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{195875,
        author = {KALPARAPU BALABHASKAR and MATTA HARSHITA and BANDLA NAYANA LAKSHMI PRANAVA and ALA VINUTHNA and BOLLA AMRUTHA},
        title = {AI-Driven Wildfire Risk Prediction and Intelligent Fire-Fighting Systems: An Integrated Framework Using ISRO BHUVAN Geospatial Data and Advanced Machine Learning Algorithms},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2351-2356},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195875},
        abstract = {Wildfires represent an escalating global crisis, threatening ecosystems, human settlements, and economic sta- bility with unprecedented intensity. The convergence of cli- mate change, land-use transformation, and increasing human encroachment into wildland-urban interfaces has amplified both the frequency and severity of fire disasters worldwide. This research presents a comprehensive artificial intelligence frame- work that seamlessly integrates predictive risk assessment with intelligent fire-fighting operations, establishing a closed-loop system for proactive wildfire management. The methodology leverages ISRO’s BHUVAN geospatial platform India’s national geo-portal developed by the Indian Space Research Organisa- tion which provides multi-sensor, multi-platform, and multi- temporal satellite imagery along with critical disaster man- agement services including forest fire SMS alerts, spatial fire information, drought indicators, and land use/land cover data at multiple scales. By integrating BHUVAN-derived datasets with meteorological observations and historical fire records within an ensemble machine learning architecture, the proposed model achieves 89.2% accuracy in predicting high-risk zones across Andhra Pradesh. Beyond risk prediction, the framework incorporates advanced fire-fighting algorithms: a dynamic re- source dispatch system optimizing suppression resource alloca- tion, a multi-agent reinforcement learning framework coordi- nating autonomous aerial suppression units, a genetic algorithm for strategic firebreak placement, and a convolutional neural network achieving 94.3% accuracy for real-time fire detection from aerial imagery. The integrated system demonstrates a 35% improvement in containment efficiency and 42% reduction in potential fire spread compared to conventional approaches. This unified framework represents a paradigm shift from reactive fire suppression to intelligent, data-driven wildfire management, providing a scalable model for implementation in fire-prone regions globally.},
        keywords = {Wildfire Prediction, Artificial Intelligence, Ma- chine Learning, BHUVAN, ISRO, Remote Sensing, Geospatial Analysis, Fire-Fighting Algorithms, Reinforcement Learning, En- semble Methods, Disaster Management},
        month = {April},
        }