Monitoring Water Quality Parameters in Small Rivers Using SuperDove Imagery

Abstract

Freshwater ecosystems provide an array of provisioning, regulating/maintenance, and cultural ecosystem services. Despite their crucial role, freshwater ecosystems are exceptionally vulnerable due to changes driven by both natural and human factors. Water quality is essential for assessing the condition and ecological health of freshwater ecosystems, and its evaluation involves various water quality parameters. Remote sensing has become an efficient approach for retrieving and mapping these parameters, even in optically complex waters such as small rivers. This study specifically focuses on modelling two non-optically active water quality parameters, dissolved oxygen (DO) and electrical conductivity (EC), by integrating 3 m PlanetScope satellite imagery with data from real-time in situ remote monitoring sensors across two small rivers in Thrace, Northeast Greece. We employed three different experimental setups using a support vector regression (SVR) algorithm: ‘Multi-seasonal by Individual Sensor’ (M-I-S) for individual sensor analysis across two seasons, ‘Multi-seasonal—All Sensors’ (M-A-S) integrating data across all seasons and sensors, and ‘Seasonal—All Sensors’ (S-A-S) focusing on per-season sensor data. The models incorporating multiple seasons and all in situ sensors resulted in R2 values of 0.549 and 0.657 for DO and EC, respectively. A multi-seasonal approach per in situ sensor resulted in R2 values of 0.885 for DO and 0.849 for EC. Meanwhile, the seasonal approach, using all in situ sensors, achieved R2 values of 0.805 for DO and 0.911 for EC. These results underscore the significant potential of combining PlanetScope data and machine learning to model these parameters and monitor the condition of ecosystems over small river surfaces.

Keywords

• water quality
• machine learning
• microsatellites
• seasonal
• remote sensing
• Earth observation