GeoMix: A Bayesian Framework for Stratigraphic and Geotechnical Inference
Abstract
Accurate characterisation of subsea sediments is essential for engineering projects such as offshore wind farms, but the challenging environment and large spatial domains involved make dense geotechnical measurements impractical. Seismic traces offer a cheap, abundant complement, yet their geotechnical interpretation relies on subjective judgement, leading to biased, hard-to-validate predictions of sediment structure. To address this, we introduce GeoMix, a fully Bayesian hierarchical framework for jointly inferring geological stratigraphy and geotechnical properties from seismic and geotechnical data. GeoMix uses a Potts Markov random field to represent spatially coherent geology organised into distinct stratigraphic layers. Labels derived from seismic interpretation are linked to the latent stratigraphy through an observation model that captures elevated uncertainty near transitions between strata. Conditional on the latent stratigraphy, geotechnical properties are modelled using class-specific Gaussian processes, with scalable likelihood evaluation enabled by a grouped Vecchia approximation. Together, these components yield a unified latent-variable model capable of recovering stratigraphy, quantifying uncertainty, and predicting geotechnical properties across large three-dimensional domains. Simulation studies and an application to the IJmuiden Ver offshore wind farm show that GeoMix produces spatially coherent stratigraphic estimates and sediment predictions that are better calibrated and more accurate than existing approaches.
Related
- A Projection-Based Approach to Bayesian Age Estimation under Stratigraphic Constraints.
- Efficient Bayesian inference for multiple network data
- Bayesian inference under model misspecification
- Modern Bayesian Modeling and Inference
- Kumaraswamy-Teissier Distribution: Bayesian and Non-Bayesian Inference, Regression Modeling and Climate Application
BibTeX
@misc{wakefield2026geomix,
title = {{GeoMix: A Bayesian Framework for Stratigraphic and Geotechnical Inference}},
author = {Bradley Wakefield and Michael Bertolacci and David Gunawan and Fraser Bransby and Phil Watson and Andrew Zammit-Mangion},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21021},
eprint = {2610.21021},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21021},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - GeoMix: A Bayesian Framework for Stratigraphic and Geotechnical Inference
AU - Bradley Wakefield
AU - Michael Bertolacci
AU - David Gunawan
AU - Fraser Bransby
AU - Phil Watson
AU - Andrew Zammit-Mangion
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.21021
UR - https://arxiv.org/abs/2610.21021
AB - Accurate characterisation of subsea sediments is essential for engineering projects such as offshore wind farms, but the challenging environment and large spatial domains involved make dense geotechnical measurements impractical. Seismic traces offer a cheap, abundant complement, yet their geotechnical interpretation relies on subjective judgement, leading to biased, hard-to-validate predictions of sediment structure. To address this, we introduce GeoMix, a fully Bayesian hierarchical framework for jointly inferring geological stratigraphy and geotechnical properties from seismic and geotechnical data. GeoMix uses a Potts Markov random field to represent spatially coherent geology organised into distinct stratigraphic layers. Labels derived from seismic interpretation are linked to the latent stratigraphy through an observation model that captures elevated uncertainty near transitions between strata. Conditional on the latent stratigraphy, geotechnical properties are modelled using class-specific Gaussian processes, with scalable likelihood evaluation enabled by a grouped Vecchia approximation. Together, these components yield a unified latent-variable model capable of recovering stratigraphy, quantifying uncertainty, and predicting geotechnical properties across large three-dimensional domains. Simulation studies and an application to the IJmuiden Ver offshore wind farm show that GeoMix produces spatially coherent stratigraphic estimates and sediment predictions that are better calibrated and more accurate than existing approaches.
ER -