Forest Fire Prediction: A Hybrid Approach Using Context Based Learning, LSTM, and XGBoost

DOI

10.2991/978-94-6463-872-1_26How to use a DOI?

Keywords

Context-Based Learning; Ensemble Learning; Long Short-Term Memory; Clustering; Deep Learning; XGBoost; Anomaly Detection; environmental data

Abstract

Wildfires present a significant danger to both the environment and the economy. Advanced disaster management necessitates powerful prediction models. In this study, we propose a Context-Driven Hybrid Wildfire Forecasting System that utilizes ensemble learning to increase the accuracy of predictions. In order to create a high-precision wildfire forecast, we combine XGBoost, Long Short-Term Memory (LSTM) networks, and Context-Based Learning Approach. Context based learning model methodology creates a Risk Score by analyzing the past weather and wildfire data and then detecting the abnormalities using a distance measurement and clustering approach. LSTM and XGBoost models incorporate this risk score as an input feature together with the historical datasets to capture the complex patterns of wildfires and temporal relationships. To make the predictions of the previous models even more precise, we employ meta-learning with Linear Regression, thereby creating a more reliable and accurate wildfire prediction system.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Satyanarayana Raju Vuddaraju
AU  - Sri Hari Sai Saran Polisetty
AU  - J. Shanthini
PY  - 2025
DA  - 2025/11/04
TI  - Forest Fire Prediction: A Hybrid Approach Using Context Based Learning, LSTM, and XGBoost
BT  - Proceedings of the 2nd International Conference on Sustainable Business Practices and Innovative Models (ICSBPIM-2025)
PB  - Atlantis Press
SP  - 394
EP  - 407
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-872-1_26
DO  - 10.2991/978-94-6463-872-1_26
ID  - Vuddaraju2025
ER  -