What question did this study set out to answer?

To establish a 'data-centric geotechnics' agenda that prioritizes geotechnical data quality, engineering context, and practical site needs over purely algorithm-focused approaches.

June 16, 2022Georisk Assessment and Management of Risk for Engineered Systems and Geohazards

Future of machine learning in geotechnics

View Full Paper

Ask AI

Bookmark

To establish a 'data-centric geotechnics' agenda that prioritizes geotechnical data quality, engineering context, and practical site needs over purely algorithm-focused approaches.
Synthesized current limitations and progress across machine learning literature in geotechnical engineering.
Conceptualized a tripartite framework focusing on data centricity, fitness for engineering practice, and domain-specific geotechnical context.
Identified data-driven site characterization as a pivotal priority for handling irregular ground data and enabling explainable site recognition.
Outlined critical pathways for machine learning adoption, including meta-learning algorithms, digital twins for real-time site modeling, and achieving operational supremacy in civil workflows.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Review reveals a data-centric framework for machine learning in geotechnical engineering, highlighting the necessity of ground context and practical transformation.

Cite This Study

Phoon et al. (2022) studied this question.

synapsesocial.com/papers/69fd4f81c105307ccb50993e https://doi.org/10.1080/17499518.2022.2087884

View Full Paper

Ask AI

Bookmark

Implication

Review reveals a data-centric framework for machine learning in geotechnical engineering, highlighting the necessity of ground context and practical transformation.

Future of machine learning in geotechnics

Key Points

Discussion

Implication

Cite This Study

Future of machine learning in geotechnics

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider