Geographically weighted Weibull regression modeling on dissolved oxygen data to analyze river water quality in East...

This study introduces the Geographically Weighted Weibull Regression (GWWR) model as an extension of the Weibull regression (WR) within the geographically weighted regression framework and applies it to spatial environmental data on dissolved oxygen (DO) levels in East Kalimantan in 2024, rather than to time-to-event data. This study maps the river water quality (RWQ) and its influencing factors using the GWWR model. The results indicate that the RWQ in East Kalimantan in 2024 generally tends to degrade, with the main influencing factors being dissolved iron, total phosphate, water temperature, and biochemical oxygen demand. The main highlights of the proposed method are as follows:•This study presents the GWWR model as an extension of the WR model and demonstrates its applicability to spatially heterogeneous data rather than to time-to-event data.•The GWWR model is employed to locally analyze RWQ and its influencing factors.•The GWWR approach represents RWQ characteristics using several statistical measures, including the probability of water quality improvement, the probability of water quality degradation, the water quality degradation rate, and the mean DO level. These statistical measures are analyzed respectively through spatial Weibull survival, cumulative distribution, hazard, and mean regression models.