Pub Date : 2023-12-14DOI: 10.1109/mcse.2023.3342149
Jie Wang
This tutorial aims to provide an intuitive introduction to Gaussian process regression (GPR). GPR models have been widely used in machine learning applications due to their representation flexibility and inherent capability to quantify uncertainty over predictions. The tutorial starts with explaining the basic concepts that a Gaussian process is built on, including multivariate normal distribution, kernels, nonparametric models, and joint and conditional probability. It then provides a concise description of GPR and an implementation of a standard GPR algorithm. In addition, the tutorial reviews packages for implementing state-of-the-art Gaussian process algorithms. This tutorial is accessible to a broad audience, including those new to machine learning, ensuring a clear understanding of GPR fundamentals.
{"title":"An Intuitive Tutorial to Gaussian Process Regression","authors":"Jie Wang","doi":"10.1109/mcse.2023.3342149","DOIUrl":"https://doi.org/10.1109/mcse.2023.3342149","url":null,"abstract":"This tutorial aims to provide an intuitive introduction to Gaussian process regression (GPR). GPR models have been widely used in machine learning applications due to their representation flexibility and inherent capability to quantify uncertainty over predictions. The tutorial starts with explaining the basic concepts that a Gaussian process is built on, including multivariate normal distribution, kernels, nonparametric models, and joint and conditional probability. It then provides a concise description of GPR and an implementation of a standard GPR algorithm. In addition, the tutorial reviews packages for implementing state-of-the-art Gaussian process algorithms. This tutorial is accessible to a broad audience, including those new to machine learning, ensuring a clear understanding of GPR fundamentals.","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139767504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-11DOI: 10.1109/mcse.2023.3340434
Stijn Hendrikx, Raphaël Widdershoven, Nico Vervliet, Lieven De Lathauwer
Tensor methods emerge as an important class of basic techniques, generalizing matrix methods to multiway data and models. We have recently released Tensorlab+, which is a downloadable archive of code and data that allows peers to reproduce the experiments reported in our publications on tensor decompositions and applications. We briefly discuss the basic tensor tools and give an introduction to the contents of Tensorlab+. We elaborate on the steps that were taken to ensure the reproducibility of the experiments and the quality of the code.
{"title":"Tensorlab+: A Case Study on Reproducibility in Tensor Research","authors":"Stijn Hendrikx, Raphaël Widdershoven, Nico Vervliet, Lieven De Lathauwer","doi":"10.1109/mcse.2023.3340434","DOIUrl":"https://doi.org/10.1109/mcse.2023.3340434","url":null,"abstract":"Tensor methods emerge as an important class of basic techniques, generalizing matrix methods to multiway data and models. We have recently released Tensorlab+, which is a downloadable archive of code and data that allows peers to reproduce the experiments reported in our publications on tensor decompositions and applications. We briefly discuss the basic tensor tools and give an introduction to the contents of Tensorlab+. We elaborate on the steps that were taken to ensure the reproducibility of the experiments and the quality of the code.","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140623667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3311148
Torsten Hoefler, Bjorn Stevens, Andreas F. Prein, Johanna Baehr, Thomas Schulthess, Thomas F. Stocker, John Taylor, Daniel Klocke, Pekka Manninen, Piers M. Forster, Tobias Kölling, Nicolas Gruber, Hartwig Anzt, Claudia Frauen, Florian Ziemen, Milan Klöwer, Karthik Kashinath, Christoph Schär, Oliver Fuhrer, Bryan N. Lawrence
Participants of the Berlin Summit on Earth Virtualization Engines (EVEs) discussed ideas and concepts to improve our ability to cope with climate change. EVEs aim to provide interactive and accessible climate simulations and data for a wide range of users. They combine high-resolution physics-based models with machine learning techniques to improve the fidelity, efficiency, and interpretability of climate projections. At its core, EVEs offer a federated data layer that enables simple and fast access to exabyte-sized climate data through simple interfaces. In this article, we summarize the technical challenges and opportunities for developing EVEs, and argue that they are essential for addressing the consequences of climate change.
{"title":"Earth Virtualization Engines: A Technical Perspective","authors":"Torsten Hoefler, Bjorn Stevens, Andreas F. Prein, Johanna Baehr, Thomas Schulthess, Thomas F. Stocker, John Taylor, Daniel Klocke, Pekka Manninen, Piers M. Forster, Tobias Kölling, Nicolas Gruber, Hartwig Anzt, Claudia Frauen, Florian Ziemen, Milan Klöwer, Karthik Kashinath, Christoph Schär, Oliver Fuhrer, Bryan N. Lawrence","doi":"10.1109/mcse.2023.3311148","DOIUrl":"https://doi.org/10.1109/mcse.2023.3311148","url":null,"abstract":"Participants of the Berlin Summit on Earth Virtualization Engines (EVEs) discussed ideas and concepts to improve our ability to cope with climate change. EVEs aim to provide interactive and accessible climate simulations and data for a wide range of users. They combine high-resolution physics-based models with machine learning techniques to improve the fidelity, efficiency, and interpretability of climate projections. At its core, EVEs offer a federated data layer that enables simple and fast access to exabyte-sized climate data through simple interfaces. In this article, we summarize the technical challenges and opportunities for developing EVEs, and argue that they are essential for addressing the consequences of climate change.","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3318749
Anne Fouilloux, Jean Iaquinta, Alok Kumar Gupta, Hamish Struthers, Oskar Landgren, Prashanth Dwarakanath, Tommi Bergman, Yanchun He
The Nordic e-Infrastructure Collaboration on Earth System Modeling Tools is a small community comprising members with diverse backgrounds, skills, and interests. Largely dependent on temporary staff to develop, operate, and maintain large scientific codes, this community devised strategies to enhance software reusability and sustainability. These strategies include collaborating with other communities for support, adopting Open Science as well as findable, accessible, interoperable, and reusable principles to optimize resource usage, growing essential knowledge within the community, and setting up a community of practice to facilitate onboarding and offboarding. The strategies also promote inclusiveness, foster external collaboration, and recognize technical contributions.
{"title":"Building on Communities to Further Software Sustainability","authors":"Anne Fouilloux, Jean Iaquinta, Alok Kumar Gupta, Hamish Struthers, Oskar Landgren, Prashanth Dwarakanath, Tommi Bergman, Yanchun He","doi":"10.1109/mcse.2023.3318749","DOIUrl":"https://doi.org/10.1109/mcse.2023.3318749","url":null,"abstract":"The Nordic e-Infrastructure Collaboration on Earth System Modeling Tools is a small community comprising members with diverse backgrounds, skills, and interests. Largely dependent on temporary staff to develop, operate, and maintain large scientific codes, this community devised strategies to enhance software reusability and sustainability. These strategies include collaborating with other communities for support, adopting Open Science as well as findable, accessible, interoperable, and reusable principles to optimize resource usage, growing essential knowledge within the community, and setting up a community of practice to facilitate onboarding and offboarding. The strategies also promote inclusiveness, foster external collaboration, and recognize technical contributions.","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3324157
{"title":"IEEE Transactions on Sustainable Computing","authors":"","doi":"10.1109/mcse.2023.3324157","DOIUrl":"https://doi.org/10.1109/mcse.2023.3324157","url":null,"abstract":"","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3324161
{"title":"IEEE Computer Society Call for Papers","authors":"","doi":"10.1109/mcse.2023.3324161","DOIUrl":"https://doi.org/10.1109/mcse.2023.3324161","url":null,"abstract":"","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3317773
Nathan W. Schoedl, Emma J. MacKie, Michael J. Field, Eric A. Stubbs, Allan Zhang, Matthew Hibbs, Mathieu Gravey
Realistically rough stochastic realizations of subglacial bed topography are crucial for improving our understanding of basal processes and quantifying uncertainty in sea-level rise projections with respect to topographic uncertainty. This can be achieved with Sequential Gaussian Simulation (SGS), which is used to generate multiple non-unique realizations of geological phenomena that sample the uncertainty space. However, SGS is very CPU intensive with a computational complexity of O( Nk 3 ), where N is the number of grid cells to simulate, and k is the number of neighboring points used for conditioning. This complexity makes SGS prohibitively time-consuming to implement at ice-sheet scales or fine resolutions. To reduce the time-cost, we implement and test a multiprocess version of SGS using Python’s multiprocessing module. By parallelizing the calculation of the weight parameters used in SGS, we achieve a speedup of 9.5 running on 16 processors for an N of 128,097. This speedup, as well as the speedup from using multiple processors, increases with N . This speed improvement makes SGS viable for large-scale topography mapping and ensemble ice-sheet modeling. Additionally, we have made our code repository and user tutorials publicly available (GitHub, Zenodo that others can use our multiprocess implementation of SGS on different datasets.
{"title":"A Python multiprocessing approach for fast geostatistical simulations of subglacial topography","authors":"Nathan W. Schoedl, Emma J. MacKie, Michael J. Field, Eric A. Stubbs, Allan Zhang, Matthew Hibbs, Mathieu Gravey","doi":"10.1109/mcse.2023.3317773","DOIUrl":"https://doi.org/10.1109/mcse.2023.3317773","url":null,"abstract":"Realistically rough stochastic realizations of subglacial bed topography are crucial for improving our understanding of basal processes and quantifying uncertainty in sea-level rise projections with respect to topographic uncertainty. This can be achieved with Sequential Gaussian Simulation (SGS), which is used to generate multiple non-unique realizations of geological phenomena that sample the uncertainty space. However, SGS is very CPU intensive with a computational complexity of O( <italic xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">Nk</i> <sup xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup> ), where <italic xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">N</i> is the number of grid cells to simulate, and <italic xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">k</i> is the number of neighboring points used for conditioning. This complexity makes SGS prohibitively time-consuming to implement at ice-sheet scales or fine resolutions. To reduce the time-cost, we implement and test a multiprocess version of SGS using Python’s multiprocessing module. By parallelizing the calculation of the weight parameters used in SGS, we achieve a speedup of 9.5 running on 16 processors for an <italic xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">N</i> of 128,097. This speedup, as well as the speedup from using multiple processors, increases with <italic xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">N</i> . This speed improvement makes SGS viable for large-scale topography mapping and ensemble ice-sheet modeling. Additionally, we have made our code repository and user tutorials publicly available (GitHub, Zenodo that others can use our multiprocess implementation of SGS on different datasets.","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135516489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3324155
{"title":"Over the Rainbow: 21st Century Security & Privacy Podcast","authors":"","doi":"10.1109/mcse.2023.3324155","DOIUrl":"https://doi.org/10.1109/mcse.2023.3324155","url":null,"abstract":"","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1109/mcse.2023.3315661
Yuxiang Gao, Gourab Ghosh, Stephen Jiménez, Ravindra Duddu
{"title":"A finite-element-based cohesive zone model of water-filled surface crevasse propagation in floating ice tongues","authors":"Yuxiang Gao, Gourab Ghosh, Stephen Jiménez, Ravindra Duddu","doi":"10.1109/mcse.2023.3315661","DOIUrl":"https://doi.org/10.1109/mcse.2023.3315661","url":null,"abstract":"","PeriodicalId":10553,"journal":{"name":"Computing in Science & Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135563362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：