Forest fires caused by different environmental and human factors are responsible for the extensive destruction of natural and economic resources. Modern machine learning techniques have become popular in developing very accurate and precise susceptibility maps of various natural disasters to help reduce the occurrence of such calamities. The present study has applied and tested multiple algorithms to map the areas susceptible to wildfire in the Mediterranean Region of Turkey. Besides, the performance of XGBoost, CatBoost, Gradient Boost, AdaBoost, and LightGBM methods for wildfire susceptibility mapping is also examined. The results have revealed the higher testing accuracy of CatBoost (95.47%) algorithm, followed by LightGBM (94.70%), XGBoost (88.8%), AdaBoost (86.0%), and GBM (84.48%) algorithms. Resultant wildfire susceptibility maps provide proper inventories for forest engineers, planners, and local governments for future policies regarding disaster management in Turkey.
The effectiveness of fire towers in combating forest fires relies on their appropriate observation angles, enabling a swift and efficient response to fire incidents. The purpose of this study is to examine the effectiveness of 49 fire towers located within the Antalya Forestry Regional Directorate, situated in the Mediterranean basin—a region prone to frequent forest fires. The assessment encompasses the visibility of the entire study area, including forested regions, as well as the visibility of 2504 forest fires recorded by the towers between 2008 and 2021. Furthermore, the evaluation considers the objectives based on Forest Management Directorates and conducts a location suitability analysis for the six towers with the lowest visibility. We utilized the Viewshed Tool in the ArcGIS application and employed the Best–Worst approach. Two scenarios were devised, considering smoke height at 0 m or 100 m, to determine the visibility of fire lookout towers. In Scenario I, assuming a smoke height of 100 m, only three towers exhibited visibility above 70%. However, in Scenario II, assuming a smoke height of 0 m, no towers achieved visibility above 70%. Scenario I indicated that only two towers possessed a view of more than 70% of the forested region, while Scenario II suggested that no towers met this criterion. For the visibility of forest fires, Scenario I identified seven towers capable of observing more than 70%, whereas Scenario II indicated that no towers possessed such capability. In the tower suitability analysis, the visibility rates varied from 41.18% to 1016.67%. Based on the evaluation results, the current visibility capacities of the 49 fire towers proved insufficient for effective preventive measures.
Karadeniz Bölümü nemli bir saha olmasına rağmen son zamanlarda çok sayıda orman yangını yaşanmıştır. Bu bölümde yer alan Bartın da biyoçeşitlilik açısından zengin ormanların bulunduğu bir ildir. Ayrıca il, ülkemizin 9 sıcak noktasından biri olan Küre Dağları Milli Parkı’nın uzantısı Batı Küre Dağları’nı da kapsamaktadır. Bu şartlar göz önünde bulundurulduğunda Bartın il sınırları içerisindeki ormanlık sahaların yangın risklerine karşı korunması gerekmektedir. Bu çerçevede çalışmanın amacı Bartın ilinde orman yangını riskinin belirlenmesidir. Bunun için çalışmada, kullanışlı bir araç olan Coğrafi Bilgi Sistemlerinden (CBS) yararlanılmıştır. Verilerin işlenmesi ve görüntülenmesi bakımından gelişmiş bir yaklaşım olan CBS, risk analizlerine olanak sağlamasıyla öne çıkmaktadır. Araştırmada, yangın riskini belirlemek için Grey Relational Analysis (GRA) kullanılmıştır. GRA, faktörlerin etki derecesini değerlendirmek için etkili bir formüldür. Hesaplamada yangını etkileyen faktörler ile acil müdahale faktörleri birbirinden ayrı analiz edilerek haritalanmıştır. Daha sonra bu haritalar birleştirilerek yangın risk haritası oluşturulmuştur. Yapılan yangın risk haritası sonucuna göre Bartın ilinde 438.1 km²’lik alan riskli çıkmıştır. Bu alanlarda sıcaklığın fazla, yükseltinin az, iğne yapraklıların bulunması dikkat çeken unsurlar olmuştur.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.