Netting hilsa with AI: Smart maps locate rich zones but raise overfishing concerns
Times of India | 16 April 2026
KOLKATA: Scientists have rolled out an AI-powered forecasting system to help fishers locate hilsa shoals in the Bay of Bengal — a first-of-its-kind initiative aimed at boosting catch, but already raising concerns among sections of the fishing community over sustainability and the risk of overfishing.
Those involved with the project said some awareness camps have been held to introduce the new Hilsa Fishery Advisory Service to fishers.
According to the Indian National Centre for Ocean Information Services (INCOIS) under the ministry of earth sciences, the Centre has launched an AI model called XGBoost to predict where hilsa is most likely to be found. The model uses data collected between 2012 and 2016 and was validated between 2021 and 2023. The service is already operational, INCOIS said in an RTI reply.
The model, developed by a team led by scientist Sandip Giri, analyses clues such as water temperature, salinity, current speed, and flow direction. “Hilsa doesn’t follow simple patterns. Traditional methods struggle to handle these complexities, but machine learning can recognise such changing relationships much better,” Giri explained.
The forecasts are produced as digital maps showing potential hilsa-rich zones. These advisories are designed to respect seasonal fishing bans and include a 5km coastal buffer zone.
Researchers used GPS-fitted boats in the Hooghly estuary, recording daily catch data — amount, duration, location — using govt-approved gill nets. The results, Giri said, showed “promising prediction accuracy”.
The findings of the research, which helped develop the AI tool, have been published in the journal ‘Fisheries Oceanography’.
At the ground level, Vidyasagar University has been conducting training and awareness programmes to help small-scale fishers access the advisories and mobile apps, wrote INCOIS in the RTI reply. “The model factors in biogeochemical parameters such as water salinity, wind direction and speed, and temperature. We are currently testing its accuracy,” said Sourav Maity, scientist at the university’s Coastal Observatory and Outreach Centre and a project team member.
But not many fishermen are aware of this project yet. Nor is everyone convinced. Shyam Sundar Das, secretary of Digha Fishermen and Fish Traders Union, said, “I do not know about anything like this.”
Debashis Shyamal, general secretary of the Dakshinbanga Matsyajibi Forum, said, “We are not aware of any such move. But if it happens, I doubt how sustainable it will be to locate fish using AI, bypassing traditional knowledge. Targeting specific concentrations of hilsa could trigger overfishing, disrupt the ecological balance, and ultimately cause severe stock depletion.”
Maity said, “We have already conducted awareness camps for fishermen in Digha and Kakdwip. And with the April-June hilsa fishing ban now in effect, we will organise more such camps, including in Fraserganj and Namkhana.”