Pub Date : 2023-02-07DOI: 10.3390/geohazards4010004
H. Abbasgholiha, V. Gičev, M. Trifunac, R. S. Jalali, M. Todorovska
We present a simple nonlinear model of a shear-beam building that experiences large nonlinear deformations and collapse when excited by large pulses of strong earthquake ground motion. In this paper, we introduce the model and show that its properties can be selected to be consistent with the damage observed in a seven-story hotel in San Fernando Valley of the Los Angeles metropolitan area during the 1994 Northridge earthquake. We also show an example of excitation that leads to the collapse of the model. We illustrate the response only for a sequence of horizontal pulses. We will describe the response of the same model to horizontal, vertical, and rocking motions at its base, as well as for more general excitation by strong earthquake ground motion, in future papers.
{"title":"Collapsing Response of a Nonlinear Shear-Beam Building Model Excited by a Strong-Motion Pulse at Its Base","authors":"H. Abbasgholiha, V. Gičev, M. Trifunac, R. S. Jalali, M. Todorovska","doi":"10.3390/geohazards4010004","DOIUrl":"https://doi.org/10.3390/geohazards4010004","url":null,"abstract":"We present a simple nonlinear model of a shear-beam building that experiences large nonlinear deformations and collapse when excited by large pulses of strong earthquake ground motion. In this paper, we introduce the model and show that its properties can be selected to be consistent with the damage observed in a seven-story hotel in San Fernando Valley of the Los Angeles metropolitan area during the 1994 Northridge earthquake. We also show an example of excitation that leads to the collapse of the model. We illustrate the response only for a sequence of horizontal pulses. We will describe the response of the same model to horizontal, vertical, and rocking motions at its base, as well as for more general excitation by strong earthquake ground motion, in future papers.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"40 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2023-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75861796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-13DOI: 10.3390/geohazards4010003
R. Bhasin, Gokhan Aslan, J. Dehls
The Himalayan state of Sikkim is prone to some of the world’s largest landslides, which have caused catastrophic damage to lives, properties, and infrastructures in the region. The settlements along the steep valley sides are particularly subject to frequent rainfall-triggered landslide events during the monsoon season. The region has also experienced smaller rock slope failures (RSF) after the 2011 Sikkim earthquake. The surface displacement field is a critical observable for determining landslide depth and constraining failure mechanisms to develop effective mitigation techniques that minimise landslide damage. In the present study, the persistent scatterers InSAR (PSI) method is employed to process the series of Sentinel 1-A/B synthetic aperture radar (SAR) images acquired between 2015 and 2021 along ascending and descending orbits for the selected areas in Gangtok, Sikkim, to detect potentially active, landslide-prone areas. InSAR-derived ground surface displacements and their spatio-temporal evolutions are combined with field investigations to better understand the state of activity and landslide risk assessment. Field investigations confirm the ongoing ground surface displacements revealed by the InSAR results. Some urban areas have been completely abandoned due to the structural damage to residential housing, schools, and office buildings caused by displacement. This paper relates the geotechnical investigations carried out on the ground to the data obtained through interferometric synthetic aperture radar (InSAR), focusing on the triggering mechanisms. A strong correlation between seasonal rainfall and landslide acceleration, as well as predisposing geological-structural setting, suggest a causative mechanism of the landslides.
{"title":"Ground Investigations and Detection and Monitoring of Landslides Using SAR Interferometry in Gangtok, Sikkim Himalaya","authors":"R. Bhasin, Gokhan Aslan, J. Dehls","doi":"10.3390/geohazards4010003","DOIUrl":"https://doi.org/10.3390/geohazards4010003","url":null,"abstract":"The Himalayan state of Sikkim is prone to some of the world’s largest landslides, which have caused catastrophic damage to lives, properties, and infrastructures in the region. The settlements along the steep valley sides are particularly subject to frequent rainfall-triggered landslide events during the monsoon season. The region has also experienced smaller rock slope failures (RSF) after the 2011 Sikkim earthquake. The surface displacement field is a critical observable for determining landslide depth and constraining failure mechanisms to develop effective mitigation techniques that minimise landslide damage. In the present study, the persistent scatterers InSAR (PSI) method is employed to process the series of Sentinel 1-A/B synthetic aperture radar (SAR) images acquired between 2015 and 2021 along ascending and descending orbits for the selected areas in Gangtok, Sikkim, to detect potentially active, landslide-prone areas. InSAR-derived ground surface displacements and their spatio-temporal evolutions are combined with field investigations to better understand the state of activity and landslide risk assessment. Field investigations confirm the ongoing ground surface displacements revealed by the InSAR results. Some urban areas have been completely abandoned due to the structural damage to residential housing, schools, and office buildings caused by displacement. This paper relates the geotechnical investigations carried out on the ground to the data obtained through interferometric synthetic aperture radar (InSAR), focusing on the triggering mechanisms. A strong correlation between seasonal rainfall and landslide acceleration, as well as predisposing geological-structural setting, suggest a causative mechanism of the landslides.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"42 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74529232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-13DOI: 10.3390/geohazards4010002
High-quality academic publishing is built on rigorous peer review [...]
高质量的学术出版建立在严格的同行评审的基础上[…]
{"title":"Acknowledgment to the Reviewers of GeoHazards in 2022","authors":"","doi":"10.3390/geohazards4010002","DOIUrl":"https://doi.org/10.3390/geohazards4010002","url":null,"abstract":"High-quality academic publishing is built on rigorous peer review [...]","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"43 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2023-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89474764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-12DOI: 10.1080/17499518.2023.2164901
Shi-hua Zheng, S. Nishimura, T. Shuku, T. Shibata, Tsubasa Tateishi
ABSTRACT This paper discusses a risk evaluation for earth-fill dams due to heavy rains. The detailed method employs a flood analysis and land use data to calculate the costs of the inundation damage in the downstream areas of earth-fill dams. The procedure to calculate the damage costs requires a lot of labour. Since a huge number of earth-fill dams exist in Japan, a straightforward method is needed. The response surface method, one of the surrogate models, is proposed in this study to reduce the calculation effort. The optimum response surface is firstly evaluated by cross validation, and then the accuracy is verified by comparing the damage costs obtained by the response surface method with those obtained by the detailed method for the earth-fill dam sites. To calculate the risks, it is necessary to determine the probability of overflow failure due to heavy rains. The risk of breaching is calculated from the product of the probability of overflow failure and the estimated damage costs. The accuracy of the response surface method is assessed by comparing the risk rankings of the dams, which is the priority in dam renovations, between the detailed and the response surface methods.
{"title":"Risk evaluation for earth-fill dams due to heavy rains by response surface method","authors":"Shi-hua Zheng, S. Nishimura, T. Shuku, T. Shibata, Tsubasa Tateishi","doi":"10.1080/17499518.2023.2164901","DOIUrl":"https://doi.org/10.1080/17499518.2023.2164901","url":null,"abstract":"ABSTRACT This paper discusses a risk evaluation for earth-fill dams due to heavy rains. The detailed method employs a flood analysis and land use data to calculate the costs of the inundation damage in the downstream areas of earth-fill dams. The procedure to calculate the damage costs requires a lot of labour. Since a huge number of earth-fill dams exist in Japan, a straightforward method is needed. The response surface method, one of the surrogate models, is proposed in this study to reduce the calculation effort. The optimum response surface is firstly evaluated by cross validation, and then the accuracy is verified by comparing the damage costs obtained by the response surface method with those obtained by the detailed method for the earth-fill dam sites. To calculate the risks, it is necessary to determine the probability of overflow failure due to heavy rains. The risk of breaching is calculated from the product of the probability of overflow failure and the estimated damage costs. The accuracy of the response surface method is assessed by comparing the risk rankings of the dams, which is the priority in dam renovations, between the detailed and the response surface methods.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"17 1","pages":"572 - 585"},"PeriodicalIF":4.8,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49589586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ABSTRACT Landslides, one of the most common mountain hazards, can result in enormous casualties and huge economic losses in mountainous regions. In order to address the landslide hazards effectively, the geological society is required not only to develop in-depth understanding of landslide mechanism but also to quantify its associated risk. In this article, landslide risk assessment is categorised into two types, hard and soft risk assessments, and reviewed separately. The hard approach focuses on the mechanics and numerical simulations of individual landslides, subsequent consequences, and their uncertainty quantifications and probabilistic analyses while the soft approach explores the quantification of disaster risk components such as hazard and vulnerability at different scales of concern. It is hoped that this article can serve as a time capsule to link the preceding and following of landslide risk assessments and shed some light on future studies.
{"title":"Time capsule for landslide risk assessment","authors":"Yu Lei, Jinsong Huang, Yifei Cui, Shui-Hua Jiang, Sheng-nan Wu, J. Ching","doi":"10.1080/17499518.2023.2164899","DOIUrl":"https://doi.org/10.1080/17499518.2023.2164899","url":null,"abstract":"ABSTRACT Landslides, one of the most common mountain hazards, can result in enormous casualties and huge economic losses in mountainous regions. In order to address the landslide hazards effectively, the geological society is required not only to develop in-depth understanding of landslide mechanism but also to quantify its associated risk. In this article, landslide risk assessment is categorised into two types, hard and soft risk assessments, and reviewed separately. The hard approach focuses on the mechanics and numerical simulations of individual landslides, subsequent consequences, and their uncertainty quantifications and probabilistic analyses while the soft approach explores the quantification of disaster risk components such as hazard and vulnerability at different scales of concern. It is hoped that this article can serve as a time capsule to link the preceding and following of landslide risk assessments and shed some light on future studies.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":" ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47789134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-09DOI: 10.1080/17499518.2023.2164900
Jayne M. Han, Kyo-Young Gu, Kyeong-Sun Kim, Kyung-Won Ham, Sung-Ryul Kim
ABSTRACT The design of foundations is often governed by the serviceability limit state (SLS) requirements of the supported structure, particularly for large spread foundations. This paper aims to develop a reliability-based SLS design method for spread foundations under uplift loading in cohesionless soils. A probabilistic framework was adopted for the empirical characterisation of the compiled load-displacement curves and the quantification of the associated uncertainties. By using the obtained statistics of the curves, reliability analysis was carried out with Monte-Carlo simulations to calibrate the resistance factors within the load and resistance factor design (LRFD) framework. The calibration results showed that the embedment ratio of the foundation and the fitting errors of the empirical model, which were previously unaddressed in the literature, had notable effects on the calibrated SLS resistance factors. The relationship of the SLS with the ultimate limit state was assessed, including the governing limit state at each allowable displacement level, and the probability of ultimate failure of the foundation at the SLS condition. By considering the relationship between the limit states, the procedures for determining the design resistance factor and foundation capacity were proposed.
{"title":"Reliability-based serviceability limit state design of spread foundations under uplift loading in cohesionless soils","authors":"Jayne M. Han, Kyo-Young Gu, Kyeong-Sun Kim, Kyung-Won Ham, Sung-Ryul Kim","doi":"10.1080/17499518.2023.2164900","DOIUrl":"https://doi.org/10.1080/17499518.2023.2164900","url":null,"abstract":"ABSTRACT The design of foundations is often governed by the serviceability limit state (SLS) requirements of the supported structure, particularly for large spread foundations. This paper aims to develop a reliability-based SLS design method for spread foundations under uplift loading in cohesionless soils. A probabilistic framework was adopted for the empirical characterisation of the compiled load-displacement curves and the quantification of the associated uncertainties. By using the obtained statistics of the curves, reliability analysis was carried out with Monte-Carlo simulations to calibrate the resistance factors within the load and resistance factor design (LRFD) framework. The calibration results showed that the embedment ratio of the foundation and the fitting errors of the empirical model, which were previously unaddressed in the literature, had notable effects on the calibrated SLS resistance factors. The relationship of the SLS with the ultimate limit state was assessed, including the governing limit state at each allowable displacement level, and the probability of ultimate failure of the foundation at the SLS condition. By considering the relationship between the limit states, the procedures for determining the design resistance factor and foundation capacity were proposed.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":" ","pages":""},"PeriodicalIF":4.8,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49616726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-02DOI: 10.1080/17499518.2023.2184834
Xu Li, Haibo Li, Saizhao Du, Liujie Jing, Pengyu Li
ABSTRACT The variation in Tunnelling boring machine (TBM) equipment and geological information of tunnels result in substantial differences in real-time TBM tunnelling data. This variation makes it difficult to apply machine learning models trained by historical engineering data on new projects. To overcome this challenge, a novel data conversion approach from a mechanical analysis perspective has been proposed to normalise TBM tunnelling data, such as cutterhead torque and cutterhead thrust, which help to unify data from different projects under the same framework. Furthermore, the effectiveness of this approach has been verified through analogy analysis and machine learning applications. With the application of these conversion relationships, the machine learning model trained on a completed Yin-Song project with big data (12,501 boring cycles) is applied to the on-going Yin-Chao Water Diversion Project in China with limited data (777 boring cycles) and gives reliable predictions for each performance parameter (with R2 for the cutterhead thrust of 0.81 and R2 for the cutterhead torque of 0.70). This approach enhances the usefulness of TBM intelligence for cross-engineering geophysical prospecting in different geological conditions.
{"title":"Cross-project utilisation of tunnel boring machine (TBM) construction data: a case study using big data from Yin-Song diversion project in China","authors":"Xu Li, Haibo Li, Saizhao Du, Liujie Jing, Pengyu Li","doi":"10.1080/17499518.2023.2184834","DOIUrl":"https://doi.org/10.1080/17499518.2023.2184834","url":null,"abstract":"ABSTRACT The variation in Tunnelling boring machine (TBM) equipment and geological information of tunnels result in substantial differences in real-time TBM tunnelling data. This variation makes it difficult to apply machine learning models trained by historical engineering data on new projects. To overcome this challenge, a novel data conversion approach from a mechanical analysis perspective has been proposed to normalise TBM tunnelling data, such as cutterhead torque and cutterhead thrust, which help to unify data from different projects under the same framework. Furthermore, the effectiveness of this approach has been verified through analogy analysis and machine learning applications. With the application of these conversion relationships, the machine learning model trained on a completed Yin-Song project with big data (12,501 boring cycles) is applied to the on-going Yin-Chao Water Diversion Project in China with limited data (777 boring cycles) and gives reliable predictions for each performance parameter (with R2 for the cutterhead thrust of 0.81 and R2 for the cutterhead torque of 0.70). This approach enhances the usefulness of TBM intelligence for cross-engineering geophysical prospecting in different geological conditions.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"17 1","pages":"127 - 147"},"PeriodicalIF":4.8,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43920960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-02DOI: 10.1080/17499518.2023.2172186
N. Xi, M. Zang, Ruoshen Lin, Yingjie Sun, Gang Mei
ABSTRACT The use of deep learning approaches to predict landslide displacement based on monitored time-series data is an effective method for the early-warning of landslides. Currently, most prediction models focus on the temporal correlation of displacements from a single monitoring point, ignoring the spatial influence of other monitoring points. To fully consider the spatiotemporal features of the displacement data, this paper develops three deep learning models based on graph convolution networks to spatiotemporally predict the landslide displacements of the Huanglianshu landslide. Specifically, we first establish a fully connected graph to represent the spatial relationships of all the deployed monitoring points. Second, we develop a temporal graph convolutional network-long short term memory (TGCN-LSTM) model and an Attention-TGCN model based on the temporal graph convolutional network-gate recurrent unit (TGCN-GRU) deep learning model and employ the three models to spatiotemporally predict displacements of the Huanglianshu landslide. The proposed spatiotemporal prediction models accurately predict the displacements at seven monitoring points, with a maximum R 2 of 0.85 at the individual monitoring points. The comparative results show that the proposed Attention-TGCN model achieves the highest spatiotemporal prediction accuracy, and the accuracy of the Attention-TGCN model can further improve after considering the movement of the monitoring points.
{"title":"Spatiotemporal prediction of landslide displacement using deep learning approaches based on monitored time-series displacement data: a case in the Huanglianshu landslide","authors":"N. Xi, M. Zang, Ruoshen Lin, Yingjie Sun, Gang Mei","doi":"10.1080/17499518.2023.2172186","DOIUrl":"https://doi.org/10.1080/17499518.2023.2172186","url":null,"abstract":"ABSTRACT The use of deep learning approaches to predict landslide displacement based on monitored time-series data is an effective method for the early-warning of landslides. Currently, most prediction models focus on the temporal correlation of displacements from a single monitoring point, ignoring the spatial influence of other monitoring points. To fully consider the spatiotemporal features of the displacement data, this paper develops three deep learning models based on graph convolution networks to spatiotemporally predict the landslide displacements of the Huanglianshu landslide. Specifically, we first establish a fully connected graph to represent the spatial relationships of all the deployed monitoring points. Second, we develop a temporal graph convolutional network-long short term memory (TGCN-LSTM) model and an Attention-TGCN model based on the temporal graph convolutional network-gate recurrent unit (TGCN-GRU) deep learning model and employ the three models to spatiotemporally predict displacements of the Huanglianshu landslide. The proposed spatiotemporal prediction models accurately predict the displacements at seven monitoring points, with a maximum R 2 of 0.85 at the individual monitoring points. The comparative results show that the proposed Attention-TGCN model achieves the highest spatiotemporal prediction accuracy, and the accuracy of the Attention-TGCN model can further improve after considering the movement of the monitoring points.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"17 1","pages":"98 - 113"},"PeriodicalIF":4.8,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44313965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-02DOI: 10.1080/17499518.2023.2185938
K. Phoon, L. M. Zhang, Z. Cao
The potential for machine learning and artificial intelligence to shape geotechnical engineering practice (and possibly theory) is immense. However, the agenda for machine learning in geotechnics should not be focused on applying or developing algorithms alone. The geotechnical context that gives rise to the data is important. The context can be related to statistics, physics, or experience. Statistics refer to the attributes of geotechnical data that depart significantly from the assumptions in classical statistics (large sample size, spatial/temporal/parametric independence, homogeneity, normality, etc.). Phoon, Ching, and Shuku (2022a) argued that geotechnical site data are “ugly”, because they are spatially varying, sparse, site-specific (or unique to some extent), and incomplete in the sense that a multivariate database is full of empty entries denoting lack of some measurements at certain locations/depths. The incompleteness attribute arises from an intent to maximize information on cross correlations between different soil parameters and geotechnical/geologic spatial correlations across a given site while minimizing the site investigation budget. At this point, this value of information optimization is an art rather than a science. The scientific challenge to draw useful insights from MUSIC-3X (Multivariate, Uncertain and Unique, Sparse, Incomplete, and potentially Corrupted with “3X” denoting 3D spatial variability) data was thought to be intractable until recently (Phoon, Ching, and Shuku 2022a). These “ugly” data attributes are the norm in a site investigation report. In rock engineering, data can be categorical rather than numerical. Phoon (2023) emphasized that “decision making in every discipline is supported by its own data with unique attributes and a tradition of successful practice (investigation, design, construction, testing, monitoring, and risk management methodology) that evolved to make the best use of these data and prevailing technologies”. Physics refers to a body of rational knowledge that associates a “number” to “meaning”. Decisions supported by physics-informed results are “explainable” and “interpretable”. The finite element method is the most prevalent embodiment of physics in geotechnical engineering. Using finite element analysis, an engineer understands cause and effect (interpretability) and knows which input parameters affect the outputs (explainability). An engineer distinguishes between material and state parameters, between effective and total stress parameters, and between input and output parameters from a physical or numerical model. These distinctions exist when one approaches data from the lens of physics. Experience refers to a body of empirical knowledge accrued from deliberate practice. It is restricted by the range of projects encountered by an engineer over his/ her working life and it cannot be shared with other engineers efficiently. In contrast to statistics and physics, it is mainly subjective
机器学习和人工智能塑造岩土工程实践(可能还有理论)的潜力是巨大的。然而,岩土工程中机器学习的议程不应该只关注应用或开发算法。产生这些数据的岩土技术背景很重要。上下文可以与统计、物理或经验相关。统计学是指岩土工程数据的属性与经典统计学中的假设(大样本量、空间/时间/参数独立性、同质性、正态性等)有显著差异。Phoon, Ching和Shuku (2022a)认为岩土工程场地数据是“丑陋的”,因为它们在空间上是变化的、稀疏的、特定于场地的(或在某种程度上是唯一的),并且在多元数据库中充满了空条目,这意味着在某些位置/深度缺乏一些测量。不完整性属性源于在最小化现场调查预算的同时,最大化不同土壤参数和岩土/地质空间相关性之间相互关联的信息的意图。在这一点上,信息优化的价值是一门艺术,而不是一门科学。从MUSIC-3X(多元、不确定和唯一、稀疏、不完整和潜在损坏的“3X”表示3D空间变异性)数据中提取有用见解的科学挑战直到最近才被认为是棘手的(Phoon, Ching, and Shuku 2022a)。这些“丑陋”的数据属性在现场调查报告中是常态。在岩石工程中,数据可以是分类的,而不是数字的。Phoon(2023)强调:“每个学科的决策都有其独特属性的数据和成功实践(调查、设计、施工、测试、监测和风险管理方法)的传统支持,这些传统是为了充分利用这些数据和流行技术而发展起来的。”物理学指的是将“数字”与“意义”联系起来的一套理性知识。由物理学结果支持的决策是“可解释的”和“可解释的”。有限元法是岩土工程中最常用的物理方法。使用有限元分析,工程师可以理解因果关系(可解释性),并知道哪些输入参数会影响输出(可解释性)。工程师区分材料和状态参数,有效和总应力参数,以及物理或数值模型的输入和输出参数。当人们从物理学的角度来看待数据时,这些区别就存在了。经验是指从有意识的练习中积累的经验知识。它受到工程师在其工作生涯中遇到的项目范围的限制,并且无法与其他工程师有效地共享。与统计学和物理学相比,它主要是主观的和定性的。尽管如此,许多工程师认为经验至关重要。例如,辛普森(2011)解释了为什么欧洲规范7 (EC7)的表述是为了确保工程师在决策中始终拥有完全的所有权:“EC7试图通过让设计师负责材料特征值的选择来做到这一点,避免其推导的数学处方。在这个过程中,不可避免地会产生受设计师主观经验、知识和判断影响的价值观。笔者认为,与其抛弃这种主观性所提供的有价值的信息,还不如接受这种主观性。”在机器学习中,经验被视为一种“厚数据”,以区别于更广为人知的定量“大数据”。当前实践中的决策是基于物理和经验的。除了定性的指导方针,如伯兰三角(伯兰1987;Phoon et al. 2022b)或Wroth规则(Wroth 1984;Phoon 2023)。因此,岩土工程实践更多地被认为是一门“艺术”而不是一门“科学”。Phoon(2023)认为,鉴于数字技术的日益强大、无处不在和融合,决策将越来越多地依赖于数据,并提出了一个数据支持决策指数(DIDI)来跟踪这一演变。将岩土可靠度视为一个阶段
{"title":"Special issue on “Machine learning and AI in geotechnics”","authors":"K. Phoon, L. M. Zhang, Z. Cao","doi":"10.1080/17499518.2023.2185938","DOIUrl":"https://doi.org/10.1080/17499518.2023.2185938","url":null,"abstract":"The potential for machine learning and artificial intelligence to shape geotechnical engineering practice (and possibly theory) is immense. However, the agenda for machine learning in geotechnics should not be focused on applying or developing algorithms alone. The geotechnical context that gives rise to the data is important. The context can be related to statistics, physics, or experience. Statistics refer to the attributes of geotechnical data that depart significantly from the assumptions in classical statistics (large sample size, spatial/temporal/parametric independence, homogeneity, normality, etc.). Phoon, Ching, and Shuku (2022a) argued that geotechnical site data are “ugly”, because they are spatially varying, sparse, site-specific (or unique to some extent), and incomplete in the sense that a multivariate database is full of empty entries denoting lack of some measurements at certain locations/depths. The incompleteness attribute arises from an intent to maximize information on cross correlations between different soil parameters and geotechnical/geologic spatial correlations across a given site while minimizing the site investigation budget. At this point, this value of information optimization is an art rather than a science. The scientific challenge to draw useful insights from MUSIC-3X (Multivariate, Uncertain and Unique, Sparse, Incomplete, and potentially Corrupted with “3X” denoting 3D spatial variability) data was thought to be intractable until recently (Phoon, Ching, and Shuku 2022a). These “ugly” data attributes are the norm in a site investigation report. In rock engineering, data can be categorical rather than numerical. Phoon (2023) emphasized that “decision making in every discipline is supported by its own data with unique attributes and a tradition of successful practice (investigation, design, construction, testing, monitoring, and risk management methodology) that evolved to make the best use of these data and prevailing technologies”. Physics refers to a body of rational knowledge that associates a “number” to “meaning”. Decisions supported by physics-informed results are “explainable” and “interpretable”. The finite element method is the most prevalent embodiment of physics in geotechnical engineering. Using finite element analysis, an engineer understands cause and effect (interpretability) and knows which input parameters affect the outputs (explainability). An engineer distinguishes between material and state parameters, between effective and total stress parameters, and between input and output parameters from a physical or numerical model. These distinctions exist when one approaches data from the lens of physics. Experience refers to a body of empirical knowledge accrued from deliberate practice. It is restricted by the range of projects encountered by an engineer over his/ her working life and it cannot be shared with other engineers efficiently. In contrast to statistics and physics, it is mainly subjective","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"17 1","pages":"1 - 6"},"PeriodicalIF":4.8,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45961885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-02DOI: 10.1080/17499518.2023.2182891
Junjie Ma, Tianbin Li, Gang Yang, Kunkun Dai, Chun-chi Ma, Hao Tang, Gangwei Wang, Jianfeng Wang, Bo Xiao, Lu-bo Meng
ABSTRACT Real-time and accurate prediction of surrounding rock grade is crucial for tunnel dynamic construction and design. However, the internationally accepted semi-quantitative methods (e.g. rock mass rating (RMR), Q, and basic quality (BQ)) cannot provide fast and accurate classification in construction. This study proposed an intelligent surrounding rock classification method and a tunnel information management system, which can predict the surrounding rock grade in real-time and accurately. A database is collected with 286 cases in China, including seven geological parameters and surrounding rock grades. Based on different training parameters, 12 classification models are established using VGGNet, ResNet, and support vector machine (SVM) algorithms. The accuracy of the SVM classifier is 93.02%, which performs better than the VGGNet and ResNet classifiers. Moreover, precision, recall, F-measure, receiver operating characteristic (ROC), and 20-case verification show that the SVM classification model has greater robustness in learning and generalising for small and imbalanced samples. Additionally, a tunnel information management system is developed with cloud technology, which can accurately predict the surrounding rock grade within 10 s. Overall, the achievements of this study can provide valuable references for real-time rock mass classification in traffic tunnels and underground powerhouses.
{"title":"A real-time intelligent classification model using machine learning for tunnel surrounding rock and its application","authors":"Junjie Ma, Tianbin Li, Gang Yang, Kunkun Dai, Chun-chi Ma, Hao Tang, Gangwei Wang, Jianfeng Wang, Bo Xiao, Lu-bo Meng","doi":"10.1080/17499518.2023.2182891","DOIUrl":"https://doi.org/10.1080/17499518.2023.2182891","url":null,"abstract":"ABSTRACT Real-time and accurate prediction of surrounding rock grade is crucial for tunnel dynamic construction and design. However, the internationally accepted semi-quantitative methods (e.g. rock mass rating (RMR), Q, and basic quality (BQ)) cannot provide fast and accurate classification in construction. This study proposed an intelligent surrounding rock classification method and a tunnel information management system, which can predict the surrounding rock grade in real-time and accurately. A database is collected with 286 cases in China, including seven geological parameters and surrounding rock grades. Based on different training parameters, 12 classification models are established using VGGNet, ResNet, and support vector machine (SVM) algorithms. The accuracy of the SVM classifier is 93.02%, which performs better than the VGGNet and ResNet classifiers. Moreover, precision, recall, F-measure, receiver operating characteristic (ROC), and 20-case verification show that the SVM classification model has greater robustness in learning and generalising for small and imbalanced samples. Additionally, a tunnel information management system is developed with cloud technology, which can accurately predict the surrounding rock grade within 10 s. Overall, the achievements of this study can provide valuable references for real-time rock mass classification in traffic tunnels and underground powerhouses.","PeriodicalId":48524,"journal":{"name":"Georisk-Assessment and Management of Risk for Engineered Systems and Geohazards","volume":"17 1","pages":"148 - 168"},"PeriodicalIF":4.8,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49088831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}