What does this research mean for the field?

Feed-forward neural networks can accurately predict complex cohesive soil material parameters from basic physical properties using small, site-specific datasets, serving as a viable proof-of-concept computational framework. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.SUPPORTS_CONSENSUS.

What question did this study set out to answer?

The aim is to predict cohesive soil material parameters using machine learning techniques to improve efficiency in civil engineering.

May 31, 2026Open Access

A Prediction of Cohesive Soil Material Parameters, Situated in Heraklion, Crete-Greece, with the Implementation of Machine Learning Methods

ASAmbrosios-Antonios SavvidesNational Technical University of Athens AAAndreas AntoniouNational Technical University of Athens

Key Points

The aim is to predict cohesive soil material parameters using machine learning techniques to improve efficiency in civil engineering.
Applied feed-forward neural networks on small datasets of in situ soil data from Heraklion, Crete.
Input parameters included void ratio, soil moisture percentage, and specific weight of the soil skeleton.
Performed hyperparameter estimation and monitored model convergence with a focus on achieving low error rates.
Model predictions showed RRMSE below 10^-7 for elasticity and strength parameters except for unconfined compressive strength (RRMSE below 10^-2).
Output variable behavior indicated non-monotonic trends with up to 150% deviation based on variable input ratios.
Validation of model predictions demonstrated consistency with literature values for cohesive soils of medium stiffness.

Abstract

Abstract The mechanical characterization of soils and the prediction of their material parameters through experimental procedures are important aspects of civil engineering. Nonetheless, these procedures can be costly and difficult to perform, whereas the neural network framework offers a computational tool for predicting material parameters from small datasets. In this paper, predictions of elasticity parameters such as Young’s modulus, shear strength parameters including the friction angle and cohesion, and hydraulic flow parameters such as the consolidation coefficient Cₕ C v are made using feed-forward neural networks trained on in situ data collected in Heraklion, Crete, Greece. The input parameters include the void ratio e, percentage of the humidity of the soil w, and the specific weight of the soil skeleton ₒ γ s. The analysis of model hyperparameter estimation and convergence during the supervised learning process indicates that approximately 10 epochs are sufficient, with the relative root mean square error (RRMSE) remaining below 10^-7 10 - 7 for all models except the one predicting unconfined compressive strength, where the RRMSE is below 10^-2 10 - 2. Furthermore, the results indicate that when ₒ γ s increases, the behavior of most output variables is not strictly monotonic, with subsets of both increasing and decreasing trends. The maximum deviation observed may reach approximately 150%, based on the ratio of maximum to minimum predicted values. Within the context of the available site-specific dataset, the proposed models demonstrate interpretability and consistent predictive performance, while remaining adaptable to future data updates. However, they remain limited to the specific site under study, and generalization to broader areas would require larger datasets, including additional experimentally obtained samples beyond the synthetically augmented dataset of the present study. The proposed model, due to the limited dataset size, should be regarded as a practical proof-of-concept framework rather than a fully generalizable computational tool. Finally, the model predictions were validated through comparison with values reported in the literature for cohesive soils of medium stiffness and strength.

Ask AI

Helpful

Bookmark

View Full Paper