Bridge predicts mechanical properties from routine soil tests in geotechnical engineering
BRIDGE: Bridging Routine Inputs and Digital modelling for Geotechnical Engineering
Computational Engineering, Finance, and Science
Summary
Mechanical properties for soil design need special lab tests, which are expensive and rare compared to common basic soil measurements. The authors created BRIDGE, a method that groups soil samples by their basic tests and then predicts detailed mechanical behaviors for all samples using only a few lab-tested examples per group. This approach ensures predictions follow physical laws and can be trusted within those groups. They tested it on a large soil database from Tokyo clay and showed it works with only 10-20% of samples needing detailed lab tests.
What this means in practice
- •For geotechnical engineers: Predict soil mechanical parameters reliably from routine test data, reducing reliance on expensive lab testing for preliminary design.
- •For civil engineering software developers: Incorporate calibrated mechanical surrogates in software to automate soil property predictions within validated soil groups.
Tested on one dataset.
Authors
Roshan Philip Saji, Waleed El-Sekelly, Tarek Abdoun, Mostafa E. Mobasher
Abstract
The mechanical properties needed for geotechnical design require laboratory tests and are thus available for far fewer field samples than routinely measured basic (index) properties which are available for nearly every sample. We term this difference as the characterization gap. Purely data-driven models do not explicitly enforce physical laws and may be unreliable beyond their training domain, while direct constitutive calibration preserves physical consistency but requires advanced laboratory data and expert judgment. We therefore propose BRIDGE (Bridging Routine Inputs and Digital modelling for Geotechnical Engineering) a modular framework that predicts mechanical properties from routinely available basic properties. BRIDGE screens the dataset for outliers and non-physical responses, bins the retained samples into Cells, and selects a small calibration dataset from each Cell, while the remaining samples are used for validation. A mechanical model is then calibrated for each calibration sample, and the converged calibrations collectively define the mechanical surrogate of the Cell together with its parameter ranges and the corresponding predictive envelope in the mechanical property space. A Cell is validated when most validation samples fall within this envelope, whereupon the surrogate can predict the mechanical property ranges of new samples whose basic properties lie within the Cell. In this work, we adopt a finite element implementation of the Extended Cam-Clay (ECC) constitutive model as the mechanical model, whose four parameters are calibrated in a multi-stage process. Applied to the Tokyo-CLAY/14/67760 database, BRIDGE predicts the mechanical properties of an entire Cell from calibrations of just 10 to 20% of its samples. Finally, since the mechanical model, the binning criteria, and the sampling method are components of BRIDGE, the framework is easily extensible.