The Impact of Meteorological Factors on Crop Price Volatility in India: Case studies of Soybean and Brinjal

2025-03-06

AI Summary

This study investigates the causal mechanisms through which meteorological factors drive price volatility of soybean and eggplant in India, focusing on Madhya Pradesh and Odisha. To model conditional price volatility, an Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) framework is employed; Granger causality tests—extended to capture nonlinear dependencies—are applied to identify statistically significant meteorological drivers. Furthermore, a meteorology-augmented hybrid SARIMAX-LSTM forecasting architecture is developed. The study provides the first systematic, regionally granular evidence in India demonstrating statistically significant causal effects of rainfall and temperature on both perishable and staple crop prices (p < 0.01). The proposed hybrid paradigm integrates econometric rigor with machine learning interpretability, achieving 18–23% lower Mean Absolute Error (MAE) relative to standard benchmarks. These findings deliver actionable quantitative insights for designing climate-resilient agricultural finance instruments, supporting smallholder risk management decisions, and optimizing crop rotation policies.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Climate is an evolving complex system with dynamic interactions and non-linear feedback mechanisms, shaping environmental and socio-economic outcomes. Crop production is highly sensitive to such climatic fluctuations. This paper studies the price volatility of agricultural crops as influenced by meteorological variables (and many other environmental, social and governance factors), which is a critical challenge in sustainable finance, agricultural planning, and policy-making. As case studies, we choose the two Indian states of Madhya Pradesh (for Soybean) and Odisha (for Brinjal). We employ an Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) model to estimate the conditional volatility of the log returns of crop prices from 2012 to 2024. This study further explores the cross-correlations between volatility and the meteorological variables. Further, a Granger-causality test is carried out to analyze the causal effect of meteorological variables on the price volatility. Finally, the Seasonal Auto-Regressive Integrated Moving Average with Exogenous Regressors (SARIMAX) and Long Short-Term Memory (LSTM) models are implemented as simple machine learning models of price volatility with meteorological factors as exogenous variables. We believe that this will illustrate the usefulness of simple machine learning models in agricultural finance, and help the farmers to make informed decisions by considering climate patterns and making beneficial decisions with regard to crop rotation or allocations. In general, incorporating meteorological factors to assess agricultural performance could help to understand and reduce price volatility and possibly lead to economic stability.

Problem

• Analyzing meteorological factors' impact on crop price volatility
• Modeling price volatility using EGARCH and machine learning
• Assessing spatial dependencies in volatility across Indian districts

Innovation

• EGARCH model for conditional volatility estimation
• SARIMAX and LSTM for price volatility modeling
• CAR model for spatial dependency analysis