{"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 & 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.
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.