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{189087,
        author = {AYUSH SURESH SARVE and Ashwini Watekar and Lokesh Nimkar and Aishvary Gobade and Anuj Malviya and Urvashi Gautam},
        title = {Forest Fire Prediction Using Regression Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4861-4864},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189087},
        abstract = {Wildfires rank among the most destructive natural disasters, leading to severe ecological damage, economic loss, and risks to human life. In recent years, their frequency and intensity have risen sharply due to climate change and human activities, making accurate prediction systems more essential than ever. This research presents a machine learning–driven approach to forest fire prediction, utilizing historical environmental data such as temperature, humidity, wind speed, and rainfall.
The proposed system explores multiple algorithms—including Linear Regression, Logistic Regression, Random Forest, and a Multilayer Perceptron (MLP) classifier—to analyze data patterns and assess fire risk levels. To improve predictive accuracy, the study emphasizes thorough data preprocessing, feature selection, and model optimization techniques. Experimental findings reveal that the MLP classifier performs the best, achieving prediction accuracy between 90% and 95%, while also demonstrating stability across different test scenarios.
In addition, a user-friendly web interface has been developed using Flask, allowing real-time input of environmental parameters and instant fire risk evaluations. This integration not only enables early warnings and timely preventive measures but also helps optimize firefighting resource allocation. By combining advanced prediction techniques with practical deployment, the study contributes to proactive wildfire management, supporting ecosystem protection, biodiversity conservation, and community safety.},
        keywords = {Forest Fire Prediction, MLP Classifier, Machine Learning, Flask, Graphical User Interface (GUI)},
        month = {December},
        }