Previous Article in Journal
Simulation-Based Evaluation of Incident Commander (IC) Competencies: A Multivariate Analysis of Certification Outcomes in South Korea
Previous Article in Special Issue
YOLOv11-CHBG: A Lightweight Fire Detection Model
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Fire
Volume 8
Issue 9
10.3390/fire8090341
fire-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection

by
Marzia Zaman
1,2,
Darshana Upadhyay
3,4,*,
Richard Purcell
4,
Abdul Mutakabbir
5,
Srinivas Sampalli
4,
Chung-Horng Lung
6 and
Kshirasagar Naik
2
1
Research & Development Department, Hegyi Geomatics, 102-30 Concourse Gate, Ottawa, ON K2E 7V7, Canada
2
Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada
3
Research & Development Department, Sanstream Technology, 4 Rue Taschereau, Suite 560, Gatineau, QC J8Y 2V5, Canada
4
Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 1W5, Canada
5
Department of Data Science, Analytics and Artificial Intelligence, Carleton University, Ottawa, ON K1S 5B6, Canada
6
Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada
*
Author to whom correspondence should be addressed.
Fire 2025, 8(9), 341; https://doi.org/10.3390/fire8090341 (registering DOI)
Submission received: 3 July 2025 / Revised: 30 July 2025 / Accepted: 18 August 2025 / Published: 25 August 2025
(This article belongs to the Special Issue Machine Learning (ML) and Deep Learning (DL) Applications in Wildfire Science: Principles, Progress and Prospects (2nd Edition))
Versions Notes

Abstract

Given the critical importance of timely forest fire detection to mitigate environmental and socio-economic consequences, this research aims to achieve high detection accuracy while maintaining real-time operational efficiency, with a particular focus on minimizing computational complexity. We propose a novel framework that systematically integrates normalization, feature selection, adaptive oversampling, and classifier optimization to enhance detection performance while minimizing computational overhead. The evaluation is conducted using three distinct Canadian forest fire datasets: Alberta Forest Fire (AFF), British Columbia Forest Fire (BCFF), and Saskatchewan Forest Fire (SFF). Initial classifier benchmarking identified the best-performing tree-based model, followed by normalization and feature selection optimization. Next, four oversampling methods were evaluated to address class imbalance. An ablation study quantified the contribution of each module to overall performance. Our targeted, stepwise strategy eliminated the need for exhaustive model searches, reducing computational cost by 97.75% without compromising accuracy. Experimental results demonstrate substantial improvements in F1-score, AFF (from 69.12% to 82.75%), BCFF (61.95% to 77.91%), and SFF (90.03% to 96.18%) alongside notable reductions in False Negative Rates compared to baseline models.
Keywords: forest fire detection; machine learning; normalization; Model-Built Feature Importance (MBFI); Recursive Feature Elimination (RFE); oversampling; ablation; modeling forest fire detection; machine learning; normalization; Model-Built Feature Importance (MBFI); Recursive Feature Elimination (RFE); oversampling; ablation; modeling

Share and Cite

MDPI and ACS Style

Zaman, M.; Upadhyay, D.; Purcell, R.; Mutakabbir, A.; Sampalli, S.; Lung, C.-H.; Naik, K. A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection. Fire 2025, 8, 341. https://doi.org/10.3390/fire8090341

AMA Style

Zaman M, Upadhyay D, Purcell R, Mutakabbir A, Sampalli S, Lung C-H, Naik K. A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection. Fire. 2025; 8(9):341. https://doi.org/10.3390/fire8090341

Chicago/Turabian Style

Zaman, Marzia, Darshana Upadhyay, Richard Purcell, Abdul Mutakabbir, Srinivas Sampalli, Chung-Horng Lung, and Kshirasagar Naik. 2025. "A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection" Fire 8, no. 9: 341. https://doi.org/10.3390/fire8090341

APA Style

Zaman, M., Upadhyay, D., Purcell, R., Mutakabbir, A., Sampalli, S., Lung, C.-H., & Naik, K. (2025). A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection. Fire, 8(9), 341. https://doi.org/10.3390/fire8090341

Article Metrics

Back to TopTop