Unlocking the Potential of Multisource Satellites for Harmonized Algal Bloom Detection in Plateau Lakes

Abstract

Algal blooms pose a considerable threat to both human health and the natural environment, their presence even extending to lakes situated across plateau regions. The geolocation and volatile climate conditions render it quite a challenge for algal bloom detection with single optical satellite across plateau lakes. To address this limitation, this study aims to achieve algal bloom detection through five satellites with high spatial resolution based on machine learning (ML) across nine lakes in Yunnan Province, China. Noteworthy findings from the study include: 1) achieving high accuracy on algal bloom detection over 0.82 based on random forest (RF) across multiple lakes and multisensors; 2) evaluating quantitatively and qualitatively algal bloom outbreaks in five out of nine plateau lakes in 2019; and 3) establishing a severity ranking of algal bloom occurrences, with Lake Dianchi exhibiting the highest severity, followed by Lake Xingyun, Lake Chenghai, Lake Erhai, and Lake Qilu. In general, this work demonstrated the effectiveness in multisource satellites observation with rational precision. These results laid the foundation for implementing a practical technical framework that enables precise algal bloom detection and facilitates comparative analyses among different lakes.