AI-Driven Climate Change Mitigation for Food Security: A Quantitative Analysis Using Satellite Data

Outlet Title

6th International Conference on Agriculture Food Security & Safety

Document Type

Conference Proceeding

Publication Date

2025

Abstract

Climate change has emerged as one of the most pressing challenges to global food security, with rising temperatures, erratic rainfall patterns, and frequent extreme weather events significantly affecting agricultural productivity. This study proposes an artificial intelligence-driven framework that integrates satellite remote sensing data, climatic observations, and soil information to evaluate the impact of climate variability on crop performance and to identify actionable mitigation strategies. Leveraging the Kaggle Agri Yield: Predict Crop Yield from Soil, Weather | Kaggle, which combines field-level maize yield data with vegetation indices such as NDVI and EVI, alongside detailed weather and soil parameters, the research emphasises quantitative modelling to capture complex relationships between climate conditions and crop outcomes. Preprocessing includes temporal alignment of multi-source datasets, normalisation of environmental variables, and cloudmasking of satellite imagery to enhance data quality. Machine learning and deep learning techniques are explored to generate predictive insights and to identify the most influential factors contributing to yield fluctuations under climate stress. The outcomes of this study aim to inform precision agriculture interventions, including adaptive planting schedules and resource-efficient irrigation, thereby enhancing resilience to climate impacts. By linking satellite-based analytics with AI-driven decision support, this research contributes to sustainable food production strategies and supports evidence-based planning for farmers, policymakers, and food security initiatives.

Link to Full Text

Share

COinS