cs.LGNov 11, 2026

Subsurface schematisation from sparse CPT data using the tabular foundation model TabPFN

Authors: Taiga Saito, Fabian Campos Montero, Bruno Zuada Coelho, Ana Martins Teixeira, Stephen Wu, Timo Schweckendiek, Yu Otake

Organizations: Department of Civil and Environmental Engineering, Tohoku University, Sendai, Japan · Safe and Resilient Infrastructure, Deltares, Delft, the Netherlands · Research Organization of Information and Systems, The Institute of Statistical Mathematics, Tachikawa, Japan · The Graduate University for Advanced Studies, Department of Statistical Science, Tachikawa, Japan

Abstract

Subsurface schematisation supports geotechnical decisions but remains challenging because sparse site-investigation data leave substantial gaps in information about ground conditions. This study explores TabPFN, a foundation model pretrained on general synthetic tabular data, for this task. Using only grid coordinates and soil behaviour type index observations from sparse cone penetration tests (CPTs), we first reconstruct two-dimensional sections without geotechnical fine-tuning or predefined layer boundaries. We evaluate the approach on synthetic sections and at two field sites in the Netherlands, comparing it with SchemaGAN, a conditional generative adversarial network trained on synthetic geotechnical sections, and with reference interpolation methods. In the baseline comparisons, TabPFN achieved mean errors close to SchemaGAN's on synthetic sections and lower mean errors at both field sites. On synthetic sections, TabPFN's mean absolute error decreased at each tested increase in CPT count, and, under the baseline input setting, its pointwise prediction intervals had mean coverage close to nominal levels. Subsequent fine-tuning on the synthetic sections used to train SchemaGAN improved synthetic test accuracy but increased mean errors at both field sites. These findings indicate that general-purpose tabular foundation models offer a promising route for updating subsurface predictions from sparse and evolving site-investigation data without retraining.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TabPFN Extensions for Interpretable Geotechnical Modelling

    Mar 22, 2026Taiga Saito, Yu Otake, Daijiro Mizutani +1Uncertainty QuantificationTabular Foundation Models

  2. On the Uncertainty Quantification Ability of Tabular Foundation Models

    May 31, 2026Tyler R. Johnson, Kian Ben-Jacob, Nima Negarandeh +2Tabular Foundation ModelsUncertainty Quantification

  3. TabPFN-3: Technical Report

    May 13, 2026Léo Grinsztajn, Klemens Flöge, Oscar Key +38Tabular Foundation ModelsEfficient Neural Network Inference