Wildfire Risk Forecasting Using Weights of Evidence and Statistical Index Models

Ghafar Salavati, Ebrahim Saniei, Ebrahim Ghaderpour and Quazi K. Hassan
Additional contact information
Ghafar Salavati: Faculty of Rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Shahid Beheshti St Central Organization of the University, Gorgan 4913815739, Iran
Ebrahim Saniei: Faculty of Rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Shahid Beheshti St Central Organization of the University, Gorgan 4913815739, Iran
Ebrahim Ghaderpour: Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada
Quazi K. Hassan: Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada

Sustainability, 2022, vol. 14, issue 7, 1-15

Abstract: The risk of forest and pasture fires is one of the research topics of interest around the world. Applying precise strategies to prevent potential effects and minimize the occurrence of such incidents requires modeling. This research was conducted in the city of Sanandaj, which is located in the west of the province of Kurdistan and the west of Iran. In this study, fire risk potential was assessed using weights of evidence (WoE) and statistical index (SI) models. Information about fire incidents in Sanandaj (2011–2020) was divided into two parts: educational data (2011–2017) and validation data (2018–2020). Factors considered for potential forest and rangeland fire risk in Sanandaj city included altitude, slope percentage, slope direction, distance from the road, distance from the river, land use/land cover (LULC), average annual rainfall, and average annual temperature. Finally, in order to validate the two models used, the receiver operating characteristic (ROC) curve was used. The results for the WoE and SI models showed that about 62.96% and 52.75% of the study area, respectively, were in the moderate risk to very high risk classes. In addition, the results of the ROC curve analysis showed that the WoE and SI models had area under the curve (AUC) values of 0.741 and 0.739, respectively. Although the input parameters for both models were the same, the WoE model showed a slightly higher AUC value compared to the SI model, and can potentially be used to predict future fire risk in the study area. The results of this study can help decision makers and managers take the necessary precautions to prevent forest and rangeland fires and/or to minimize fire damage.

Keywords: elevation; forecasting; geographic information system; Kurdistan; land use/land cover; statistical index; Sanandaj county; weights of evidence; wildfire risk; Zagros forests (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://www.mdpi.com/2071-1050/14/7/3881/pdf (application/pdf)
https://www.mdpi.com/2071-1050/14/7/3881/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:14:y:2022:i:7:p:3881-:d:779418

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().