A transparent and valid framework for rockburst assessment: unifying Interpretable machine learning and conformal prediction

Date

2024

Authors

Ibrahim, B.
Tetteh Asare, A.
Ahenkorah, I.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

Rock Mechanics and Rock Engineering, 2024; 57(8):6211-6225

Statement of Responsibility

Conference Name

Abstract

The utilization of machine learning (ML) for rockburst assessment is hindered by an incomplete problem formalization in prior studies, which have focused more on predictive accuracy and less on factors such as explainability and uncertainty quantification. Despite achieving commendable accuracies, practitioners remain apprehensive about real-time implementation due to concerns surrounding transparency and validity, particularly when dealing with challenging or unfamiliar rock samples. This uncertainty may result in arbitrary predictions which are mostly incorrect. Establishing trust in ML applications, particularly in critical domains like rockburst assessment, requires models to provide transparent reasoning, communicate uncertainty, and exercise caution when making assertive predictions with unfamiliar data. This paper addresses these concerns by introducing a novel framework that combines interpretable ML techniques specifically Shapley additive explanation (SHAP), with adaptive conformal prediction (CP), built atop extreme gradient boosting to establish a transparent and reliable predictive framework. The validity of the proposed framework was rigorously assessed using conformal metrics, including marginal coverage, conditional coverage, and average prediction set size. Additionally, the SHAP technique was employed to elucidate explanations for predictions flagged as unreliable through CP. The results justify the framework’s high effectiveness in generating valid predictions for rockburst grades, concurrently providing corresponding confidence levels and insights into the underlying mechanisms that drive these predictions. The proposed framework facilitates the identification of unreliable predictions, ensuring that only reliable predictions inform decision-making. This not only enhances user confidence in the predictive model but also contributes to the overall safety of underground engineering projects.

School/Discipline

Dissertation Note

Provenance

Description

Data source: Supplementary information, https://doi.org/10.1007/s00603-024-03847-0

Access Status

Rights

Copyright 2024 The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.

License

Grant ID

Call number

Persistent link to this record