Operational monitoring of urban coastal pollution: integrating satellite remote sensing and machine learning to manage turbid and suspected sewage plumes

Abstract Effective management of urban coastal pollution is often hindered by an inability to track the spatial and seasonal dynamics of wastewater plumes from creeks and canals. This study addresses this management gap by developing and validating a satellite-based operational monitoring framework for one of the polluted creeks in the Chennai metropolitan city, and adjacent coastal waters of the Bay of Bengal, India. The present study assessed water quality and plume dynamics using monthly one cloud free data from January 2023 to December 2025. Satellite-derived Chlorophyll-a and Total Suspended Matter were processed using the Case 2 Regional Coast Colour processor, and turbidity was estimated using a semi-empirical algorithm. Retrieved products were validated against synchronous in-situ measurements from two different field campaigns, demonstrating a strong positive correlation. Time-series analysis revealed low turbidity or no plume events during the dry season and extensive, highly turbid plumes during the Northeast Monsoon season (October to December) with plume extension observed up to 5 km offshore. A Random Forest classifier was trained using unsupervised K-means++ clustering of > 80,000 remote sensing reflectance spectra from a representative high-discharge (15 th November 2024) event produced 14 spectrally distinct optical water types, ranging from clear marine waters to anomalously polluted types characterized by elevated red and near-infrared reflectance. This hybrid approach provides a robust framework for the spatial detection and monitoring of coastal discharges. This framework enables early warning of pollution events, supports compliance tracking with environmental regulations, and allows targeted interventions to reduce ecological impacts. This approach demonstrates how readily available satellite data and machine learning can be operationalized to improve coastal water quality management in rapidly urbanizing regions facing similar challenges.

Authors

Institutions

Publication Details

Journal
Anthropocene Coasts
Published
2026-10-26
DOI
https://doi.org/10.1007/s44218-026-00157-6
Primary Topic
Coastal and Marine Dynamics
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Operational monitoring of urban coastal pollution: integrating satellite remote sensing and machine learning to manage turbid and suspected sewage plumes

Roop Singh Kankara, Sanitha K. Sivadas, Chinmay Shah, Karri Ramu et al.
Anthropocene Coasts
Coastal and Marine Dynamics
article

Operational monitoring of urban coastal pollution: integrating satellite remote sensing and machine learning to manage turbid and suspected sewage plumes

Roop Singh Kankara, Sanitha K. Sivadas, Chinmay Shah, Karri Ramu, Natarajan Logesh, Muthukumar Chandrasekaran, Manigandan Vajravelu
article en

Abstract

Abstract Effective management of urban coastal pollution is often hindered by an inability to track the spatial and seasonal dynamics of wastewater plumes from creeks and canals. This study addresses this management gap by developing and validating a satellite-based operational monitoring framework for one of the polluted creeks in the Chennai metropolitan city, and adjacent coastal waters of the Bay of Bengal, India. The present study assessed water quality and plume dynamics using monthly one cloud free data from January 2023 to December 2025. Satellite-derived Chlorophyll-a and Total Suspended Matter were processed using the Case 2 Regional Coast Colour processor, and turbidity was estimated using a semi-empirical algorithm. Retrieved products were validated against synchronous in-situ measurements from two different field campaigns, demonstrating a strong positive correlation. Time-series analysis revealed low turbidity or no plume events during the dry season and extensive, highly turbid plumes during the Northeast Monsoon season (October to December) with plume extension observed up to 5 km offshore. A Random Forest classifier was trained using unsupervised K-means++ clustering of > 80,000 remote sensing reflectance spectra from a representative high-discharge (15 th November 2024) event produced 14 spectrally distinct optical water types, ranging from clear marine waters to anomalously polluted types characterized by elevated red and near-infrared reflectance. This hybrid approach provides a robust framework for the spatial detection and monitoring of coastal discharges. This framework enables early warning of pollution events, supports compliance tracking with environmental regulations, and allows targeted interventions to reduce ecological impacts. This approach demonstrates how readily available satellite data and machine learning can be operationalized to improve coastal water quality management in rapidly urbanizing regions facing similar challenges.

Anthropocene CoastsVol. 9(1)
Ministry of Earth Sciences (IN), National Centre for Coastal Research (IN)
Ministry of Earth Sciences
Openalex Percentile: Top 17%
Coastal and Marine Dynamics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon