Skip to main navigation Skip to search Skip to main content

2D Site Characterization by Mixture of Gaussian Processes

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

Gaussian process regression is an effective method for the stochastic interpolation of geotechnical site data. However, a significant drawback of this method is its stationarity assumption, which is unrealistic given the existence of different soil layers. This assumption results in higher uncertainty in interpolation and poorer performance. To address this limitation, a mixture of Gaussian processes model is investigated for simultaneous layer identification and spatial interpolation in 2D. The model is based on the probabilistic assessment of layer boundaries and Gaussian processes for defining the statistical properties of the layers as well as spatial interpolation. The accuracy of the model is tested with real CPT profiles. The performance of the model is evaluated based on interpolation accuracy.
Original languageEnglish
Title of host publicationProceedings of the 9th International Symposium for Geotechnical Safety and Risk (ISGSR)
EditorsZhongqiang Liu, Jian Dai, Kate Robinson
Place of PublicationSingapore
PublisherResearch Publishing
Pages136-139
Number of pages4
ISBN (Electronic)978-981-94-4075-7
DOIs
Publication statusPublished - 2025
Event9th International Symposium on Geotechnical Safety and Risk - Oslo, Norway
Duration: 25 Aug 202528 Aug 2025
https://www.isgsr2025.com/

Conference

Conference9th International Symposium on Geotechnical Safety and Risk
Abbreviated titleISGSR 2025
Country/TerritoryNorway
CityOslo
Period25/08/2528/08/25
Internet address

Keywords

  • CPT
  • Gaussian process
  • mixture of Gaussian processes
  • site characterization

Fingerprint

Dive into the research topics of '2D Site Characterization by Mixture of Gaussian Processes'. Together they form a unique fingerprint.

Cite this