Climate Change Analysis for Agriculture Using Data Science and Predictive Modeling

Abstract

This study investigates the impact of climate change on agricultural productivity using data science and predictive modeling techniques. Climate variability, including changes in temperature, rainfall, and humidity, poses major threats to crop yield and soil fertility. By integrating long-term meteorological data with agricultural production datasets, the study employs regression models, time-series forecasting, and machine learning algorithms to analyze patterns and predict the future impact of climatic changes on crops. The results highlight a strong correlation between climate variables and yield decline, emphasizing the importance of adopting data-driven adaptive strategies in agriculture.

Introduction

Climate change poses a serious global threat to food security, water resources, and rural livelihoods. Even slight shifts in temperature and rainfall can significantly impact crop yields. This study applies data science and AI techniques to analyze historical climate and agricultural data, aiming to understand how weather variability affects crop productivity and to forecast future yields.

Objectives

The study seeks to:

1. Examine the impact of changing climate on crop productivity.

2. Use data science models for predicting agricultural performance.

3. Identify key temperature and rainfall trends influencing soil and yield.

4. Propose AI-based strategies for climate-resilient farming.

Literature Review

Previous research (Lobell et al., Wheeler & von Braun) confirms that rising temperatures and erratic rainfall reduce yields and increase food insecurity, particularly in developing regions. Machine learning models—such as Random Forests and Artificial Neural Networks—have shown promise in predicting agricultural outcomes under climate stress.

Methodology

Using data from the Indian Meteorological Department (IMD) and crop reports (2000–2024), the study employed correlation, regression, and predictive modeling. Techniques included Multiple Linear Regression, Random Forest, and LSTM neural networks to forecast crop yields based on climatic variables.

Results

Findings reveal that a 1°C rise in average temperature reduces major crop yields (rice, wheat) by 4–5%. Rainfall variability strongly correlates with yield changes. LSTM and Random Forest models achieved the highest predictive accuracy (95% and 93%). The most affected regions were the semi-arid zones of Maharashtra and Karnataka, where rainfall has steadily declined.

Discussion

Climate factors are decisive in agricultural performance. Machine learning and data visualization tools help identify risk patterns and support adaptation strategies, including efficient irrigation, drought-resistant crops, and real-time weather-based decision systems for farmers and policymakers.

Conclusion

This study demonstrates how predictive modeling and data science can be leveraged to analyze and mitigate the impact of climate change on agriculture. Accurate forecasting models enable proactive responses to climatic challenges, ensuring sustainable food production and agricultural resilience. Integrating AI tools in agriculture can guide farmers in making better, data-informed decisions.

References

[1] Lobell, D. B., Schlenker, W., & Costa-Roberts, J. (2011). Climate Trends and GlobalCrop Production Since 1980. Science. [2] Wheeler, T., & von Braun, J. (2013). Climate Change Impacts on Global Food Security Science. [3] IPCC (2021). Sixth Assessment Report: Climate Change 2021 – The Physical ScienceBasis. [4] Jain, S. K., & Kumar, V. (2018). Climate Variability and Agricultural Productivity in India Agricultural Systems.

Copyright

Copyright © 2025 Kajal Sarode , Radha Ture, Pangare Sakshi, Prof. Mukul Jagtap, Prof. Dipti Sangade. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.