Code and Data for Deep Learning-Assisted Spatial Sensitivity Analysis of the SWAT Model in the Jinghe River Basin

This repository contains the code and supporting data used to reproduce the analyses and figures for the study “Identifying Dominant Parameters in SWAT Across Subbasin and HRU Scales Using a Two-Step Deep Learning-Assisted Spatial Sensitivity Analysis”. The study develops a two-step framework that combines Morris screening, multilayer perceptron surrogate modeling, and Sobol’ spatial sensitivity analysis to identify dominant SWAT parameters across subbasin and hydrologic response unit (HRU) scales in the Jinghe River Basin, China.