Pathway to a fully data-driven geotechnics: lessons from materials informatics

TL;DR

This paper explores how data-driven methods, inspired by materials informatics, can revolutionize geotechnics by addressing soil complexity, promoting open data initiatives, and leveraging deep learning and large language models for innovation.

Contribution

It highlights the challenges in integrating data-driven approaches into geotechnics and proposes strategies like community databases and advanced AI tools to foster progress.

Findings

Deep learning enhances feature extraction from complex geotechnical data.

Open science and community databases are crucial for progress in geotechnics.

Large language models have potential to transform geotechnics informatics.

Abstract

This paper elucidates the challenges and opportunities inherent in integrating data-driven methodologies into geotechnics, drawing inspiration from the success of materials informatics. Highlighting the intricacies of soil complexity, heterogeneity, and the lack of comprehensive data, the discussion underscores the pressing need for community-driven database initiatives and open science movements. By leveraging the transformative power of deep learning, particularly in feature extraction from high-dimensional data and the potential of transfer learning, we envision a paradigm shift towards a more collaborative and innovative geotechnics field. The paper concludes with a forward-looking stance, emphasizing the revolutionary potential brought about by advanced computational tools like large language models in reshaping geotechnics informatics.