An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining
Blast induced ground vibrations (BIGV) pose critical challenges in surface mining, threatening structural integrity, worker safety, and environmental compliance. This study proposes a novel hybrid artificial intelligence (AI) framework that integrates physics informed neural networks (PINNs) with co...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025021188 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839634688500563968 |
|---|---|
| author | Charan Kumar Ala Zefree Lazarus Mayaluri Aman Kaushik Nikhat Parveen Surabhi Saxena Abu Taha Zamani Debendra Muduli |
| author_facet | Charan Kumar Ala Zefree Lazarus Mayaluri Aman Kaushik Nikhat Parveen Surabhi Saxena Abu Taha Zamani Debendra Muduli |
| author_sort | Charan Kumar Ala |
| collection | DOAJ |
| description | Blast induced ground vibrations (BIGV) pose critical challenges in surface mining, threatening structural integrity, worker safety, and environmental compliance. This study proposes a novel hybrid artificial intelligence (AI) framework that integrates physics informed neural networks (PINNs) with conventional machine learning (ML) algorithms for the accurate prediction and optimization of BIGV. Unlike empirical equations that lack generalizability or black box ML models with limited transparency, the proposed approach embeds domain specific physical laws while leveraging data driven learning to improve both predictive accuracy and interpretability. A multiobjective optimization scheme is employed to balance competing goals: minimizing peak particle velocity (PPV), maximizing fragmentation efficiency, and reducing operational costs. Crucially, the framework incorporates Explainable AI (XAI) techniques such as Shapley Additive Explanations (SHAP) and Local Interpretable Model Agnostic Explanations (LIME) and uncertainty quantification (UQ) methods based on Bayesian Neural Networks to provide insight into model decisions and confidence in predictions. Validation across five operational mines in the Godavari Valley Coalfields (India) demonstrates strong generalizability, achieving up to a 20% reduction in RMSE compared to empirical baselines. The improvement is statistically significant (p<0.01) as confirmed through a paired t-test across cross-validation folds. These findings highlight that a physics informed, explainable, and uncertainty aware AI framework can substantially improve vibration prediction, ensure regulatory compliance, and support safer, more sustainable blasting operations in modern surface mining. |
| format | Article |
| id | doaj-art-b078ab0f9b074c87b733e65fd8d2fc9f |
| institution | Matheson Library |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-b078ab0f9b074c87b733e65fd8d2fc9f2025-07-10T04:35:01ZengElsevierResults in Engineering2590-12302025-09-0127106046An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface miningCharan Kumar Ala0Zefree Lazarus Mayaluri1Aman Kaushik2Nikhat Parveen3Surabhi Saxena4Abu Taha Zamani5Debendra Muduli6Department of Mining Engineering, National Institute of Technology Rourkela, IndiaDepartment of Electrical Engineering, C. V. Raman Global University, Odisha, India; Corresponding authors.AIT-CSE, Chandigarh University, Mohali, Punjab, 140413, IndiaDepartment of Artificial Intelligence, College of Computing and Information Technology, University of Bisha, Eastern Province, Saudi ArabiaDepartment of Computer Science, CHRIST University, Bengaluru, IndiaDepartment of Computer Science, Faculty of Science, Northern Border University, Arar 73213, Saudi ArabiaDepartment of Computer Science and Engineering, C. V. Raman Global University, Odisha, India; Corresponding authors.Blast induced ground vibrations (BIGV) pose critical challenges in surface mining, threatening structural integrity, worker safety, and environmental compliance. This study proposes a novel hybrid artificial intelligence (AI) framework that integrates physics informed neural networks (PINNs) with conventional machine learning (ML) algorithms for the accurate prediction and optimization of BIGV. Unlike empirical equations that lack generalizability or black box ML models with limited transparency, the proposed approach embeds domain specific physical laws while leveraging data driven learning to improve both predictive accuracy and interpretability. A multiobjective optimization scheme is employed to balance competing goals: minimizing peak particle velocity (PPV), maximizing fragmentation efficiency, and reducing operational costs. Crucially, the framework incorporates Explainable AI (XAI) techniques such as Shapley Additive Explanations (SHAP) and Local Interpretable Model Agnostic Explanations (LIME) and uncertainty quantification (UQ) methods based on Bayesian Neural Networks to provide insight into model decisions and confidence in predictions. Validation across five operational mines in the Godavari Valley Coalfields (India) demonstrates strong generalizability, achieving up to a 20% reduction in RMSE compared to empirical baselines. The improvement is statistically significant (p<0.01) as confirmed through a paired t-test across cross-validation folds. These findings highlight that a physics informed, explainable, and uncertainty aware AI framework can substantially improve vibration prediction, ensure regulatory compliance, and support safer, more sustainable blasting operations in modern surface mining.http://www.sciencedirect.com/science/article/pii/S2590123025021188Surface miningPhysics-informed neural networksExplainable AIUncertainty quantificationBlast-induced vibrations |
| spellingShingle | Charan Kumar Ala Zefree Lazarus Mayaluri Aman Kaushik Nikhat Parveen Surabhi Saxena Abu Taha Zamani Debendra Muduli An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining Results in Engineering Surface mining Physics-informed neural networks Explainable AI Uncertainty quantification Blast-induced vibrations |
| title | An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining |
| title_full | An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining |
| title_fullStr | An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining |
| title_full_unstemmed | An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining |
| title_short | An explainable AI-based framework for predicting and optimizing blast-induced ground vibrations in surface mining |
| title_sort | explainable ai based framework for predicting and optimizing blast induced ground vibrations in surface mining |
| topic | Surface mining Physics-informed neural networks Explainable AI Uncertainty quantification Blast-induced vibrations |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025021188 |
| work_keys_str_mv | AT charankumarala anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT zefreelazarusmayaluri anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT amankaushik anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT nikhatparveen anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT surabhisaxena anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT abutahazamani anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT debendramuduli anexplainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT charankumarala explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT zefreelazarusmayaluri explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT amankaushik explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT nikhatparveen explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT surabhisaxena explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT abutahazamani explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining AT debendramuduli explainableaibasedframeworkforpredictingandoptimizingblastinducedgroundvibrationsinsurfacemining |