基于机器学习的 Vögelsberg 深层滑坡预报:为何预测缓慢变形并非易事

IF 4.2 2区 地球科学 Q1 GEOSCIENCES, MULTIDISCIPLINARY
A. V. van Natijne, T. Bogaard, T. Zieher, J. Pfeiffer, R. Lindenbergh
{"title":"基于机器学习的 Vögelsberg 深层滑坡预报:为何预测缓慢变形并非易事","authors":"A. V. van Natijne, T. Bogaard, T. Zieher, J. Pfeiffer, R. Lindenbergh","doi":"10.5194/nhess-23-3723-2023","DOIUrl":null,"url":null,"abstract":"Abstract. Landslides are one of the major weather-related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope processes is required. Landslide modelling is typically based on data-rich geomechanical models. Recently, machine learning has shown promising results in modelling a variety of processes. Furthermore, slope conditions are now also monitored from space, in wide-area repeat surveys from satellites. In the present study we tested if use of machine learning, combined with readily available remote sensing data, allows us to build a deformation nowcasting model. A successful landslide deformation nowcast, based on remote sensing data and machine learning, would demonstrate effective understanding of the slope processes, even in the absence of physical modelling. We tested our methodology on the Vögelsberg, a deep-seated landslide near Innsbruck, Austria. Our results show that the formulation of such a machine learning system is not as straightforward as often hoped for. The primary issue is the freedom of the model compared to the number of acceleration events in the time series available for training, as well as inherent limitations of the standard quality metrics such as the mean squared error. Satellite remote sensing has the potential to provide longer time series, over wide areas. However, although longer time series of deformation and slope conditions are clearly beneficial for machine-learning-based analyses, the present study shows the importance of the training data quality but also that this technique is mostly applicable to the well-monitored, more dynamic deforming landslides.\n","PeriodicalId":18922,"journal":{"name":"Natural Hazards and Earth System Sciences","volume":" 22","pages":""},"PeriodicalIF":4.2000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine-learning-based nowcasting of the Vögelsberg deep-seated landslide: why predicting slow deformation is not so easy\",\"authors\":\"A. V. van Natijne, T. Bogaard, T. Zieher, J. Pfeiffer, R. Lindenbergh\",\"doi\":\"10.5194/nhess-23-3723-2023\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract. Landslides are one of the major weather-related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope processes is required. Landslide modelling is typically based on data-rich geomechanical models. Recently, machine learning has shown promising results in modelling a variety of processes. Furthermore, slope conditions are now also monitored from space, in wide-area repeat surveys from satellites. In the present study we tested if use of machine learning, combined with readily available remote sensing data, allows us to build a deformation nowcasting model. A successful landslide deformation nowcast, based on remote sensing data and machine learning, would demonstrate effective understanding of the slope processes, even in the absence of physical modelling. We tested our methodology on the Vögelsberg, a deep-seated landslide near Innsbruck, Austria. Our results show that the formulation of such a machine learning system is not as straightforward as often hoped for. The primary issue is the freedom of the model compared to the number of acceleration events in the time series available for training, as well as inherent limitations of the standard quality metrics such as the mean squared error. Satellite remote sensing has the potential to provide longer time series, over wide areas. However, although longer time series of deformation and slope conditions are clearly beneficial for machine-learning-based analyses, the present study shows the importance of the training data quality but also that this technique is mostly applicable to the well-monitored, more dynamic deforming landslides.\\n\",\"PeriodicalId\":18922,\"journal\":{\"name\":\"Natural Hazards and Earth System Sciences\",\"volume\":\" 22\",\"pages\":\"\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2023-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Natural Hazards and Earth System Sciences\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.5194/nhess-23-3723-2023\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Natural Hazards and Earth System Sciences","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.5194/nhess-23-3723-2023","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

摘要。山体滑坡是与天气有关的主要地质灾害之一。为了评估其潜在影响和设计缓解方案,需要详细了解斜坡过程。滑坡建模通常基于数据丰富的地质力学模型。最近,机器学习在各种过程建模方面显示出有希望的结果。此外,现在还从空间监测斜坡情况,通过卫星进行大面积重复调查。在本研究中,我们测试了是否使用机器学习,结合现成的遥感数据,允许我们建立变形临近预报模型。基于遥感数据和机器学习的成功的滑坡变形临近预报,即使在没有物理建模的情况下,也将证明对边坡过程的有效理解。我们在奥地利因斯布鲁克附近的Vögelsberg深层滑坡上测试了我们的方法。我们的研究结果表明,这样一个机器学习系统的公式并不像人们通常希望的那样简单。主要问题是与时间序列中可用于训练的加速事件数量相比,模型的自由度,以及标准质量指标(如均方误差)的固有局限性。卫星遥感有可能在广大地区提供更长的时间序列。然而,尽管更长的变形和斜坡条件时间序列显然有利于基于机器学习的分析,但目前的研究表明,训练数据质量的重要性,而且这种技术主要适用于监测良好、更动态的变形滑坡。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Machine-learning-based nowcasting of the Vögelsberg deep-seated landslide: why predicting slow deformation is not so easy
Abstract. Landslides are one of the major weather-related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope processes is required. Landslide modelling is typically based on data-rich geomechanical models. Recently, machine learning has shown promising results in modelling a variety of processes. Furthermore, slope conditions are now also monitored from space, in wide-area repeat surveys from satellites. In the present study we tested if use of machine learning, combined with readily available remote sensing data, allows us to build a deformation nowcasting model. A successful landslide deformation nowcast, based on remote sensing data and machine learning, would demonstrate effective understanding of the slope processes, even in the absence of physical modelling. We tested our methodology on the Vögelsberg, a deep-seated landslide near Innsbruck, Austria. Our results show that the formulation of such a machine learning system is not as straightforward as often hoped for. The primary issue is the freedom of the model compared to the number of acceleration events in the time series available for training, as well as inherent limitations of the standard quality metrics such as the mean squared error. Satellite remote sensing has the potential to provide longer time series, over wide areas. However, although longer time series of deformation and slope conditions are clearly beneficial for machine-learning-based analyses, the present study shows the importance of the training data quality but also that this technique is mostly applicable to the well-monitored, more dynamic deforming landslides.
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
Natural Hazards and Earth System Sciences
Natural Hazards and Earth System Sciences 地学-地球科学综合
CiteScore
7.60
自引率
6.50%
发文量
192
审稿时长
3.8 months
期刊介绍: Natural Hazards and Earth System Sciences (NHESS) is an interdisciplinary and international journal dedicated to the public discussion and open-access publication of high-quality studies and original research on natural hazards and their consequences. Embracing a holistic Earth system science approach, NHESS serves a wide and diverse community of research scientists, practitioners, and decision makers concerned with detection of natural hazards, monitoring and modelling, vulnerability and risk assessment, and the design and implementation of mitigation and adaptation strategies, including economical, societal, and educational aspects.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信