Surrogate Models in Rock and Soil Mechanics: Integrating Numerical Modeling and Machine Learning

Furtney, Jason; Thielsen, C.; Fu, Wei; Goc, Romain Le

doi:10.1007/s00603-021-02720-8

Cited by 17 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of coupling is often referred to as surrogate modeling. An excellent review of the concept of surrogate models is presented by [19]. Surrogate models allow for fast and rigorous data analysis and help provide insights that may otherwise remain unrecognized.…”

Section: Machine-learningmentioning

confidence: 99%

Investigation of Transfer Learning for Tunnel Support Design

Mitelman

Urlainis

2023

Mathematics

View full text Add to dashboard Cite

The potential of machine learning (ML) tools for enhancing geotechnical analysis has been recognized by several researchers. However, obtaining a sufficiently large digital dataset is a major technical challenge. This paper investigates the use of transfer learning, a powerful ML technique, used for overcoming dataset size limitations. The study examines two scenarios where transfer learning is applied to tunnel support analysis. The first scenario investigates transferring knowledge between a ground formation that has been well-studied to a new formation with very limited data. The second scenario is intended to investigate whether transferring knowledge is possible from a dataset that relies on simplified tunnel support analysis to a more complex and realistic analysis. The technical process for transfer learning involves training an Artificial Neural Network (ANN) on a large dataset and adding an extra layer to the model. The added layer is then trained on smaller datasets to fine-tune the model. The study demonstrates the effectiveness of transfer learning for both scenarios. On this basis, it is argued that, with further development and refinement, transfer learning could become a valuable tool for ML-related geotechnical applications.

show abstract

Section: Machine-learningmentioning

confidence: 99%

Investigation of Transfer Learning for Tunnel Support Design

Mitelman

Urlainis

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Currently, many researchers in the field of engineering geology have demonstrated the use of ML methods for various applications (Morgenroth, Khan, and Perras 2019; Padarian, Minasny, and McBratney 2019; Furtney et al 2022). However, data sets collected from geological engineering projects of sufficient quantity and quality for ML are rarely available.…”

Section: Geological Engineeringmentioning

confidence: 99%

Choosing between prediction and explanation in geological engineering: lessons from psychology

Mitelman

Yang

Elmo

et al. 2023

Interdisciplinary Science Reviews

View full text Add to dashboard Cite

the authors highlight difficulties in traditional explanatory research in the field of psychology and argue in favour of novel data-driven science. By applying machine-learning methods to large data sets, predictive power has been shown to increase significantly. Geological engineers are responsible for a wide range of applications, including the design of tunnels, dams, foundations, and mines. While the field of geological engineering stands on solid mechanistic grounds, we argue that its predictive aspect aligns more closely with psychology than other mechanistic sciences. We therefore propose a paradigm shift in geological engineering research towards a prediction-centric approach. Potentially, this could enhance cost-effectiveness in structural design and lead to substantial societal savings.

show abstract

“…This makes them extremely valuable in scenarios where rapid decision-making is crucial, such as emergency response planning, environmental impact assessments, or policy development [11,38,60,102,132,179,180,184]. Surrogate models are typically developed using advanced machine learning tools [11,60,144,158,179,184] (e.g., Koopman operator [15]) or statistical methods [43], and are trained on simulated data generated by complex physical models. To fully capture the essential patterns and relationships inherent in environmental processes, scientific knowledge can also be leveraged to enhance the ML-based surrogate models.…”

Section: Surrogate Modeling Solving Pdesmentioning

confidence: 99%

Knowledge-Guided Machine Learning

Karpatne¹,

Kannan²,

Kumar³

2022

View full text Add to dashboard Cite

This paper presents an overview of scientific modeling and discusses the complementary strengths and weaknesses of ML methods for scientific modeling in comparison to process-based models. It also provides an introduction to the current state of research in the emerging field of scientific knowledge-guided machine learning (KGML) that aims to use both scientific knowledge and data in ML frameworks to achieve better generalizability, scientific consistency, and explainability of results. We discuss different facets of KGML research in terms of the type of scientific knowledge used, the form of knowledge-ML integration explored, and the method for incorporating scientific knowledge in ML. We also discuss some of the common categories of use cases in environmental sciences where KGML methods are being developed, using illustrative examples in each category.

show abstract

Surrogate Models in Rock and Soil Mechanics: Integrating Numerical Modeling and Machine Learning

Cited by 17 publications

References 23 publications

Investigation of Transfer Learning for Tunnel Support Design

Investigation of Transfer Learning for Tunnel Support Design

Choosing between prediction and explanation in geological engineering: lessons from psychology

Knowledge-Guided Machine Learning

Contact Info

Product

Resources

About