A comparative evaluation of statistical and machine learning approaches for debris flow susceptibility zonation mapping in the Indian Himalayas

IF 4.7 3区 环境科学与生态学 Q2 ENVIRONMENTAL SCIENCES Environment, Development and Sustainability Pub Date : 2024-09-14 DOI:10.1007/s10668-024-05398-4
Rajesh Kumar Dash, Neha Gupta, Philips Omowumi Falae, Rajashree Pati, Debi Prasanna Kanungo
{"title":"A comparative evaluation of statistical and machine learning approaches for debris flow susceptibility zonation mapping in the Indian Himalayas","authors":"Rajesh Kumar Dash, Neha Gupta, Philips Omowumi Falae, Rajashree Pati, Debi Prasanna Kanungo","doi":"10.1007/s10668-024-05398-4","DOIUrl":null,"url":null,"abstract":"<p>Spatial prediction of debris flows in terms of susceptibility mapping is the first and foremost requirement for disaster mitigation. In the present study, a comparative evaluation of machine learning and statistical approaches for debris flow susceptibility zonation (DFSZ) mapping has been attempted using 10 causative thematic layers (slope, aspect, elevation, plan curvature, profile curvature, topographic wetness index, stream power index, geology, proximity to streams, normalized difference vegetation index) and a debris flow inventory containing 85 debris flow locations. The employed machine learning (ML) approaches include random forest (RF), naïve Bayes (NB), and extreme gradient boosting (XGBoost) models whereas statistical models include the weight of evidence (WoE) and index of entropy (IoE). The results indicated that in all 5 DFSZ maps, about 21.20–47.98% of the area is very highly and highly susceptible to debris flows. It is observed that the major debris flows as well as high susceptible zones are distributed along the river Alakananda and its tributaries and at the vicinity of the NH-58. Among the statistical models, the DFSZ map prepared using the weight of evidence (WoE) model provides higher accuracy in terms of the success rate and the prediction rate compared to that prepared using the index of entropy model (IoE). Among the machine learning-based models, both the extreme gradient boosting (XGBoost) and random forest (RF) models give better accuracy and are more efficient than the Naïve Bayes (NB) model. It is also observed that the ML models perform better than the statistical models for a part of Chamoli district, Uttarakhand state (India). The novelty of the present study lies in the spatial prediction of one of the most destructive forms of mass movement (debris flow) in the Indian Himalayas using statistical and ML models and establishing the superiority of the ML Random Forest &amp; XGBoost model over other ML and statistical models for the present case. This study will help make decisions on the suitability of developmental activities and human settlement in the area under consideration. The present study is one among the few studies focused on the DFSZ mapping in Indian Himalayas and can be replicated in other debris flow prone regions worldwide.</p>","PeriodicalId":540,"journal":{"name":"Environment, Development and Sustainability","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environment, Development and Sustainability","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1007/s10668-024-05398-4","RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Spatial prediction of debris flows in terms of susceptibility mapping is the first and foremost requirement for disaster mitigation. In the present study, a comparative evaluation of machine learning and statistical approaches for debris flow susceptibility zonation (DFSZ) mapping has been attempted using 10 causative thematic layers (slope, aspect, elevation, plan curvature, profile curvature, topographic wetness index, stream power index, geology, proximity to streams, normalized difference vegetation index) and a debris flow inventory containing 85 debris flow locations. The employed machine learning (ML) approaches include random forest (RF), naïve Bayes (NB), and extreme gradient boosting (XGBoost) models whereas statistical models include the weight of evidence (WoE) and index of entropy (IoE). The results indicated that in all 5 DFSZ maps, about 21.20–47.98% of the area is very highly and highly susceptible to debris flows. It is observed that the major debris flows as well as high susceptible zones are distributed along the river Alakananda and its tributaries and at the vicinity of the NH-58. Among the statistical models, the DFSZ map prepared using the weight of evidence (WoE) model provides higher accuracy in terms of the success rate and the prediction rate compared to that prepared using the index of entropy model (IoE). Among the machine learning-based models, both the extreme gradient boosting (XGBoost) and random forest (RF) models give better accuracy and are more efficient than the Naïve Bayes (NB) model. It is also observed that the ML models perform better than the statistical models for a part of Chamoli district, Uttarakhand state (India). The novelty of the present study lies in the spatial prediction of one of the most destructive forms of mass movement (debris flow) in the Indian Himalayas using statistical and ML models and establishing the superiority of the ML Random Forest & XGBoost model over other ML and statistical models for the present case. This study will help make decisions on the suitability of developmental activities and human settlement in the area under consideration. The present study is one among the few studies focused on the DFSZ mapping in Indian Himalayas and can be replicated in other debris flow prone regions worldwide.

Abstract Image

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
印度喜马拉雅山泥石流易发区划绘图的统计和机器学习方法比较评估
绘制泥石流易发区地图对泥石流进行空间预测是减灾的首要要求。在本研究中,尝试使用 10 个成因专题层(坡度、坡向、海拔、平面曲率、剖面曲率、地形湿润指数、溪流动力指数、地质、溪流邻近度、归一化差异植被指数)和包含 85 个泥石流位置的泥石流清单,对机器学习和统计方法进行比较评估,以绘制泥石流易发区(DFSZ)图。采用的机器学习(ML)方法包括随机森林(RF)、天真贝叶斯(NB)和极端梯度提升(XGBoost)模型,而统计模型包括证据权重(WoE)和熵指数(IoE)。结果表明,在所有 5 幅 DFSZ 地图中,约有 21.20%-47.98% 的区域极易发生泥石流。据观察,主要的泥石流和高易受区分布在阿拉卡南达河及其支流沿岸和 NH-58 公路附近。在统计模型中,使用证据权重模型(WoE)绘制的泥石流易发区地图在成功率和预测率方面都比使用熵指数模型(IoE)绘制的地图更准确。在基于机器学习的模型中,极梯度提升模型(XGBoost)和随机森林模型(RF)都比奈夫贝叶斯模型(NB)更准确、更高效。此外,在印度北阿坎德邦 Chamoli 地区的部分地区,ML 模型的表现也优于统计模型。本研究的新颖之处在于利用统计和 ML 模型对印度喜马拉雅山脉最具破坏性的大规模运动(泥石流)之一进行空间预测,并在本案例中确定了 ML 随机森林 & XGBoost 模型优于其他 ML 和统计模型。这项研究将有助于对所考虑地区的开发活动和人类定居的适宜性做出决策。本研究是为数不多的侧重于印度喜马拉雅山 DFSZ 地图绘制的研究之一,可在全球其他泥石流易发地区推广。
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 去求助
来源期刊
Environment, Development and Sustainability
Environment, Development and Sustainability Economics, Econometrics and Finance-Economics and Econometrics
CiteScore
10.20
自引率
6.10%
发文量
754
期刊介绍: Environment, Development and Sustainability is an international and multidisciplinary journal covering all aspects of the environmental impacts of socio-economic development. It is also concerned with the complex interactions which occur between development and environment, and its purpose is to seek ways and means for achieving sustainability in all human activities aimed at such development. The subject matter of the journal includes the following and related issues: -mutual interactions among society, development and environment, and their implications for sustainable development -technical, economic, ethical and philosophical aspects of sustainable development -global sustainability - the obstacles and ways in which they could be overcome -local and regional sustainability initiatives, their practical implementation, and relevance for use in a wider context -development and application of indicators of sustainability -development, verification, implementation and monitoring of policies for sustainable development -sustainable use of land, water, energy and biological resources in development -impacts of agriculture and forestry activities on soil and aquatic ecosystems and biodiversity -effects of energy use and global climate change on development and sustainability -impacts of population growth and human activities on food and other essential resources for development -role of national and international agencies, and of international aid and trade arrangements in sustainable development -social and cultural contexts of sustainable development -role of education and public awareness in sustainable development -role of political and economic instruments in sustainable development -shortcomings of sustainable development and its alternatives.
期刊最新文献
Analyzing the effects of socioeconomic, natural and landscape factors on PM2.5 concentrations from a spatial perspective Addressing the contradiction between water supply and demand: a study on multi-objective regional water resources optimization allocation Development of single and dual crop coefficients for drip-irrigated broccoli using weighing type field lysimeters in semi-arid environment Energy transition policy, cash flow uncertainty and R&D expenditures of energy enterprises Green recycling of used motor oil and steel slag aggregate in concrete
×
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