Development and Assessment of a Sentinel Based Monitoring System for Harmful Algae Indicators on a Small Inland Lake

Excessive algae growth can lead to negative consequences for ecosystem function, economic opportunity, and human and animal health. Due to the cost-effectiveness and temporal consistency of satellite image data, remote sensing has become a powerful tool for water quality monitoring. The ability to discriminate between cyanobacteria and other algae species during a bloom event may allow water managers to make informed decisions about closing beaches or communicating water quality information to the public. Remotely sensed water quality products may be particularly beneficial for small inland lakes, which may have limited in situ monitoring programs. To evaluate the ability of remote sensing imagery to monitor algae and cyanobacteria conditions in a small inland lake, chlorophyll-a and phycocyanin concentrations are measured using a YSI EXO2 Sonde during Sentinel-2 and Sentinel-3 overpasses from 2019 to 2022 on Lake Mendota, WI. Machine learning methods are implemented with existing Chlorophyll-a and Phycocyanin retrieval algorithms to model Chlorophyll-a, Phycocyanin, Phycocyanin/Chlorophyll-a, and Dissolved Oxygen. Model performance is evaluated spatially to explore potential drivers of variability in water quality, with implications for lake management.