Teodosio, Bertrand ORCID: 0000-0002-3909-4054, Wasantha, PLP, Yaghoubi, Ehsan ORCID: 0000-0003-0639-0225, Guerrieri, Maurice ORCID: 0000-0001-7916-7003, an Staden, RC and Fragomeni, Salvatore ORCID: 0000-0002-0733-4770 (2022) Shrink–swell index prediction through deep learning. Neural Computing and Applications, 35. pp. 4569-4586. ISSN 0941-0643

Abstract

Growing application of artificial intelligence in geotechnical engineering has been observed; however, its ability to predict the properties and nonlinear behaviour of reactive soil is currently not well considered. Although previous studies provided linear correlations between shrink–swell index and Atterberg limits, obtained model accuracy values were found unsatisfactory results. Artificial intelligence, specifically deep learning, has the potential to give improved accuracy. This research employed deep learning to predict more accurate values of shrink–swell indices, which explored two scenarios; Scenario 1 used the features liquid limit, plastic limit, plasticity index, and linear shrinkage, whilst Scenario 2 added the input feature, fines percentage passing through a 0.075-mm sieve (%fines). Findings indicated that the implementation of deep learning neural networks resulted in increased model measurement accuracy in Scenarios 1 and 2. The values of accuracy measured in this study were suggestively higher and have wider variance than most previous studies. Global sensitivity analyses were also conducted to investigate the influence of each input feature. These sensitivity analyses resulted in a range of predicted values within the variance of data in Scenario 2, with the %fines having the highest contribution to the variance of the shrink–swell index and a relevant interaction between linear shrinkage and %fines. The proposed model Scenario 2 was around 10–65% more accurate than the preceding models considered in this study, which can then be used to expeditiously estimate more accurate values of shrink–swell indices.

Search Google Scholar

Repository staff login