about crops, field boundaries, soil conditions, and farm practices. Common approaches combine optical and radar time series with weather or terrain data, using methods such as U-Net-style segmentation, temporal transformers, tree-based models, and self-supervised learning. Applications include crop-type and parcel mapping, yield forecasting, and detection of weeds, disease, water stress, and nutrient status. A central challenge is reliable transfer across regions, years, sensors, and crop stages, especially when reference labels are noisy or scarce and foundation-model features do not consistently improve generalization.

Latest papers

CardsList

93 papers11 papers in the last four weeks, up 57% on the four weeks before. 0.1% of all new papers.

  1. Mapping and Classification of Trees Outside Forests using Deep Learning

    Oct 29, 2025Moritz Lucas, Hamid Ebrahimy, Viacheslav Barkov +3Remote Sensing Image SegmentationAgricultural Remote Sensing

  2. T3ST^{3}S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series

    Jun 15, 2025Mehmet Ozgur Turkoglu, Selene Ledain, Jeffrey Zweidler +2Agricultural Image AnalysisAgricultural Remote Sensing

  3. Tackling fluffy clouds: robust agricultural field boundary delineation from Sentinel-1 and Sentinel-2 satellite image time series

    Sep 20, 2024Foivos I. Diakogiannis, Zheng-Shu Zhou, Jeff Wang +133D ViTsRemote Sensing Image Segmentation