Forest Research Division, Research Institute of Forests and Rangelands, Agricultural Research Education and Extension Organization (AREEO), Tehran, 13185-116, Iran.
Department of Natural Resources and Environmental Engineering, College of Agriculture, Shiraz University, Shiraz, Iran.
Environ Sci Pollut Res Int. 2021 Sep;28(34):47395-47406. doi: 10.1007/s11356-021-13881-y. Epub 2021 Apr 23.
Fires have increased in northeastern Iran as its semi-arid climate landscape is desiccated by human activities. To combat fire outbreaks in any region, fire susceptibility must be mapped using accurate and efficient models. This research mapped fire susceptibility in the forests and rangelands of Golestan Province in northeastern Iran using new data-mining models. Fire effective factors, including elevation, slope angle, annual mean rainfall, annual mean temperature, wind effect, topographic wetness index (TWI), plan curvature, distance to river, distance to road, and distance to village were obtained from several sources. The relative importance of each variable was determined using a random-forest algorithm. Fire-susceptibility maps were produced in R 3.0.2 software using GAM, MARS, SVM algorithms, and a new ensemble of the three models: GAM-MARS-SVM. The four fire-susceptibility maps were validated using the area under the curve. The results show that the distance to the village, annual mean rainfall, and elevation were of greatest importance in predicting fire susceptibility. The new GAM-MARS-SVM ensemble model achieved the highest precision of fire-susceptibility mapping. The fire-susceptibility map produced using the GAM-MARS-SVM ensemble model best detected the high fire risk areas in Golestan Province. The fire-susceptibility map produced by the ensemble model can be very useful for creating and enhancing management strategies for preventing fires, particularly in the higher-risk portions of Golestan Province.
由于伊朗东北部的半干旱气候景观受到人类活动的影响而变得干燥，该地区的火灾有所增加。为了在任何地区扑灭火灾，必须使用准确和高效的模型来绘制火灾易感性图。本研究使用新的数据挖掘模型，绘制了伊朗东北部戈勒斯坦省森林和牧场的火灾易感性图。火灾有效因素，包括海拔、坡度角、年平均降雨量、年平均气温、风效、地形湿度指数（TWI）、平面曲率、到河流的距离、到道路的距离和到村庄的距离，均从多个来源获得。使用随机森林算法确定了每个变量的相对重要性。使用 R 3.0.2 软件，利用 GAM、MARS、SVM 算法和三个模型的新集成体（GAM-MARS-SVM）生成火灾易感性图。使用曲线下面积验证了四张火灾易感性图的准确性。结果表明，到村庄的距离、年平均降雨量和海拔对预测火灾易感性最为重要。新的 GAM-MARS-SVM 集成模型在火灾易感性制图方面取得了最高的精度。使用 GAM-MARS-SVM 集成模型生成的火灾易感性图最能检测出戈勒斯坦省的高火灾风险区。该集成模型生成的火灾易感性图对于制定和加强火灾预防管理策略非常有用，特别是在戈勒斯坦省的高风险地区。
