← Research

AI for Social Good: Ecology & Conservation

Applying agent-based modeling and machine learning to conservation problems: the first agent-based model of Asian elephant crop-raid dynamics (with movement, behaviour, and thermoregulation models, validated against field survey data), habitat suitability prediction, and — from the MIT postdoc years — fish modeling and Bayesian learning for sustainable fisheries in the Lakshadweep Islands. This is also one of the pillars touched by the lab’s emerging Agentic AI direction, which now spans all seven research pillars.

Publications in this pillar

1. Online Learning of Strategic Defense against Ecological Adversaries under Partial Observability with Semi-Bandit Feedback

   Anjali Purathekandy, Deepak N. Subramani · arXiv preprint · 2026

2. An agent-based model of elephant crop raid dynamics in the Periyar–Agasthyamalai complex, India

   Anjali Purathekandy, Meera Anna Oommen, Martin Wikelski, Deepak N. Subramani · Ecological Modelling, Vol. 496, 110843 · 2024

3. A Dynamic Data Driven Agent Based Model for Characterizing the Space Utilization of Asian Elephants in Response to Water Availability

   Anjali Purathekandy, Deepak Subramani · DDDAS 2024, Princeton, NJ, USA · 2024 ★ Third Best Paper Award

4. Inter and Intra-Annual Spatio-Temporal Variability of Habitat Suitability for Asian Elephants in India: A Random Forest Model-based Analysis

   P. Anjali, D. N. Subramani · 2021 IEEE International India Geoscience and Remote Sensing Symposium (InGARSS), Ahmedabad, India, pp. 467-470 · 2021 ★ Second Prize, student presentation category

5. Fish Modeling and Bayesian Learning for the Lakshadweep Islands

   A. Gupta, P. J. Haley, D. N. Subramani, P. F. J. Lermusiaux · OCEANS 2019 MTS/IEEE Seattle, pp. 1-10 · 2019

All AI for Social Good: Ecology & Conservation publications on the Publications page →