Under the combined impacts of climate change and intensified human activities, harmful algal blooms (HABs) have occurred with increasing frequency in China’s coastal waters, posing growing risks to marine ecosystems and regional sustainability. Chlorophyll-a concentration (Chl-a), a key indicator of phytoplankton biomass, plays a crucial role in HAB monitoring and early warning. This study integrates satellite remote sensing data from 2000 to 2004, 2011 to 2013, and 2023 to 2024 with in situ measurements and environmental variables (e.g., dissolved oxygen) to investigate Chl-a dynamics in the East China Sea. The results indicate pronounced spatiotemporal heterogeneity across the region. Spectral features were represented using band-ratio methods and the BRG model, followed by variable selection based on the Bayesian Information Criterion (BIC) to determine the optimal band combinations for model training. Six mainstream machine learning models were evaluated, and the Backpropagation Neural Network (BP) was selected as the baseline model due to its superior performance. To further improve model robustness and global optimization capability, the Artificial Lemming Algorithm (ALA) was employed to optimize the BP network, resulting in the ALA-BP inversion model. The optimized model achieved correlation coefficients of 0.933 on the test set and 0.940 on the independent validation set, outperforming the other models. The proposed model was further applied to the 2024 algal bloom event in the East China Sea, successfully capturing the spatiotemporal variations of Chl-a. This study provides an effective retrieval framework for Chl-a in optically complex coastal waters and demonstrates its applicability in HAB monitoring.
Cao et al. (Sun,) studied this question.