Remote sensing for water quality monitoring in oligotrophic rivers : Using satellite-based data and machine learning

Sammanfattning

Water quality monitoring is crucial globally due to the vital role of freshwater in providing drinking water, irrigation, and ecosystem services. Highly polluted water poses risks to both ecosystems and human health. Current water quality monitoring methods deployed in the field are often expensive, labor-intensive, and invasive. To overcome these issues, this degree project investigated the use of remote sensing to assess critical water quality parameters in the Swedish river Indalsälven. The research questions focus on determining the accuracy of predicting chemical oxygen demand (COD), river color, turbidity, and total phosphorus (TP) using satellite data and machine learning algorithms. The findings revealed that COD can be predicted with a cross-validated coefficient of determination (R²CV) of 0.7, indicating a robust predictive capability. The study suggests that while approximate quantitative prediction of COD in oligotrophic rivers is feasible using Sentinel-2 imagery, predictions for the other parameters remain challenging in the context of Indalsälven. Improvements in prediction accuracy were achieved through optimized band combinations, reduced datasets encompassing satellite data collected within two days of field measurements, and suitable pre-processing methods.