Accounting for spatial variability with geo-aware random forest: A case study for US major crop mapping

Open Webpage

Yiqun Xie, Anh N. Nhu, Xiao-Peng Song, Xiaowei Jia, Sergii Skakun, Haijun Li, Zhihao Wang

Published: 01 Mar 2025, Last Modified: 08 Nov 2025Remote Sensing of EnvironmentEveryoneRevisionsCC BY-SA 4.0
Abstract: Highlights•We develop a Geo-aware Random Forest (Geo-RF) to address spatial variability.•Geo-RF automatically recognizes spatial variability during training.•Geo-RF efficiently optimizes space-partitioning to address variability.•Case studies on crop mapping in CONUS showed significant improvements in many areas.•Sensitivity analyses were performed to understand the effects of parameter settings.