2 results
Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Development of neural network-based surrogate models in geotechnics: a state-of- the-art reviewPurpose -This state-of-the-art paper provides an overview of surrogate modelling methods suitable for geotechnical engineering, covering the entire cycle of model development. Design/methodology/approach -The paper discusses neural network-based surrogate modelling and its applicability in geotechnical engineering, including its limitations. It addresses techniques for data set generation, sampling, tuning, selecting activation functions and assessing accuracy Findings - Each step during the development of surrogate models offers various options and therefore requires a systematic approach. Besides standardised benchmarking and richer data sets key areas for future research include advanced or hybrid architectures, such as physics-informed long short-term memory networks and transformers to improve generalisability, efficiency and physical consistency.</jats:p> Originality/value -This paper reviews and highlights the most promising methods for surrogate model development in geotechnical engineering, considering the most critical aspects for building high-performing predictive models and lays an outlook for future research.Publicationtype: Journal Article7 3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Predicting soil stress–strain behaviour with bidirectional long short-term memory networksPurpose Artificial intelligence, particularly deep learning (DL), has increasingly influenced various scientific fields, including soil mechanics. This paper aims to present a novel DL application of long short-term memory (LSTM) networks for predicting soil behaviour during constant rate of strain (CRS) tests. Design/methodology/approach LSTMs are adept at capturing long-term dependencies in sequential data, making them suitable for predicting the complex, nonlinear stress–strain behaviour of soil. This paper evaluates various LSTM configurations, optimising parameters such as step size, batch size, data sampling rate and training subset size to balance prediction accuracy and computational efficiency. The study uses a comprehensive data set from numerical finite element method simulations conducted with PLAXIS 2D and laboratory CRS tests. Findings The proposed LSTM model, trained on data at lower stress levels, accurately forecasts soil behaviour at higher stress levels. The optimal LSTM setup achieved a median error of 3.59% and 5.10% for numerical data and 3.86% for laboratory data, presenting the setup’s effectiveness. Originality/value This approach reduces the required time to complete extensive laboratory testing, aligning with sustainable industrial practices. The findings suggest that LSTM networks can enhance geotechnical engineering applications by efficiently predicting soil behaviour.Publicationtype: Journal Article8 12