Reproduce “Using GeoAI and machine learning tools for consistent high-resolution land cover mapping based on time-series NAIP imagery” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jie Liu, Xusheng Tang, Chao Wang, Zhengxiao Yan, Yuchen Dai, Qi Zhang, Conghe Song

The authors map historical land cover using separate workflows for recent and poorer-quality imagery. Recent maps use a pretrained classifier and crop seeds, while earlier maps use 30-meter land-cover change data and image-derived objects to guide reconstruction. In six counties, area-weighted overall accuracy was 0.887 in 2014 and 0.733 in 2004. These are three-year, six-county results.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.