检索结果-南通市图书馆

Interpretability and spatial efficacy of a deep-learning-based on-site early warning framework using explainable artificial intelligence and geographically weighted random forests

引用

Geoscience Frontiers 2024年第5期15卷 182-196页

作者： Jawad Fayaz carmine galasso Department of Computer Science University of ExeterUK Department of Civil Environmentaland Geomatic EngineeringUniversity College London(UCL)LondonUK

Earthquakes pose significant risks globally,necessitating effective seismic risk mitigation strategies like earthquake early warning(EEW)***,developing and optimizing such systems requires thoroughly understanding their internal procedures and coverage *** study examines a deep-learning-based on-site EEW framework known as ROSERS(Real-time On-Site Estimation of Response Spectra)proposed by the authors,which constructs response spectra from early recorded ground motion waveforms at a target *** study has three primary goals:(1)evaluating the effectiveness and applicability of ROSERS to subduction seismic sources;(2)providing a detailed interpretation of the trained deep neural network(DNN)and surrogate latent variables(LVs)implemented in ROSERS;and(3)analyzing the spatial efficacy of the framework to assess the coverage area of on-site EEW *** is retrained and tested on a dataset of around 11,000 unprocessed Japanese subduction ground ***-of-fit testing shows that the ROSERS framework achieves good performance on this database,especially given the peculiarities of the subduction seismic *** trained DNN and LVs are then interpreted using game theory-based Shapley additive explanations to establish cause-effect ***,the study explores the coverage area of ROSERS by training a novel spatial regression model that estimates the LVs using geographically weighted random forest and determining the radius of *** results indicate that on-site predictions can be considered reliable within a 2–9 km radius,varying based on the magnitude and distance from the earthquake *** information can assist end-users in strategically placing sensors,minimizing blind spots,and reducing errors from regional extrapolation.

关键词： Earthquake early warning systems Spatial regression Neural networks Japanese subduction Explainable artificial intelligence

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Engineering Analysis of Strong Motion Data from Recent Earthquakes in Sichuan, China

引用

工程科学与技术 2018年第3期50卷 112-124页

作者： HUANG Chen galasso carmine Department of Civil Environmental and Geomatic Engineering University College London (UCL) London WC1E 6BT UK

Recent earthquakes in the Sichuan Province have contributed to significantly expand the existing ground-motion database for China with new,high-quality ground-motion *** study investigated the compatibility of ground-motion prediction equations(GMPEs)established by the NGA-West2 project in the US and local GMPEs for China,with respect to magnitude scaling,distance scaling,and site scaling implied by recent Chinese strong-motion *** NGA-West2 GMPEs for shallow crustal earthquakes in tectonically active regions are considerably more sophisticated than widely used previous models,particularly in *** a mixed-effects procedure,the study evaluated event terms(inter-event residuals)and intra-event residuals of Chinese data relative to the NGA-West2 *** scaling was investigated by examining trends of intra-event residuals with source-to-site *** with respect to site conditions was investigated by examining trends of intra-event residuals with soil *** study also investigated other engineering characteristics of Chinese strong ground *** particular,the records were analyzed for evidence of pulse-like forward-directivity *** elastic median response spectra of the selected stations were compared to code-mandated design spectra for various mean return *** showed that international and local GMPEs can be applied for seismic hazard analysis in Sichuan with minor modification of the regression coefficients related to the source-to-site distance and soil ***,the Chinese data attenuated faster than implied by the considered GMPEs and the differences were statistically significant in some ***-source,pulse-like ground motions were identified at two recording stations for the 2008 Wenchuan earthquake,possibly implying rupture *** median recorded spectra were consistent with the code-based spectra in terms of amplitude and *** new ground-motion data can be used to deve

关键词： ground motion prediction equations NGA-West2 project code-based spectrum pulse-like ground motions

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Likert Scale-Based Model for Benchmarking Operational Capacity,Organizational Resilience,and Disaster Risk Reduction

引用

International Journal of Disaster Risk Science 2020年第3期11卷 404-409页

作者： Gianluca Pescaroli Omar Velazquez Irasema Alcántara-Ayala carmine galasso Patty Kostkova David Alexander Institute for Risk and Disaster Reduction University College London(UCL)London WC1E 6BTUK Institute of Geography National Autonomous University of Mexico(UNAM)Mexico CityMexico Department of Civil Environmental and Geomatic EngineeringUniversity College London(UCL)London WC1E 6BTUK

Likert scales are a common methodological tool for data collection used in quantitative or mixed-method approaches in multiple *** are often employed in surveys or questionnaires,for benchmarking answers in the fields of disaster risk reduction,business continuity management,and organizational ***,both scholars and practitioners may lack a simple scale of reference to assure consistency across disciplinary *** article introduces a simple-to-use rating tool that can be used for benchmarking responses in questionnaires,for example,for assessing disaster risk reduction,gaps in operational capacity,and organizational *** aim,in particular,to support applications in contexts in which the target groups,due to cultural,social,or political reasons,may be unsuitable for in-depth analyses that use,for example,scales from 1 to 7 or from 1 to *** methodology is derived from the needs emerged in our recent fieldwork on interdisciplinary projects and from dialogue with the stakeholders *** output is a replicable scale from 0 to 3 presented in a table that includes category labels with qualitative attributes and descriptive equivalents to be used in the formulation of model *** include examples of levels of resilience,capacity,and *** are connected to other tools that could be used for in-depth *** advantage of our Likert scale-based response model is that it can be applied in a wide variety of disciplines,from social science to engineering.

关键词： Assessment Disaster risk reduction Interdisciplinary Likert scale Questionnaires Scales

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：