Nutrition-Aware and Climate-Responsive Crop Rotation Modeling in Indian Agriculture
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Indian agriculture currently faces a dual challenge: adapting to unpredictable climate patterns while addressing widespread nutritional insecurity. We propose a machine learning framework which optimizes crop rotation by balancing yield maximization with specific nutritional targets. Unlike traditional models that focus solely on productivity, our system integrates Random Forest (RF) regression for rainfall forecasting with XGBoostbased crop yield prediction to optimize the output of five critical nutrients: protein, iron, calcium, zinc, and folate. We first model district-specific rainfall patterns using temporal and geographic data, achieving a Coefficient of Determination ($R^{2}$) of 0.816. These meteorological forecasts then feed into an XGBoost yield predictor ($R^{2}$of 0.9388), which estimates production potential (tons/hectare). The final module generates three-crop rotation sequences that adhere to soil health protocols while maximizing nutrient density. Validated on agricultural data from West Bengal and Tamil Nadu, the framework successfully generates rotation plans that improve economic viability for farmers while simultaneously enhancing regional nutritional security.
Fields of Study & Subjects
Smart Agriculture and AI
Climate change impacts on agriculture
Agricultural Science and Fertilization
Publication details
- Journal / source
- International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
- Pages
- 1–7
- Publication date
- 8 January 2026
- Language
- EN