Effective water management requires frequent monitoring, but traditional methods are limited in spatiotemporal scope. While satellite remote sensing provides extensive data, a gap persists in accessible, integrated software for non-specialists. To address this, we developed the RS-WaterQuality Mapper, an open-source Python plugin for QGIS. This toolbox provides a complete, scientifically robust workflow for aquatic remote sensing, from aqua-focused atmospheric correction to the application of advanced machine learning models. A key innovation is the implementation of a multi-predictor ensemble model based on spectral-space partitioning, which enhances predictive accuracy in optically complex inland waters. Built on optimized Python libraries and a multi-processing architecture, the tool ensures computational efficiency for processing large satellite scenes. The toolbox’s utility was validated in diverse case studies—a U.S. reservoir, a Kenyan saline lake, and a U.S. river system—demonstrating strong performance (R 2>0.80). By embedding state-of-the-art science into a familiar GIS environment, the RS-WaterQuality Mapper empowers a global community of researchers and water resource managers to leverage satellite data for more effective ecosystem management.
Su et al. (Tue,) studied this question.