当前位置: X-MOL 学术Ecol. Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Machine-learning modelling of fire susceptibility in a forest-agriculture mosaic landscape of southern India
Ecological Informatics ( IF 5.1 ) Pub Date : 2021-06-09 , DOI: 10.1016/j.ecoinf.2021.101348
A.L. Achu , Jobin Thomas , C.D. Aju , Girish Gopinath , Satheesh Kumar , Rajesh Reghunath

The recurrent forest fires have been a serious management concern in southern Western Ghats, India. This study investigates the applicability of various geospatial data, machine learning techniques (MLTs) and spatial statistical tools to demarcate the forest fire susceptible regions of the forested landscape of the Wayanad district in the southern Western Ghats (Kerala, India). The inventory map of 279 forest fire locations (period = 2001–2018) was developed via Sentinel 2A satellite images, NASA fire archives, and field visits. The forest fire susceptibility modelling involves twelve influencing factors, such as ambient air temperature, wind speed, rainfall, relative humidity, atmospheric water vapor pressure (WVP), elevation, slope angle, topographical wetness index (TWI), slope aspect, land use/land cover (LU/LC), distance from the road and distance from the villages. Considering the varying level of performances (i.e., receiver operating characteristics-area under curve (ROC-AUC) values ranging from 0.869 to 0.924 in the testing phase) of the MLTs, viz., artificial neural network (ANN), generalized linear model (GLM), multivariate adaptive regression splines (MARS), Naïve Bayesian classifier (NBC), K-nearest neighbour (KNN), support vector machine (SVM), random forest (RF), gradient boosting machine (GBM), adaptive boosting (AdaBoost) and maximum entropy (MaxEnt), we propose a weighted approach to characterize the forest fire susceptibility of the region using the outputs of the different MLTs. The proposed method demonstrates improvement in accuracy (AUC = 0.890) for mapping the forest fire susceptibility of the region compared to the individual MLTs (AUC = 0.715 to 0.869) while validating with the recent forest fire data (i.e., 2019–2021). This study suggests that roughly one-third of the study area is highly susceptible to the occurrence of forest fires, implying the severity of the disturbance regime. The analysis also indicates the role of anthropogenic factors in the occurrence of forest fires in the region. It is expected that the demarcation and prioritization of the forest fire susceptibility zones in the region, which is a part of one of the global biodiversity hotspots, have significant implications on biodiversity conservation at a regional scale.



中文翻译:

印度南部森林农业马赛克景观火灾敏感性的机器学习模型

反复发生的森林火灾一直是印度西高止山脉南部严重的管理问题。本研究调查了各种地理空间数据、机器学习技术 (MLT) 和空间统计工具的适用性,以划分西高止山脉南部(印度喀拉拉邦)Wayanad 地区森林景观的森林火灾易感区域。279 个森林火灾地点(期间 = 2001-2018)的库存地图是通过 Sentinel 2A 卫星图像、NASA 火灾档案和实地考察开发的。森林火灾敏感性建模涉及环境气温、风速、降雨量、相对湿度、大气水蒸气压(WVP)、海拔、坡度角、地形湿度指数(TWI)、坡向、土地利用/土地覆盖(LU/LC),离公路的距离和离村庄的距离。考虑到 MLT 的不同性能水平(即,接收器操作特征曲线下面积 (ROC-AUC) 值在测试阶段从 0.869 到 0.924 不等),即人工神经网络 (ANN)、广义线性模型 ( GLM)、多元自适应回归样条 (MARS)、朴素贝叶斯分类器 (NBC)、K-最近邻 (KNN)、支持向量机 (SVM)、随机森林 (RF)、梯度提升机 (GBM)、自适应提升 (AdaBoost) ) 和最大熵 (MaxEnt),我们提出了一种加权方法,使用不同 MLT 的输出来表征该地区的森林火灾敏感性。所提出的方法证明了准确性的提高(AUC = 0。890)用于绘制该地区与单个 MLT 相比的森林火灾敏感性(AUC = 0.715 至 0.869),同时使用最近的森林火灾数据(即 2019-2021)进行验证。这项研究表明,大约三分之一的研究区域极易发生森林火灾,这意味着干扰状况的严重性。分析还表明了人为因素在该地区森林火灾发生中的作用。预计作为全球生物多样性热点之一的该地区森林火灾易发区的划分和优先排序对区域尺度的生物多样性保护具有重大意义。这项研究表明,大约三分之一的研究区域极易发生森林火灾,这意味着干扰状况的严重性。分析还表明了人为因素在该地区森林火灾发生中的作用。预计作为全球生物多样性热点之一的该地区森林火灾易发区的划分和优先排序对区域尺度的生物多样性保护具有重大意义。这项研究表明,大约三分之一的研究区域极易发生森林火灾,这意味着干扰状况的严重性。分析还表明了人为因素在该地区森林火灾发生中的作用。预计作为全球生物多样性热点之一的该地区森林火灾易发区的划分和优先排序对区域尺度的生物多样性保护具有重大意义。

更新日期:2021-07-13
down
wechat
bug