Copyright © 2025 Authors retain the copyright of this article. This article 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.

@article{187467,
        author = {Sujoy Halder and Dr. Priyanka Vashisht},
        title = {Climate-Adaptive Agriculture AI: Predicting Crop Resilience Using Multimodal Data and Generative Counterfactuals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {5884-5892},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187467},
        abstract = {Agricultural systems are becoming more vulnerable to climate changes, land degradation, and limited resources. This study presents a new Climate-Adaptive Agriculture AI framework that predicts crop resilience by using deep learning and generative counterfactual reasoning. The model combines climate, soil, and plant data with a strong late-fusion architecture and a conditional Variational Autoencoder-Generative Adversarial Network (cVAE-GAN) to simulate different scenarios. By linking predictions with understandable results through SHAP (SHapley Additive exPlanations), the framework provides accurate forecasts along with practical insights for climate-resilient farming practices. The experiments showed a 15% reduction in RMSE compared to baseline models and improved understanding. This highlights the framework's potential as a tool to support decisions in sustainable agriculture.},
        keywords = {Climate-Adaptive AI, Crop Resilience, Multimodal Learning, Generative Counterfactuals, Precision Agriculture, Explainable AI (XAI)},
        month = {November},
        }