潜在机器学习模型在滑坡易发性评估中的应用:越南安沛省万安县案例研究

IF 2.9 Q2 GEOGRAPHY, PHYSICAL Quaternary Science Advances Pub Date : 2024-03-16 DOI:10.1016/j.qsa.2024.100181
Van Anh Tran , Thanh Dong Khuc , Xuan Quang Truong , An Binh Nguyen , Truong Thanh Phi
{"title":"潜在机器学习模型在滑坡易发性评估中的应用:越南安沛省万安县案例研究","authors":"Van Anh Tran ,&nbsp;Thanh Dong Khuc ,&nbsp;Xuan Quang Truong ,&nbsp;An Binh Nguyen ,&nbsp;Truong Thanh Phi","doi":"10.1016/j.qsa.2024.100181","DOIUrl":null,"url":null,"abstract":"<div><p>Landslides are natural hazards that cause significant damage to both property and human lives. This study employs potential machine learning models such as Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM) to assess landslide susceptibility in Van Yen District, Yen Bai Province, Vietnam, that experiences a higher frequency of landslides compared to other localities in the region. The study incorporates thirteen input variables, including elevation, slope angle, aspect, plan curvature, profile curvature, Topographic Wetness Index (TWI), distance to faults, lithology, distance to roads, distance to rivers, land cover, rainfall, and Normalized Difference Vegetation Index (NDVI). To construct the models, landslide statistics reports were utilized, consisting of 302 landslide points collected through field surveys and 52 landslide points determined using Radar Sentinel-1 images. The Google Earth Engine cloud computing platform is utilized for constructing the landslide susceptibility models. The outcome of the research is a landslide susceptibility map with five levels: very low, low, moderate, high, and very high. The Area Under the Curve (AUC) is used as a metric to evaluate the performance of all three models. The findings indicate that, besides similarities observed in landslide susceptibility maps for previously occurred landslides, the Random Forest model demonstrates a favorable performance compared to the other models, with an AUC of 0.883.</p></div>","PeriodicalId":34142,"journal":{"name":"Quaternary Science Advances","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666033424000194/pdfft?md5=ca03da695d70b76a4759ffd87272c116&pid=1-s2.0-S2666033424000194-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Application of potential machine learning models in landslide susceptibility assessment: A case study of Van Yen district, Yen Bai province, Vietnam\",\"authors\":\"Van Anh Tran ,&nbsp;Thanh Dong Khuc ,&nbsp;Xuan Quang Truong ,&nbsp;An Binh Nguyen ,&nbsp;Truong Thanh Phi\",\"doi\":\"10.1016/j.qsa.2024.100181\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Landslides are natural hazards that cause significant damage to both property and human lives. This study employs potential machine learning models such as Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM) to assess landslide susceptibility in Van Yen District, Yen Bai Province, Vietnam, that experiences a higher frequency of landslides compared to other localities in the region. The study incorporates thirteen input variables, including elevation, slope angle, aspect, plan curvature, profile curvature, Topographic Wetness Index (TWI), distance to faults, lithology, distance to roads, distance to rivers, land cover, rainfall, and Normalized Difference Vegetation Index (NDVI). To construct the models, landslide statistics reports were utilized, consisting of 302 landslide points collected through field surveys and 52 landslide points determined using Radar Sentinel-1 images. The Google Earth Engine cloud computing platform is utilized for constructing the landslide susceptibility models. The outcome of the research is a landslide susceptibility map with five levels: very low, low, moderate, high, and very high. The Area Under the Curve (AUC) is used as a metric to evaluate the performance of all three models. The findings indicate that, besides similarities observed in landslide susceptibility maps for previously occurred landslides, the Random Forest model demonstrates a favorable performance compared to the other models, with an AUC of 0.883.</p></div>\",\"PeriodicalId\":34142,\"journal\":{\"name\":\"Quaternary Science Advances\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2024-03-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2666033424000194/pdfft?md5=ca03da695d70b76a4759ffd87272c116&pid=1-s2.0-S2666033424000194-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Quaternary Science Advances\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666033424000194\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"GEOGRAPHY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Quaternary Science Advances","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666033424000194","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOGRAPHY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

山体滑坡是一种自然灾害,会对财产和生命造成重大损失。本研究采用随机森林(RF)、梯度提升(GB)和支持向量机(SVM)等潜在的机器学习模型来评估越南安沛省万安县的滑坡易发性。该研究采用了 13 个输入变量,包括海拔、坡角、坡面、平面曲率、剖面曲率、地形湿润指数 (TWI)、与断层的距离、岩性、与道路的距离、与河流的距离、土地覆盖、降雨量和归一化植被指数 (NDVI)。为构建模型,利用了滑坡统计报告,其中包括通过实地调查收集的 302 个滑坡点和利用雷达哨兵-1 图像确定的 52 个滑坡点。谷歌地球引擎云计算平台用于构建滑坡易发性模型。研究成果是一张滑坡易发性地图,分为五个等级:极低、低、中、高和极高。曲线下面积(AUC)被用作评估所有三种模型性能的指标。研究结果表明,除了在以前发生的滑坡的滑坡易发性地图中观察到的相似性之外,随机森林模型与其他模型相比表现出了良好的性能,其 AUC 为 0.883。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Application of potential machine learning models in landslide susceptibility assessment: A case study of Van Yen district, Yen Bai province, Vietnam

Landslides are natural hazards that cause significant damage to both property and human lives. This study employs potential machine learning models such as Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM) to assess landslide susceptibility in Van Yen District, Yen Bai Province, Vietnam, that experiences a higher frequency of landslides compared to other localities in the region. The study incorporates thirteen input variables, including elevation, slope angle, aspect, plan curvature, profile curvature, Topographic Wetness Index (TWI), distance to faults, lithology, distance to roads, distance to rivers, land cover, rainfall, and Normalized Difference Vegetation Index (NDVI). To construct the models, landslide statistics reports were utilized, consisting of 302 landslide points collected through field surveys and 52 landslide points determined using Radar Sentinel-1 images. The Google Earth Engine cloud computing platform is utilized for constructing the landslide susceptibility models. The outcome of the research is a landslide susceptibility map with five levels: very low, low, moderate, high, and very high. The Area Under the Curve (AUC) is used as a metric to evaluate the performance of all three models. The findings indicate that, besides similarities observed in landslide susceptibility maps for previously occurred landslides, the Random Forest model demonstrates a favorable performance compared to the other models, with an AUC of 0.883.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Quaternary Science Advances
Quaternary Science Advances Earth and Planetary Sciences-Earth-Surface Processes
CiteScore
4.00
自引率
13.30%
发文量
16
审稿时长
61 days
期刊最新文献
Tracing drainage capture between the two large tributaries of the Yangtze River in the southeastern Tibetan plateau: Insights from detrital apatite fission-track thermochronology GIS and remote sensing-based wildlife habitat suitability analysis for Mountain Nyala (Tragelaphus buxtoni) at Bale Mountains National Park, Ethiopia Combined GIS, FR and AHP approaches to landslide susceptibility and risk zonation in the Baso Liben district, Northwestern Ethiopia Cultural rhythms and pulses on MIS 5-3 migration episodes of Homo sapiens dispersal in Northeast Africa Middle Stone Age technological organisation from MIS 5 at Mertenhof Rockshelter, South Africa
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1