Lennart Paul, Jorge-Humberto Urrea-Quintero, Umer Fiaz, Ali Hussein, Hazem Yaghi, Henning Wessels, Ulrich Römer, Joachim Stahlmann
{"title":"高斯过程在深层地质弃置中实现了模型校准","authors":"Lennart Paul, Jorge-Humberto Urrea-Quintero, Umer Fiaz, Ali Hussein, Hazem Yaghi, Henning Wessels, Ulrich Römer, Joachim Stahlmann","doi":"arxiv-2409.02576","DOIUrl":null,"url":null,"abstract":"This work introduces a surrogate modeling approach for an emplacement drift\nof a deep geological repository based on Gaussian Processes (GPs). The\nsurrogate model is used as a substitute for the high-fidelity mechanical model\nin many-query scenarios, such as time-dependent sensitivity analysis and\ncalibration. Our GP-based approach emulates the behavior of an emplacement\ndrift of a deep geological repository with significantly reduced computational\ntime, enabling faster design iterations and effective incorporation as well as\ninterpretation of monitoring data. Our findings show that only a few key\nparameters are essential for accurately reflecting in-situ conditions in\ncomplex rock salt models, which is critical for ensuring safety in deep\ngeological disposal.","PeriodicalId":501270,"journal":{"name":"arXiv - PHYS - Geophysics","volume":"26 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Gaussian Processes enabled model calibration in the context of deep geological disposal\",\"authors\":\"Lennart Paul, Jorge-Humberto Urrea-Quintero, Umer Fiaz, Ali Hussein, Hazem Yaghi, Henning Wessels, Ulrich Römer, Joachim Stahlmann\",\"doi\":\"arxiv-2409.02576\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work introduces a surrogate modeling approach for an emplacement drift\\nof a deep geological repository based on Gaussian Processes (GPs). The\\nsurrogate model is used as a substitute for the high-fidelity mechanical model\\nin many-query scenarios, such as time-dependent sensitivity analysis and\\ncalibration. Our GP-based approach emulates the behavior of an emplacement\\ndrift of a deep geological repository with significantly reduced computational\\ntime, enabling faster design iterations and effective incorporation as well as\\ninterpretation of monitoring data. Our findings show that only a few key\\nparameters are essential for accurately reflecting in-situ conditions in\\ncomplex rock salt models, which is critical for ensuring safety in deep\\ngeological disposal.\",\"PeriodicalId\":501270,\"journal\":{\"name\":\"arXiv - PHYS - Geophysics\",\"volume\":\"26 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Geophysics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.02576\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Geophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.02576","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
这项工作介绍了一种基于高斯过程(GPs)的深层地质储藏库位移漂移替代建模方法。代用模型可在多种查询场景中替代高保真力学模型,例如随时间变化的敏感性分析和校准。我们基于 GP 的方法模拟了深层地质资料库的位移漂移行为,大大缩短了计算时间,从而加快了设计迭代速度,并有效地纳入和解释了监测数据。我们的研究结果表明,要准确反映复杂岩盐模型的原位条件,只有几个关键参数是必不可少的,这对于确保深部地质处置的安全性至关重要。
Gaussian Processes enabled model calibration in the context of deep geological disposal
This work introduces a surrogate modeling approach for an emplacement drift
of a deep geological repository based on Gaussian Processes (GPs). The
surrogate model is used as a substitute for the high-fidelity mechanical model
in many-query scenarios, such as time-dependent sensitivity analysis and
calibration. Our GP-based approach emulates the behavior of an emplacement
drift of a deep geological repository with significantly reduced computational
time, enabling faster design iterations and effective incorporation as well as
interpretation of monitoring data. Our findings show that only a few key
parameters are essential for accurately reflecting in-situ conditions in
complex rock salt models, which is critical for ensuring safety in deep
geological disposal.