DEVELOPMENT OF A DATA-DRIVEN MODEL TO PREDICT LANDSLIDE SENSITIVE AREAS

IF 0.7 Q4 GEOGRAPHY, PHYSICAL

Geographia Technica Pub Date : 2021-02-05 DOI:10.21163/GT_2021.161.09

S. A. Eslaminezhad, Davoud Omarzadeh, M. Eftekhari, M. Akbari

{"title":"DEVELOPMENT OF A DATA-DRIVEN MODEL TO PREDICT LANDSLIDE SENSITIVE AREAS","authors":"S. A. Eslaminezhad, Davoud Omarzadeh, M. Eftekhari, M. Akbari","doi":"10.21163/GT_2021.161.09","DOIUrl":null,"url":null,"abstract":": The occurrence of landslides has always been a problem in spatial planning as one of the environmental threats. The aim of the present study is to estimate the landslide sensitive areas in the Urmia Lake basin based on determining effective criteria and spatial and non-spatial data-driven models. The criteria used in this research include distance to faults, distance to roads, distance to hydrology network, land use, lithology, soil classes, Elevation, slope, aspect and Precipitation. The novelty of this study is to present new combination approaches to determine the effective criteria in landslide sensitive areas (Urmia Lake basin). In this regard, the geographically weighted regression (GWR) with exponential and bi-square kernels and artificial neural network (ANN) combined with a binary particle swarm optimization algorithm (BPSO). The best value of the fitness function (1-R2) for ANN, GWR with the exponential kernel, and GWR with bi-square kernel was obtained 0.2780, 0.07453, and 0.0022, respectively, Which indicates higher compatibility of the bi-square kernel than the other models. It was also found that the criteria used have a significant effect on the landslide sensitive zoning.","PeriodicalId":45100,"journal":{"name":"Geographia Technica","volume":" ","pages":""},"PeriodicalIF":0.7000,"publicationDate":"2021-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geographia Technica","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21163/GT_2021.161.09","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"GEOGRAPHY, PHYSICAL","Score":null,"Total":0}

引用次数: 2

Abstract

: The occurrence of landslides has always been a problem in spatial planning as one of the environmental threats. The aim of the present study is to estimate the landslide sensitive areas in the Urmia Lake basin based on determining effective criteria and spatial and non-spatial data-driven models. The criteria used in this research include distance to faults, distance to roads, distance to hydrology network, land use, lithology, soil classes, Elevation, slope, aspect and Precipitation. The novelty of this study is to present new combination approaches to determine the effective criteria in landslide sensitive areas (Urmia Lake basin). In this regard, the geographically weighted regression (GWR) with exponential and bi-square kernels and artificial neural network (ANN) combined with a binary particle swarm optimization algorithm (BPSO). The best value of the fitness function (1-R2) for ANN, GWR with the exponential kernel, and GWR with bi-square kernel was obtained 0.2780, 0.07453, and 0.0022, respectively, Which indicates higher compatibility of the bi-square kernel than the other models. It was also found that the criteria used have a significant effect on the landslide sensitive zoning.

查看原文本刊更多论文

开发数据驱动模型预测滑坡敏感区

滑坡的发生作为环境威胁之一，一直是空间规划中的一个难题。本研究的目的是在确定有效标准、空间和非空间数据驱动模型的基础上，对乌尔米亚湖流域的滑坡敏感区进行估算。本研究中使用的标准包括到断层的距离、到道路的距离、到水文网络的距离、土地利用、岩性、土壤类别、高程、坡度、坡向和降水。本研究的新颖之处在于提出了新的组合方法来确定滑坡敏感区(乌尔米亚湖盆地)的有效准则。为此，将指数核和双平方核的地理加权回归(GWR)与人工神经网络(ANN)结合的二元粒子群优化算法(BPSO)相结合。人工神经网络、指数核GWR和双平方核GWR的适应度函数(1-R2)的最佳值分别为0.2780、0.07453和0.0022，表明双平方核模型的兼容性高于其他模型。研究还发现，所采用的准则对滑坡敏感区划有显著影响。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Geographia Technica GEOGRAPHY, PHYSICAL-

CiteScore

2.30

自引率

14.30%

发文量

期刊介绍： Geographia Technica is a journal devoted to the publication of all papers on all aspects of the use of technical and quantitative methods in geographical research. It aims at presenting its readers with the latest developments in G.I.S technology, mathematical methods applicable to any field of geography, territorial micro-scalar and laboratory experiments, and the latest developments induced by the measurement techniques to the geographical research. Geographia Technica is dedicated to all those who understand that nowadays every field of geography can only be described by specific numerical values, variables both oftime and space which require the sort of numerical analysis only possible with the aid of technical and quantitative methods offered by powerful computers and dedicated software. Our understanding of Geographia Technica expands the concept of technical methods applied to geography to its broadest sense and for that, papers of different interests such as: G.l.S, Spatial Analysis, Remote Sensing, Cartography or Geostatistics as well as papers which, by promoting the above mentioned directions bring a technical approach in the fields of hydrology, climatology, geomorphology, human geography territorial planning are more than welcomed provided they are of sufficient wide interest and relevance.