Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression

Generally, soil properties are measured only at limited locations. To rationally estimate the spatial distribution of soil properties, it is preferable to effectively use all available measurement data, including indirect data. We propose a Gaussian process regression with multiple random fields tha...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuto Tsuda, Ikumasa Yoshida, Shinichi Nishimura
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Soils and Foundations
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0038080625000587
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849701764936237056
author Yuto Tsuda
Ikumasa Yoshida
Shinichi Nishimura
author_facet Yuto Tsuda
Ikumasa Yoshida
Shinichi Nishimura
author_sort Yuto Tsuda
collection DOAJ
description Generally, soil properties are measured only at limited locations. To rationally estimate the spatial distribution of soil properties, it is preferable to effectively use all available measurement data, including indirect data. We propose a Gaussian process regression with multiple random fields that considers the cross-correlation between one of the random fields of direct data and indirect data, and show the application to simulated data and actual measured data. In the application, the direct data are of CPT tip resistance (qc), which was obtained within a narrow area, and the indirect data are of shear wave velocity (Vs) obtained by surface wave exploration, which were obtained over a wide area. We estimate the spatial distribution of qc from the limited qc and wide area Vs data. The estimation accuracy of the proposed method is evaluated by cross-validation, and its effectiveness is discussed.
format Article
id doaj-art-4d7f57ec82bc42e8ba5cfecab9999e4e
institution DOAJ
issn 2524-1788
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Soils and Foundations
spelling doaj-art-4d7f57ec82bc42e8ba5cfecab9999e4e2025-08-20T03:17:52ZengElsevierSoils and Foundations2524-17882025-06-0165310162410.1016/j.sandf.2025.101624Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regressionYuto Tsuda0Ikumasa Yoshida1Shinichi Nishimura2Postdoctoral Researcher, School of Integrative Science and Engineering, Tokyo City University, Tokyo 158-8557, Japan; Corresponding author.Professor Emeritus, Department of Urban and Civil Engineering, Tokyo City University, Tokyo 158-8557, JapanDepartment of Civil Environmental Engineering, Okayama University, Okayama 700-8530, JapanGenerally, soil properties are measured only at limited locations. To rationally estimate the spatial distribution of soil properties, it is preferable to effectively use all available measurement data, including indirect data. We propose a Gaussian process regression with multiple random fields that considers the cross-correlation between one of the random fields of direct data and indirect data, and show the application to simulated data and actual measured data. In the application, the direct data are of CPT tip resistance (qc), which was obtained within a narrow area, and the indirect data are of shear wave velocity (Vs) obtained by surface wave exploration, which were obtained over a wide area. We estimate the spatial distribution of qc from the limited qc and wide area Vs data. The estimation accuracy of the proposed method is evaluated by cross-validation, and its effectiveness is discussed.http://www.sciencedirect.com/science/article/pii/S0038080625000587Shear wave velocityGaussian process regressionRandom fieldCPT tip resistanceIndirect data
spellingShingle Yuto Tsuda
Ikumasa Yoshida
Shinichi Nishimura
Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
Soils and Foundations
Shear wave velocity
Gaussian process regression
Random field
CPT tip resistance
Indirect data
title Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
title_full Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
title_fullStr Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
title_full_unstemmed Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
title_short Spatial distribution estimation by considering the cross-correlation between components with indirect data using Gaussian process regression
title_sort spatial distribution estimation by considering the cross correlation between components with indirect data using gaussian process regression
topic Shear wave velocity
Gaussian process regression
Random field
CPT tip resistance
Indirect data
url http://www.sciencedirect.com/science/article/pii/S0038080625000587
work_keys_str_mv AT yutotsuda spatialdistributionestimationbyconsideringthecrosscorrelationbetweencomponentswithindirectdatausinggaussianprocessregression
AT ikumasayoshida spatialdistributionestimationbyconsideringthecrosscorrelationbetweencomponentswithindirectdatausinggaussianprocessregression
AT shinichinishimura spatialdistributionestimationbyconsideringthecrosscorrelationbetweencomponentswithindirectdatausinggaussianprocessregression