Intelligent Decision Framework for Climate Resilient Agriculture
Abstract
Climate volatility amplifies smallholder decision un- certainty in India, influencing when and what to plant. Purely data-driven advisories often fail due to behavioral barriers such as loss aversion, default bias, and limited foresight. This paper proposes a Behavioral-Aware Decision Support System (BDSS) that integrates behavioral economics principles into an intelligent recommendation architecture. The model combines climate prediction, IoT sensor data, and behavioral models to optimize adaptive recommendations. A multi-agent simulation with 200 virtual farmers and ten growing seasons demonstrates that BDSS improves adoption of climate-smart practices by 18%, reduces water usage by 10%, and lowers yield variance by 12% compared to a standard DSS. The study highlights how embedding behavioral mechanisms in DSS can bridge the gap between information availability and farmer action, fostering sustainable and climate-resilient agriculture.
References
K. Vasilaky, A. Harou, and K. Alfredo, “What Works for Water Conservation? Evidence from a Field Experiment in India,” Journal of Environmental Economics and Management, 2023.
M. Correa Secall, J. Nielsen, and H. Persson, “Nudging Fails to Increase Conservation Actions among Farmers,” Frontiers in Environmental Economics, 2025.
N. Rao, A. Mishra, et al., “Behavioral Barriers in ClimateSmart Agriculture Adoption: Evidence from Smallholder Farms in India,” Agricultural Systems, 2024.
E. Han, B. Norton, et al., “Climate–Agriculture Modeling and Decision Tool (CAMDT),” Environmental Modelling
and Software, 2017.
K.-O. Wenkel, et al., “LandCaRe DSS: A Spatial Decision Support System for Climate Adaptation,” Journal of Environmental Management, 2013.
M. Debeljak, et al., “Soil Navigator DSS: Multi-Criteria Soil Functions Decision Support System,” Frontiers in Environmental Science, 2019.
