article · Scientific Reports
Artificial neural networks integrated with swarm intelligence algorithms provide an effective approach to forecasting swell pressure and unconfined compressive strength in expansive soils. Four computational models combining neural networks with particle swarm optimisation, grey wolf optimisation, slime mould algorithm, and marine predators algorithm were developed. These systems utilised nine influential geotechnical parameters compiled from 145 published studies. Across the evaluations, the marine predators algorithm integration delivered the strongest overall performance, achieving the lowest mean absolute error rates of around five percent across training, testing, and validation data for swell pressure. Although the models experienced some overfitting when predicting unconfined compressive strength during testing, the majority of predictions across all models fell within a twenty percent error margin. Sensitivity and monotonicity analyses aligned with established geotechnical literature, demonstrating that metaheuristic optimisation addresses hyperparameter tuning challenges in soil mechanics modelling.
Expansive soils pose significant structural risks to infrastructure because they swell and shrink with moisture changes. Accurately assessing soil swell pressure and compressive strength typically demands time-consuming laboratory tests. Using optimised machine learning models allows geotechnical engineers to predict critical soil behaviours reliably from standard parameters, reducing testing burdens and aiding safer civil engineering design.
The models could support software tools for geotechnical consultants, site investigators, and civil engineering design teams assessing soil stability for construction projects. Because the models were developed and tested using datasets gathered from published literature rather than demonstrated on active construction sites, this computational approach is early-stage to applied research. Further practical validation is needed before integration into commercial engineering design workflows.
AI-generated from the published abstract. Always read the original work before citing.
This research suggests a robust integration of artificial neural networks (ANN) for predicting swell pressure and the unconfined compression strength of expansive soils (P<sub>s</sub>UCS-ES). Four novel ANN-based models, namely ANN-PSO (i.e., particle swarm optimization), ANN-GWO (i.e., grey wolf optimization), ANN-SMA (i.e., slime mould algorithm) alongside ANN-MPA (i.e., marine predators' algorithm) were deployed to assess the P<sub>s</sub>UCS-ES. The models were trained using the nine most influential parameters affecting P<sub>s</sub>UCS-ES, collected from a broader range of 145 published papers. The observed results were compared with the predictions made by the ANN-based metaheuristics models. The efficacy of all these formulated models was evaluated by utilizing mean absolute error (MAE), Nash-Sutcliffe (NS) efficiency, performance index ρ, regression coefficient (R<sup>2</sup>), root mean square error (RMSE), ratio of RMSE to standard deviation of actual observations (RSR), variance account for (VAF), Willmott's index of agreement (WI), and weighted mean absolute percentage error (WMAPE). All the developed models for P<sub>s</sub>-ES had an R significantly > 0.8 for the overall dataset. However, ANN-MPA excelled in yielding high R values for training dataset (TrD), testing dataset (TsD), and validation dataset (VdD). This model also exhibited the lowest MAE of 5.63%, 5.68%, and 5.48% for TrD, TsD, and VdD, respectively. The results of the UCS model's performance revealed that R exceeded 0.9 in the TrD. However, R decreased for TsD and VdD. Also, the ANN-MPA model yielded higher R values (0.89, 0.93, and 0.94) and comparatively low MAE values (5.11%, 5.67, and 3.61%) in the case of PSO, GWO, and SMA, respectively. The UCS models witnessed an overfitting problem because the aforementioned R values of the metaheuristics were 0.62, 0.56, and 0.58 (TsD), respectively. On the contrary, no significant observation was recorded in the VdD of UCS models. All the ANN-base models were also tested using the a-20 index. For all the formulated models, maximum points were recorded to lie within ± 20% error. The results of sensitivity as well as monotonicity analyses depicted trending results that corroborate the existing literature. Therefore, it can be inferred that the recently built swarm-based ANN models, particularly ANN-MPA, can solve the complexities of tuning the hyperparameters of the ANN-predicted P<sub>s</sub>UCS-ES that can be replicated in practical scenarios of geoenvironmental engineering.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1038/s41598-024-65547-7
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
