Comput. Geosci.最新文献

Probabilistic volcanic mass flow hazard assessment using statistical surrogates of deterministic simulations 用确定性模拟的统计替代方法进行概率火山块状流危险性评估

Comput. Geosci. Pub Date : 2022-02-18 DOI: 10.1002/essoar.10510568.1

S. Mead, J. Procter, M. Bebbington

引用次数: 1

Decomposition and Inference of Sources through Spatiotemporal Analysis of Network Signals: The DISSTANS Python package 通过网络信号的时空分析进行源的分解和推断:DISSTANS Python包

Comput. Geosci. Pub Date : 2021-12-08 DOI: 10.1002/essoar.10509232.1

Tobias Köhne, B. Riel, M. Simons

{"title":"Decomposition and Inference of Sources through Spatiotemporal Analysis of Network Signals: The DISSTANS Python package","authors":"Tobias Köhne, B. Riel, M. Simons","doi":"10.1002/essoar.10509232.1","DOIUrl":"https://doi.org/10.1002/essoar.10509232.1","url":null,"abstract":"Dense, regional-scale, continuously-operating Global Navigation Satellite System (GNSS) networks are powerful tools to monitor plate motion and surface deformation. The spatial extent and density of these networks, as well as the length of observation records, have steadily increased in the past three decades.Software to enable the efficient analysis (especially the decomposition) of the ever-increasing amount of available timeseries should have the following desirable qualities: geographic portability, computational speed, automation (minimizing the need for manual inspection of each station), use of spatial correlation (exploiting the fact that stations experience common signals), source code availability, and documentation.We introduce the DISSTANS Python package, which aims to be generic (therefore portable), parallelizable (fast), and able to exploit the spatial structure of the observation records in a user-assisted, semi-automated framework, including uncertainty propagation.The code is open-source, includes an application interface documentation as well as usage tutorials, and is easily extendable.We present two case studies that demonstrate our code, one using a synthetic dataset and one using real GNSS network timeseries.","PeriodicalId":10649,"journal":{"name":"Comput. Geosci.","volume":"43 1","pages":"105247"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78012307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Qmin - A machine learning-based application for processing and analysis of mineral chemistry data Qmin -基于机器学习的应用程序，用于处理和分析矿物化学数据

Comput. Geosci. Pub Date : 2021-12-01 DOI: 10.1016/j.cageo.2021.104949

Guilherme Ferreira da Silva, Marcos Vinicius Ferreira, I. Costa, Renato Borges Bernardes, C. Mota, Federico Alberto Cuadros Jiménez

引用次数: 6

Coupled physics-deep learning inversion 耦合物理-深度学习反演

Comput. Geosci. Pub Date : 2021-12-01 DOI: 10.1016/J.CAGEO.2021.104917

D. Colombo, E. Turkoglu, Weichang Li, D. Rovetta

引用次数: 10

Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties 具有非均质材料性质的孔隙弹性数据驱动解的连续条件生成对抗网络

Comput. Geosci. Pub Date : 2021-11-29 DOI: 10.1016/j.cageo.2022.105212

T. Kadeethum, D. O’Malley, Y. Choi, H. Viswanathan, N. Bouklas, H. Yoon

引用次数: 11

WlCount: Geological lamination detection and counting using an image analysis approach 地质分层检测和计数使用图像分析方法

Comput. Geosci. Pub Date : 2021-11-09 DOI: 10.31223/x5ks6w

F. Oriani, P. Treble, A. Baker, G. Mariéthoz

引用次数: 17

Superpixel segmentations for thin sections: Evaluation of methods to enable the generation of machine learning training data sets 薄片的超像素分割:评估生成机器学习训练数据集的方法

Comput. Geosci. Pub Date : 2021-10-16 DOI: 10.31223/x55s65

Jiaxin Yu, F. Wellmann, S. Virgo, Marven von Domarus, M. Jiang, J. Schmatz, B. Leibe

{"title":"Superpixel segmentations for thin sections: Evaluation of methods to enable the generation of machine learning training data sets","authors":"Jiaxin Yu, F. Wellmann, S. Virgo, Marven von Domarus, M. Jiang, J. Schmatz, B. Leibe","doi":"10.31223/x55s65","DOIUrl":"https://doi.org/10.31223/x55s65","url":null,"abstract":"Training data is the backbone of developing either Machine Learning (ML) models or specific deep learning algorithms. The paucity of well-labeled training image data has significantly impeded the applications of ML-based approaches, especially the development of novel Deep Learning (DL) methods like Convolutional Neural Networks (CNNs) in mineral thin section images identification. However, image annotation, especially pixel-wise annotation is always a costly process. Manually creating dense semantic labels for rock thin section images has been long considered as an unprecedented challenge in view of the ubiquitous variety and complexity of minerals in thin sections. To speed up the annotation, we propose a human-computer collaborative pipeline in which superpixel segmentation is used as a boundary extractor to avoid hand delineation of instances boundaries. The pipeline consists of two steps: superpixel segmentation using MultiSLIC, and superpixel labeling through a specific-designed tool. We use a cutting-edge methodology Virtual Petroscopy (ViP) for automatic image acquisition. Bentheimer sandstone sample is used to conduct performance testing of the pipeline. Three standard error metrics are used to evaluate the performance of MultiSLIC. The result indicates that MultiSLIC is able to extract compact superpixels with satisfying boundary adherence given multiple input images. According to our test results, large and complex thin section images with pixel-wisely accurate labels can be annotated with the labeling tool more efficiently than in a conventional, purely manual work, and generate data of high quality.","PeriodicalId":10649,"journal":{"name":"Comput. Geosci.","volume":"26 1","pages":"105232"},"PeriodicalIF":0.0,"publicationDate":"2021-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78204026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Integrating scientific knowledge into machine learning using interactive decision trees 利用交互式决策树将科学知识整合到机器学习中

Comput. Geosci. Pub Date : 2021-07-24 DOI: 10.31223/x5pp75

Thorsten Wagener, F. Pianosi

引用次数: 7

Comput. Geosci. Pub Date : 2021-06-24 DOI: 10.21203/rs.3.rs-614652/v1

P. Bajracharya, Shaleen Jain

{"title":"Hydrologic similarity based on width function and hypsometry: An unsupervised learning approach","authors":"P. Bajracharya, Shaleen Jain","doi":"10.21203/rs.3.rs-614652/v1","DOIUrl":"https://doi.org/10.21203/rs.3.rs-614652/v1","url":null,"abstract":"\u0000 In ungauged or data-scarce watersheds, systematic analyses of a set of proximate watersheds (for example, selected based on locational proximity or similarity in climate, morphometry, lithology, soils, and vegetation) have been shown to lend significant insights regarding hydrologic response and prediction. Current approaches often rely on: (a) statistical regression models that use measurable watershed attributes, such as area, slope, and stream length; and (b) comparative hydrology that considers watershed characteristics to assess hydrologic similarity to select analogous gauged watersheds as proxies. Newer conceptions regarding hydrologic similarity focus on hydrologic response and therefore emphasize the use of dynamical measures of the stream network and watershed terrain. For example, the width function and hypsometric curve can be readily estimated using the available global digital terrain datasets and represented as functional forms involving a small set of parameters, thus achieving significant data reduction. In this study, a new approach to hydrological similarity in watersheds, one that utilizes these functional forms to identify dynamically similar watersheds, is presented. Dissimilarity matrices are created based on divergence measures, and watersheds are classified using hierarchical clustering. The joint analysis of watershed width functions and hypsometric curves allows for the classification of watersheds into a reduced number of dynamically-similar groups. An illustrative case study for the Narmada River, with 72 sub-watersheds, is presented.","PeriodicalId":10649,"journal":{"name":"Comput. Geosci.","volume":"14 1","pages":"105097"},"PeriodicalIF":0.0,"publicationDate":"2021-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72994802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Testing scenarios on geological models: Local interface insertion in a 2D mesh and its impact on seismic wave simulation 地质模型测试场景:二维网格局部界面插入及其对地震波模拟的影响

Comput. Geosci. Pub Date : 2021-06-08 DOI: 10.23967/admos.2021.077

Capucine Legentil, J. Pellerin, P. Cupillard, A. Froehly, G. Caumon

引用次数: 2