Deep Learning Based Wildfire Detection for Peatland Fires Using Transfer Learning

2026-03-02

AI Summary

This study addresses the unique challenges posed by peatland fires—characterized by smoldering combustion, low flame intensity, persistent smoke emissions, and subsurface burning—which significantly degrade the performance of conventional deep learning models for wildfire detection. To overcome the scarcity of labeled peatland fire data, this work proposes the first effective application of transfer learning to this domain, leveraging convolutional neural networks pretrained on general wildfire imagery and fine-tuning them with domain-specific images from Malaysian peatlands. The approach substantially improves detection accuracy and robustness under complex conditions such as low-contrast smoke, partial occlusion, and varying illumination. Compared to training from scratch, the transferred model demonstrates markedly enhanced stability, offering a practical solution for real-time monitoring and early warning of peatland fires.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Machine learning (ML)-based wildfire detection methods have been developed in recent years, primarily using deep learning (DL) models trained on large collections of wildfire images and videos. However, peatland fires exhibit distinct visual and physical characteristics -- such as smoldering combustion, low flame intensity, persistent smoke, and subsurface burning -- that limit the effectiveness of conventional wildfire detectors trained on open-flame forest fires. In this work, we present a transfer learning-based approach for peatland fire detection that leverages knowledge learned from general wildfire imagery and adapts it to the peatland fire domain. We initialize a DL-based peatland fire detector using pretrained weights from a conventional wildfire detection model and subsequently fine-tune the network using a dataset composed of Malaysian peatland images and videos. This strategy enables effective learning despite the limited availability of labeled peatland fire data. Experimental results demonstrate that transfer learning significantly improves detection accuracy and robustness compared to training from scratch, particularly under challenging conditions such as low-contrast smoke, partial occlusions, and variable illumination. The proposed approach provides a practical and scalable solution for early peatland fire detection and has the potential to support real-time monitoring systems for fire prevention and environmental protection.

Problem

• peatland fires
• wildfire detection
• deep learning
• transfer learning
• smoldering combustion

Innovation

• transfer learning
• peatland fire detection
• deep learning
• wildfire detection
• smoldering combustion