GCNT-Plume: Long-term observation of global nuclear power plants thermal plumes using Landsat images and deep learning

This repository contains the relevant code and data for the paper <strong>Long-term observation of global nuclear power plants thermal plumes using Landsat images and deep learning</strong><strong> </strong>(Wei et al, 2023, <em>Remote Sensing of Environment</em>). Specifically, the <strong>U-Net.zip</strong> file includes the associated codes for segmenting surface thermal plumes from nuclear power plants along the global coasts and the Great Lakes by using the U-Net model integrated with prior knowledge. The <strong>GCNT-Plume.zip</strong> file includes the occurrence footprints of core area plumes (the <strong>occurrence_all </strong>folder), raw water temperature increment (WST) images (the <strong>delta </strong>folder), mixed area plumes and annotations (the <strong>extractWithLocation </strong>folder), model-predicted core area plumes (the <strong>prediction*_*</strong> folders), the mixed/core area plumes and background areas in shapefile format (the <strong>sampleAnnotation* </strong>folders), and location information (the <strong>location.xlsx </strong>table). Please refer to the <strong>README.md </strong>file in the <strong>U-Net.zip</strong> file for more detailed information.