Comparative Analysis of Non-Negative Matrix Factorization in Fire Susceptibility Mapping: A Case Study of Semi-Mediterranean and Semi-Arid

• Type: Other Publications
• Date: 2025

Authors

Rahimi, I (Author) Other; Lia Duarte (Author) FCUP; Barkhoda, W (Author) Other; Ana Teodoro (Author) FCUP

Other information

Authenticus ID: P-018-MCP

DOI: 10.20944/preprints202504.1231.v1

Abstract (EN): <jats:p>The semi-Mediterranean (SM) and semi-arid (SA) regions, exemplified by the Kurdo-Zagrosian forests in western Iran and northern Iraq, have experienced frequent wildfires in recent years. This study has proposed a modified Non-Negative Matrix Factorization (NMF) method for detecting fire-prone areas using satellite-derived data in SM and SA forests. The performance of the proposed method was then compared with three other already proposed NMF methods: Principal Component Analysis (PCA), K-means, and IsoData. NMF is a factorization method renowned for performing dimensionality reduction and feature extraction. It imposes non-negativity constraints on factor matrices, enhancing interpretability and suitability for analyzing real-world datasets. Sentinel-2 imagery, the Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM), and the Zagros Grass Index (ZGI) from 2020 were employed as inputs and validated against post-2020 burned area derived from the Normalized Burned Ration (NBR) index. Results demonstrate NMF&rsquo;s effectiveness in identifying fire-prone areas across large geographic extents typical of SM and SA regions. The results also revealed that when elevation was included, NMF_L1/2 sparsity offered the best outcome among the used NMF methods. In contrast, the proposed NMF method provided the best results when only Sentinel 2 bands and ZGI were used.</jats:p>

Language: English

Type (Professor's evaluation): Scientific