Benchmarking Artificial Neural Networks and U-Net Convolutional Architectures for Wildfire Susceptibility Prediction: Innovations in Geospatial Intelligence

Harikesh Singh; Li-Minn Ang; Sanjeev Kumar Srivastava

doi:10.1109/TGRS.2025.3529134

Back

Benchmarking Artificial Neural Networks and U-Net Convolutional Architectures for Wildfire Susceptibility Prediction: Innovations in Geospatial Intelligence

Journal article

Open access

Peer reviewed

Benchmarking Artificial Neural Networks and U-Net Convolutional Architectures for Wildfire Susceptibility Prediction: Innovations in Geospatial Intelligence

Harikesh Singh, Li-Minn Ang and Sanjeev Kumar Srivastava

IEEE Transactions on Geoscience and Remote Sensing, Vol.63, pp.1-15

2025

DOI: https://doi.org/10.1109/TGRS.2025.3529134

Files and links (2)

pdf

Benchmarking_Artificial_Neural_Networks_and_U-Net_Convolutional_Architectures_for_Wildfire_Susceptibility_Prediction_Innovations_in_Geospatial_Intelligence9.09 MBDownload View

Published VersionCC BY V4.0, Open Access

url

https://doi.org/10.1109/TGRS.2025.3529134View

Published Version

Abstract

wildfire susceptibility

artificial neural network

U-Net

forest inventory

sensitivity analysis

Effective wildfire susceptibility mapping is critical for managing forest fire risks, especially in vulnerable regions like Lamington National Park, Queensland, Australia. This study compares Artificial Neural Networks (ANN) and U-Net Convolutional Neural Networks (CNN), highlighting their strengths and limitations. ANN, known for its simplicity and efficiency, is ideal for rapid assessments and resource-constrained applications, achieving higher overall accuracy. Conversely, the U-Net model excels in precision, recall, and F1 score, leveraging its advanced spatial feature extraction and localization capabilities. This makes U-Net particularly suitable for detailed mapping and critical decision-making in complex terrains or high-stakes scenarios. Utilizing geospatial datasets, including elevation, slope, vegetation indices, and proximity to infrastructure, the study demonstrates that ANN is effective for broad applications, while U-Net addresses scenarios where minimizing false positives and negatives is essential. These findings guide stakeholders in selecting the appropriate model for tailored wildfire management and proactive mitigation strategies.

Details

Title: Benchmarking Artificial Neural Networks and U-Net Convolutional Architectures for Wildfire Susceptibility Prediction: Innovations in Geospatial Intelligence
Authors: Harikesh Singh - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Li-Minn Ang - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Sanjeev Kumar Srivastava - University of the Sunshine Coast, Queensland, School of Science, Technology and Engineering
Publication details: IEEE Transactions on Geoscience and Remote Sensing, Vol.63, pp.1-15
Publisher: Institute of Electrical and Electronics Engineers
Date published: 2025
DOI: 10.1109/TGRS.2025.3529134
ISSN: 1558-0644; 0196-2892
Copyright note: This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
Grant note: University of the Sunshine Coast, Queensland, Australia, and SmartSat CRC.
Organisation Unit: School of Science, Technology and Engineering; Sustainability Research Cluster
Language: English
Record Identifier: 991093998002621
Output Type: Journal article

Metrics

4 File views/ downloads

54 Record Views

4 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration
Web Of Science research areas: Engineering, Electrical & Electronic; Geochemistry & Geophysics; Imaging Science & Photographic Technology; Remote Sensing

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites