Principal Investigator: Padmanava Dash
Led by Dr. Padmanava Dash, this project focused on developing a web-based platform to monitor primary productivity in Lake Chilika, India, using satellite data and machine learning. The goal was to create a tool that could support research and education on the impacts of land use, climate change, and water quality on fisheries productivity in one of Asia’s largest coastal lagoons.
Throughout the year, Dr. Dash and Co-PI Dr. Panda collaborated with Indian partner Dr. Pradipta Muduli, who provided an extensive dataset of field measurements collected over several years. This data enabled the team to develop localized chlorophyll-a algorithms tailored to the optically complex waters of Lake Chilika. These algorithms, built using machine learning techniques, offer more accurate estimations than global models and lay the groundwork for future assessments of net primary productivity and ecosystem health.
The project also included field visits to India, satellite data acquisition, and the submission of a joint NSF-DST proposal for continued development of the ALERT platform. While the team faced delays due to international travel logistics and grant writing commitments, they successfully completed the algorithm development phase and are preparing to integrate the results into a visualization tool and submit a peer-reviewed manuscript. This initiative demonstrated the value of international collaboration in environmental monitoring and highlighted the potential for expanding this approach to other lakes and regions facing similar ecological challenges.
Project Impact
Ahmad, H., Dash, P., Panda, R., and Muduli, P. R. 2025. Integrating machine learning and remote sensing for long-term monitoring of chlorophyll-a in Chilika Lagoon, India. Environ. Monit. Assess., 197, 98. https://link.springer.com/article/10.1007/s10661-024-13463-8.