Copyright © 2026 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{178454,
        author = {Sonam Yadav and Pranshi Verma and Priyanshi Gupta and Sugandha Chakraverti},
        title = {Machine Learning for Climate Forecasting: A Systematic Review of ML-Based Approaches for Climate Change Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {5140-5146},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178454},
        abstract = {Climate change as a global crisis, necessitates the accurate prediction and modeling of temperatures, sea level rise as well extreme weather events. Climate models are noble but have difficulty with huge datasets and non-linear relationships to adequately treat in traditional climate models. ML (Machine Learning)- based techniques like Random Forests, SVMs, Artificial Neural Networks (ANN) Gradient Boosting regressors e.g. XGBoost and Long Short-Term Memory (LSTM) network brought great upgrade in climate forecasting by increasing accuracy to improve climate prediction and sizeable climate datasets. This comprehensive analysis of the ML models considers its utility and shortcomings for climate change modeling. Aside from discussing data quality troubles, computing power needs and interpretability pitfalls; integration with physics-based models are major challenges. The paper calls for interdisciplinary effort between climate scientists, data scientists and policy makers to increase transparency of models, standardize data formats and address ethical considerations for climate predictions. Solving the challenges will enable ML-based climate models to be put into play and reach new frontiers in unraveling climate dynamics and design successful mitigation strategies},
        keywords = {Machine learning, Climate Change Prediction, Climate Data Analysis, Environmental Impact, Computational Climate Modelling},
        month = {May},
        }