Subsurface schematisations are a crucial geotechnical problem which generally consists of filling substantial gaps in subsurface information from the limited site investigation data available and relying heavily on the engineer’s experience and occasionally geostatistical tools. To address this, schemaGAN, a conditional Generative Adversarial Network (GAN) to generate geotechnical subsurface schematisations from site investigation data is introduced. This novel method can learn complex underlying rules that govern the subsurface geometries and anisotropy from a big database of training cross-sections, and can produce subsurface schematisations from Cone Penetration Tests (CPT) in an insignificant timeframe. To test and demonstrate the performance of schemaGAN, a database of 24,000 synthetic geotechnical cross-sections with their corresponding CPT data was created, including spatial variability and gradually spatially varying layers. After training, the effectiveness of schemaGAN was compared against several interpolation methods, and it is seen that schemaGAN outperforms all other methods, with results characterised by clear layer boundaries and an accurate representation of anisotropy within the layers. SchemaGAN’s superior performance was confirmed through a blind survey, and in two real case studies in the Netherlands, where the model demonstrates better predictive accuracy for known CPT data.

Bayesian inference poses as a means for characterizing the uncertainty in geotechnical parameters based on limited site investigation data. In this study, a Hierarchical Bayesian analysis framework is used to analyse a site investigation database in order to derive geotechnical soil parameters for two widely applied strength models. The first one focuses on calibrating the relationship between in-situ CPT measurements and undrained shear strength. The second one is the SHANSEP soil strength model, which is used forevaluating the undrained shear strength using OCR information. The framework operates in a hierarchical fashion, performing inference on separate project sites and at the same time drawing conclusions on a global level. The result is site characterization on a probabilistic level and the derivation of geotechnical parameters together with their probability distributions. The results are assessed by evaluating their influence in the failure probability of a geotechnical structure, demonstrating that the proposed hierarchical approach provides a more complete description of uncertainty than standard practice methods.