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{200662,
        author = {Sanket Vinayak Jagtap and Chaitanya Anil Sarje and Mohit Rooparam Sirvi and Rajendra Dilip Walave},
        title = {Predicting Environmental Changes Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2154-2158},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200662},
        abstract = {Environmental variability poses far-reaching consequences for ecosystems, economic systems, and public welfare. This study investigates four widely adopted machine learning (ML) classifiers — K-Nearest Neighbours (KNN), Support Vector Machines (SVM), Decision Trees (DT), and Naive Bayes (NB) — for predicting categorical climate states from meteorological measurements including temperature, humidity, and wind speed. The research further examines whether predictive performance can be elevated through stacking ensemble learning. The standalone Decision Tree achieved the highest accuracy at 92.6%, while the stacking ensemble reduced Decision Tree training time to 3.62 seconds — a significant gain for real-time forecasting scenarios. These findings demonstrate the practical value of ML-based ensemble techniques for environmental forecasting applications.},
        keywords = {Climate prediction, Decision Tree, ensemble learning, machine learning, stacking, Support Vector Machine.},
        month = {May},
        }