Artificial neural networks for assessing forest fire susceptibility in Türkiye

Kantarcioglu O., KOCAMAN GÖKÇEOĞLU S., Schindler K.

Ecological Informatics, vol.75, 2023 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 75
  • Publication Date: 2023
  • Doi Number: 10.1016/j.ecoinf.2023.102034
  • Journal Name: Ecological Informatics
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, BIOSIS, CAB Abstracts, Geobase, Pollution Abstracts, Veterinary Science Database
  • Keywords: Artificial neural network, Earth observation, Forest fire susceptibility assessment, Forest inventory, Spectral indices
  • Hacettepe University Affiliated: Yes


Wildfires often threaten natural and economic resources and human lives. Wildfire susceptibility assessments have become essential for efficient disaster management and increasing resilience. In this study, we assessed the forest fire susceptibility in Istanbul Province and Thrace Region, Türkiye using a well-known machine learning technique, Artificial Neural Networks (ANN). Benefiting from freely available Earth Observation datasets such as Sentinel-2 images, Tree Cover Density from European Union (EU) European Environment Agency (EEA) Copernicus Land Monitoring Service, Shuttle Radar Topography Mission (SRTM) data, etc., and a forest inventory with ignition locations recorded over a period of eight years, we utilized a total of 16 independent and one dependent variables. The variables can be categorized as anthropogenic, topographic, vegetation, and hydrological factors. A ratio of 1:2 was preferred for the fire/non-fire location samples. The results show that the ANN exhibited high prediction performance with Area Under the Receiver Operating Characteristic Curve (AUC) value and F-1 score of 0.94 and 0.80, respectively. Based on feature importance analyses, we found that a human-related factor, proximity to forest roads, was the most predictive input variable. The ANN model trained with openly available data (i.e., without forest database) also yielded a high F-1 score, but produced maps with fewer details. Our results confirm that data-driven machine learning methods are promising for regional forest fire susceptibility assessments and can be extended further for other regions by deriving similar parameters from freely available Earth Observation datasets.