Analyzing spatio-temporal variability of aquatic productive components in Northern Bay of Bengal using advanced machine learning models

This study documents a novel method for tracking spatio-temporal variability of productivity-related elements, including particulate organic carbon (POC), particular inorganic carbon (PIC), chlorophyll-a (Chl-a), dissolved nitrate, total phosphate, and dissolved phosphate, in the Sundarbans coastal aquatic system over a period of twenty years (2002–2021). Machine learning (ML) algorithms were employed to compute all the parameters from optical remote sensing data. Input data were obtained from the MODIS multispectral imageries bands satellite data sets and data extraction and analysis were performed using SVM regression models. Moving average study of POC and Chl-a concentration along the coastal zone revealed shallow deltaic coagulation, eutrophication, microbial decomposition, and lysis-caused variation and deterioration. However, high ambient temperatures and organic waste decomposition increase dissolved phosphate in inland mangrove creeks before the monsoon. Elevated nutrient levels lead to a reduction in Chl-a and particulate organic carbon is highly correlated with Chl-a to the extent of 0.79 Especially in summer time nutrient loading from agriculture and urban runoff cause harmful algal blooms that destroy aquatic life and degrade ecosystem functions. Even though collecting samples from the field on a seasonal basis for monitoring water quality and aquatic productivity is the ideal approach, it is time-consuming and also uneconomical, given the remoteness of the expansive mangrove forest. This study demonstrates efficacy of cost-effective methods like utilizing satellite data and adopting ML techniques for continuous monitoring of Sundarbans deltaic coast for its water quality and aquatic health.