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

Abstract

Effective wildfire susceptibility mapping (WfSM) is critical for managing forest fire risks, especially in vulnerable regions like Lamington National Park, Queensland, Australia. This study compares artificial neural networks (ANNs) and U-Net convolutional neural networks (CNNs), 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 F 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. By using 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 (FPs) and negatives is essential. These findings guide stakeholders in selecting the appropriate model for tailored wildfire management and proactive mitigation strategies.