Gangiredla et al. (2026) Forest Fire Prediction Using AI: In-Depth Feature Analysis and Explainable AI Techniques

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Santosh Gangiredla, Nikhil Gokavarapu, Narendra Kumar Grandhi, Madhu Karatam, T. Deepika
• DOI: 10.1007/978-3-032-15410-1_25

Research Groups

Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Coimbatore, India

Short Summary

This paper proposes a forest fire forecasting system that integrates deep learning models with explainable AI techniques to enhance the accuracy and transparency of region-wise fire hazard predictions, utilizing historical meteorological and fire data.

Objective

• To propose and test a forest fire forecasting system that combines deep learning models with explainable AI methods to improve the accuracy and transparency of region-wise fire hazard predictions for efficient wildfire management.

Study Configuration

• Spatial Scale: Region-wise (specific geographical regions not detailed in the provided text).
• Temporal Scale: Based on past meteorological and fire data (specific duration not detailed in the provided text).

Methodology and Data

• Models used: Deep learning models, Explainable AI (XAI) methods.
• Data sources: Past meteorological data, historical fire data.

Main Results

• The proposed system effectively predicts region-wise fire hazards.
• Models were tested using evaluation measures, demonstrating improved accuracy.
• Explainable AI methods successfully revealed important environmental variables that determine fire events.
• The method enhances fire hazard prediction, contributing to more efficient management of wildfires.

Contributions

• Introduction of a novel forest fire forecasting system that integrates deep learning with explainable AI, offering enhanced accuracy and transparency.
• The application of XAI techniques to identify and reveal critical environmental variables influencing fire events, providing deeper insights into prediction factors.
• Improvement in the efficiency of wildfire management through more precise and understandable fire hazard predictions.

Funding

Not specified in the provided text.

Citation

@article{Gangiredla2026Forest,
  author = {Gangiredla, Santosh and Gokavarapu, Nikhil and Grandhi, Narendra Kumar and Karatam, Madhu and Deepika, T.},
  title = {Forest Fire Prediction Using AI: In-Depth Feature Analysis and Explainable AI Techniques},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-3-032-15410-1_25},
  url = {https://doi.org/10.1007/978-3-032-15410-1_25}
}