Lake eutrophication has attracted the attention of the government and general public. Chlorophyll-a (Chl-a) is a key indicator of algal biomass and eutrophication. Satellite remote sensing has enabled us to gain more insights pertaining to lakes water-quality monitoring.
Recently, a research led by Dr. LI Sijia and Prof. SONG Kaishan from the Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences developed a machine-learning algorithm for [Chl-a] using Sentinel Multispectral Imager product, with improved accuracy and performance, and concluded with a case-study in lakes with different elevation and economic levels.
They collected a total of 273 samples from 45 typical lakes across China to obtain measured- [Chl-a], and cloud-free images were used to extract normalized water leaving reflectance. The six MSI bands and their combinations were considered as input variables in machine learning algorithms.
The results showed that support vector machine model obtained a better degree of measured- and derived- fitting than those of linear regression model, Catboost model and documented nine Chl-a algorithms.
“The remote estimation of Chl-a based on artificial intelligence can provide an effective and robust way to monitor the lake eutrophication on a macro-scale; and offer a better approach to elucidate the response of lake ecosystems to global change.” said Dr. Li, first author of the study.
This study has been published on Science of the Total Environment recently titled "Quantification of chlorophyll-a in typical lakes across China using Sentinel-2 MSI imagery with machine learning algorithm".