Benchmarks of AI in Geotechnics and Tunnelling

A special issue of Geosciences (ISSN 2076-3263). This special issue belongs to the section "Geomechanics".

Deadline for manuscript submissions: closed (31 October 2023) | Viewed by 5959

Special Issue Editors

Institute of Soil Mechanics, Foundation Engineering and Computational Geotechnics, Graz University of Technology, 12, Rechbauerstraße, 8020 Graz, Austria
Interests: computational geotechnics; slope stability analysis; constitutive modelling; pa-rameter determination; application of machine learning in geotechnics; building information modelling
Norwegian Geotechnical Institute - NGI, Sandakerveien 140, 0484 Oslo, Norway
Interests: engineering geology; tunnelling; quantitaive ground characterization; rock and soil mechanics; machine learning; building information modelling
Institute of Rock Mechanics and Tunnelling, Graz University of Technology, 12, Rechbauerstraße, 8020 Graz, Austria
Interests: soil and rock tunnel design including large cross sections and caverns with low overburden but also deep tunnels and shafts; rock mechanics (hard rock, soft rock and hard soils); rock stability analysis; constitutive modelling within rock mechanics; application of machine learning in tunnelling

Special Issue Information

Dear Colleagues,

Driven by a global trend for digitalization, we have seen an explosion of contributions on artificial intelligence (AI) technologies for geotechnics and engineering geology in the past years. In 2018 we – the editors – founded a working group on “Machine Learning in Geotechnics” at the Graz University of Technology, which continues to closely collaborate with the Norwegian Geotechnical Institute up to the present day. While the developments of AI in geotechnics are in line with global trends, we also see deficits that hinder the general advancement of AI technology in our field. An overwhelming number of contributions can be attributed to the field of supervised machine learning, where algorithms learn input-output relationships based on predefined examples though other fields of AI are underrepresented. Furthermore, there is a significant number of studies that are partly or fully irreproducible due to lacking source code and original data.

With this Special Issue, we wish to provide a platform for high-quality contributions from all fields of AI, including but not limited to supervised machine learning (ML), unsupervised ML, self-supervised ML, reinforcement learning, evolutionary computation, and swarm intelligence. The applied geoscientific context of the contributions is set to be very wide, ranging from fields of geotechnics such as slope stability, constitutive modelling, or tunnelling to all applications of engineering geology such as ground investigations, mapping, or geological modelling.

A requirement of contributions is that the associated source code as well as the original training data or representative substitute data are provided such that the presented approaches are reproducible to the highest possible degree.

By gathering the best contributions of AI for geotechnics and engineering geology, this Special Issue will serve as a benchmark for many future developments in this field and further push the state of the art.

Dr. Franz Tschuchnigg
Dr. Georg H. Erharter
Dr. Thomas Marcher
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Geosciences is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • geotechnics
  • tunnelling
  • engineering geology
  • reproducibility
  • benchmarks

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

23 pages, 22700 KiB  
Article
Influence of Sampling Methods on the Accuracy of Machine Learning Predictions Used for Strain-Dependent Slope Stability
by Sudan Shakya, Christoph Schmüdderich, Jan Machaček, Luis Felipe Prada-Sarmiento and Torsten Wichtmann
Geosciences 2024, 14(2), 44; https://doi.org/10.3390/geosciences14020044 - 05 Feb 2024
Viewed by 992
Abstract
Supervised machine learning (ML) techniques have been widely used in various geotechnical applications. While much attention is given to the ML techniques and the specific geotechnical problem being addressed, the influence of sampling methods on ML performance has received relatively less scrutiny. This [...] Read more.
Supervised machine learning (ML) techniques have been widely used in various geotechnical applications. While much attention is given to the ML techniques and the specific geotechnical problem being addressed, the influence of sampling methods on ML performance has received relatively less scrutiny. This study applies supervised ML to the strain-dependent slope stability (SDSS) method for the prediction of the factor of safety (FoS) using hypoplasticity. It delves into different sampling strategies for training the ML model, emphasizing predictions of soil behavior in lower stress ranges. A novel sampling method is introduced to ensure a more representative distribution of samples in these ranges, which is challenging to achieve through traditional sampling approaches. The ML models were trained using traditional and modified sampling methods. Subsequently, slope stability analyses using SDSS were conducted with ML models trained from six different sampling methods. The results illustrate the impact of sampling methods on the FoS. Besides a noticeable improvement in predictions of shear stresses within the lower stress ranges, a decisive effect on the overall FoS was observed as well. Full article
(This article belongs to the Special Issue Benchmarks of AI in Geotechnics and Tunnelling)
Show Figures

Figure 1

21 pages, 7022 KiB  
Article
Dynamic Prediction of Longitudinal Settlement of Existing Tunnel Using ConvRes-DLinear Model with Integration of Undercrossing Construction Process Information
by Cong Nie, Dongming Zhang, Linghan Ouyang, Xu Huang, Bo Zhang and Yue Tong
Geosciences 2023, 13(7), 189; https://doi.org/10.3390/geosciences13070189 - 22 Jun 2023
Cited by 1 | Viewed by 1112
Abstract
Undercrossing construction can cause severe structural deformation of the above existing tunnel in operation. The induced longitudinal differential settlement between the segments can pose a huge risk to running subways, hence it is of great importance to monitor and predict the settlement. Within [...] Read more.
Undercrossing construction can cause severe structural deformation of the above existing tunnel in operation. The induced longitudinal differential settlement between the segments can pose a huge risk to running subways, hence it is of great importance to monitor and predict the settlement. Within this study, a Wireless Sensor Network (WSN) system was implemented to obtain hourly monitoring data of settlement from the very beginning of undercrossing to post construction period. An improved direct multi-step (DMS) forecasting model called ConvRes-DLinear is proposed, which fuses monitoring data with time and process encoding bias to deeply extract and learn temporal correlation of time series. A residual LSTM model is also constructed to compare the accuracy of the improved DLinear model. The training and testing experiment on the monitoring data of longitudinal settlement obtained by WSN system shows that the ConvRes-DLinear model with time and process encoding bias performs surprisingly well with a minimum prediction error. The features of the proposed model are discussed to make the results explainable. The monitoring system and time series forecasting model proposed in this study have a guiding significance for the monitoring and prediction of longitudinal differential settlement of tunnels under environmental disturbance. Full article
(This article belongs to the Special Issue Benchmarks of AI in Geotechnics and Tunnelling)
Show Figures

Figure 1

23 pages, 2340 KiB  
Article
Reinforcement Learning for the Face Support Pressure of Tunnel Boring Machines
by Enrico Soranzo, Carlotta Guardiani and Wei Wu
Geosciences 2023, 13(3), 82; https://doi.org/10.3390/geosciences13030082 - 13 Mar 2023
Cited by 3 | Viewed by 2255
Abstract
In tunnel excavation with boring machines, the tunnel face is supported to avoid collapse and minimise settlement. This article proposes the use of reinforcement learning, specifically the deep Q-network algorithm, to predict the face support pressure. The algorithm uses a neural network to [...] Read more.
In tunnel excavation with boring machines, the tunnel face is supported to avoid collapse and minimise settlement. This article proposes the use of reinforcement learning, specifically the deep Q-network algorithm, to predict the face support pressure. The algorithm uses a neural network to make decisions based on the expected rewards of each action. The approach is tested both analytically and numerically. By using the soil properties ahead of the tunnel face and the overburden depth as the input, the algorithm is capable of predicting the optimal tunnel face support pressure whilst minimising settlement, and adapting to changes in geological and geometrical conditions. The algorithm reaches maximum performance after 400 training episodes and can be used for random geological settings without retraining. Full article
(This article belongs to the Special Issue Benchmarks of AI in Geotechnics and Tunnelling)
Show Figures

Figure 1

Back to TopTop