Data.rar

Chlorophyll-a (Chl-a), a critical indicator of the status of aquatic ecosystems, is influenced by a complex interplay of hydrological, meteorological, and water quality (WQ) parameters. This study employs the Random Forest (RF) machine learning algorithm, integrating remote sensing and in situ data, to develop a robust model for estimating Chl-a concentrations in three distinct areas of Gorgan Bay, Iran. In this research, the Permutation Variable Importance (PVI) index is incorporated to identify and rank influential quality, hydrometric, and meteorological parameters affecting Chl-a concentrations.The RF-based model performance, as evaluated by various statistical metrics, demonstrates the model's ability to accurately capture the complex relationship between environmental variables and Chl-a levels in Gorgan Bay. The study pinpoints monitoring stations that have a significant impact on Chl-a levels. According to the results, Particulate Organic Carbon concentration (POC) in the bay, pH, and discharge of incoming rivers to the bay exhibit the most significant influence on Gorgan Bay Chl-a concentration. To conclude, for the preservation and enhancement of aquatic ecosystems, implementing a comprehensive monitoring program focusing on the identified key variables at influential stations is essential.