Unveiling the Illusion of Successful Water Quality Governance Using Deep Learning

This dataset contains explanatory variables and river water quality observations used in the study “Unveiling the Illusion of Successful Water Quality Governance Using Deep Learning.” Explanatory variables (Folder 01): Daily time series (2010–2023) of meteorological data (rainfall, temperature), socio-economic indicators (GDP, population density), and land-use categories (farmland, forest, grassland, water, settlements, unused land) for 86 sub-watersheds in the Pearl River Basin, China. Water quality data (Folder 02): Daily monitoring records (2010–2023) of dissolved oxygen (DO), chemical oxygen demand (COD), ammonia nitrogen (NH₃-N), total phosphorus (TP), and total nitrogen (TN) from 86 sub-watersheds, harmonized and quality-controlled. All data are provided as CSV files with clear variable names and units, supporting reproducibility of the deep learning models and analyses presented in the manuscript.