About

Erik Westman is a professor in the Mining and Minerals Engineering department at Virginia Tech. His research interests include resource and reserve estimation, rock mechanics, mining-induced seismicity and seismic tomography, and data analytics for mine and quarry optimization. He has a background in mining and minerals engineering, having earned his Ph.D. from Virginia Tech in 1999, a master's degree in civil engineering from the University of Colorado in 1994, and a bachelor's degree in geophysical engineering from the Colorado School of Mines in 1986. His educational and professional background supports his focus on advancing mining technologies and safety through innovative research and data-driven approaches.

Research topics

• Geology
• Seismology
• Geotechnical engineering
• Materials science
• Mining engineering
• Soil science
• Composite material
• Mechanics
• Engineering
• Petroleum engineering
• Structural engineering

Selected publications

• Investigating stress evolution in rock burst prone regions in an underground mine with seismic tomographic imaging

  Geomechanics for Energy and the Environment · 2026-02-23

  article
  PublisherDOI

• Experimental study of rock mass decomposition during slip

  2026-01-21

  book-chapterSenior author

  The present study is concerned with the failure mechanics of the slope build-up on the bedrock with a smooth surface. This arrangement is typical for the internal tailings in the surface coal mines. The experimental study was conducted in a stand enabling tilting. A scale model was constructed from equvivalent materials. The smooth surface was made from a special epoxy resin. For the mathematical part, the FLAC Distinct Element Modelling Code was employed. The pile 1bored to the bedrock, instrumented with strain gages, restrain the slope movement in the experimental case. The cable tieback was considered in the mathematical solution. Both methods have shown the slip as a time depending process. Moreover, experiments allow to describe a decomposition of the originally homogeneous and isotropic body into blocks (see Figures 2–3) and, therefore, they treat the slip as a discontinous deformation process. In the future, by the use of the PFC Distinct Element Code, it will be possible to investigate the developement of cracks also in a mathematical model

  PublisherDOI

• The Role of EDA in Developing Robust Machine Learning Models for Lithology and Penetration Rate Prediction from MWD Data

  Mining · 2026-03-04 · 1 citations

  articleOpen accessSenior authorCorresponding

  Measure-While-Drilling (MWD) data provide real-time insight into subsurface conditions and drilling performance, yet their complexity and operational noise often hinder reliable modeling. This study demonstrates the role of Exploratory Data Analysis (EDA) in developing robust machine learning (ML) models for lithology classification and penetration rate (PR) prediction in mining operations. A structured EDA workflow—comprising data integrity assessment, feature distribution analysis, correlation mapping, and depth-wise parameter profiling—was implemented to identify redundant attributes, isolate non-productive intervals, and enhance dataset consistency. Through EDA-informed normalization and feature selection, data consistency and model performance were significantly improved. Machine learning algorithms, including Decision Tree, Random Forest, and Multi-Layer Perceptron, were trained on the refined dataset. The Random Forest Classifier achieved 98.45% accuracy in lithology prediction, while the Random Forest Regressor produced the most accurate PR estimation (R2 = 0.83, RMSE = 0.52). These results highlight EDA as a critical foundation for constructing physics-informed, data-driven models that enhance predictive reliability and operational efficiency in mining environments.

  PublisherOA PDFDOI

• A Comparative Study of Machine Learning and Traditional Techniques for Grade Prediction and Grade-Tonnage Evaluation in a Small VMS Deposit

  Minerals · 2026-03-07

  articleOpen accessSenior authorCorresponding

  Estimating grades in small-volume, high-grade volcanogenic massive sulfide (VMS) deposits can be difficult due to sharp changes in mineralization and limited data coverage around high-grade zones. This study compares ensemble machine learning models with interpolation and geostatistical methods to compare gold estimation and grade-tonnage results. Random Forest and Gradient Boosting were trained using drillhole composites and evaluated against Inverse Distance Weighting (IDW), Simple Kriging (SK), and Ordinary Kriging (OK). The trained models were applied across the block model to generate continuous grade predictions and support grade-tonnage calculations at multiple cutoff grades. The ensemble models showed lower RMSE and higher R2 values and captured grade patterns more efficiently than traditional methods. Grade-tonnage comparison indicated that IDW generated the highest contained gold equivalent at low cutoff grades, while OK and Gradient Boosting produced more consistent and geologically reasonable estimates. Overall, the results show that machine learning methods can complement traditional estimation techniques when combined with geological domain control and appropriate model tuning.

  PublisherOA PDFDOI

• A Machine Learning Approach to Lithology Classification in Mining Using Measurement While Drilling and Exploration Data

  Mining Metallurgy & Exploration · 2025-05-29 · 2 citations

  articleOpen access

  Abstract Accurate lithology classification is essential as variations in rock formations can significantly impact the cost and efficiency of mineral exploration and mining. Initial exploration maps provide insights into subsurface formations, though typically collected at widely spaced intervals. This study examines the use of early exploration data and Measurement While Drilling (MWD) data for lithology prediction through machine learning. The research specifically evaluates the benefit of incorporating spatial coordinates with MWD parameters to enhance classification accuracy, using support vector machine (SVM), random forest (RF), and extra gradient boosting (XGBoost) classifiers with tenfold cross-validation. The models were trained on 235,501 data points of six MWD parameters from 308 drill holes. The effects of raw (imbalanced) versus Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbor (SMOTEENN) (balanced) data were analyzed, along with a comparison between random and spatial data splits. Results indicate that SMOTEENN-balanced data paired with a spatial split strategy consistently improved model stability, with the XGBoost model achieving the highest performance, with a precision of 95.60% and an F1 score of 94.41% on unseen data. Additionally, the study revealed that integrating spatial coordinates of drilling locations consistently enhanced lithology classification, with a notable F1 score improvement of 27.97% using XGBoost. The findings highlight the value of combining spatial coordinates and MWD data for improved lithology classification and offer potential support for geological modeling and sustainable mining practices.

  PublisherOA PDFDOI

• Predicting rock mass strength from drilling data using synergistic unsupervised and supervised machine learning approaches

  Earth Science Informatics · 2025-03-12 · 3 citations

  articleOpen access

  Abstract Extracting rock mass strength properties from existing data like Measurement While Drilling (MWD) is important to reduce the cost of additional geological and geotechnical surveys. This study presents an approach that combines clustering (unsupervised learning) and classification algorithms to identify similar rock groups for their prediction. The dataset comprises 272,272 MWD from 2,790 drill holes, split into 215,401 data points (2,332 drill holes) for cross-validation, and another 215,401 data points, from 558 previously unseen drill holes for testing. Principal component analysis (PCA) and clustering algorithms such as K-means, Gaussian mixture, C Fuzy, and hierarchical clustering were employed to group rocks with similar MWD parameters. The combination of PCA and k-means clustering provides good cluster quality which best describes the different rock strength characteristics (clusters), as revealed by geological investigation and coring data. After identifying the rock categories, Extra Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) approaches were used to develop classification models for rock strength prediction. The XGBoost model achieved the best and most reliable performance with accuracy, precision, recall, and F1 score exceeding 98% on the test set. This study highlights the synergetic benefits of combining unsupervised and supervised machine learning techniques to predict rock mass conditions, especially in scenarios with limited geological information or unavailable labeled data.

  PublisherOA PDFDOI

• Improved Adaptive Variational Mode Decomposition for Denoising Teleseismic P-Wave Data

  Rock Mechanics and Rock Engineering · 2025-12-22

  article
  PublisherDOI

• Research on failure mechanism and support technology of fractured rock mass in an undersea gold mine

  Geomatics Natural Hazards and Risk · 2023-06-10 · 7 citations

  articleOpen access

  The surrounding rock control has been a difficult problem for fractured rock mass in hard rock mines. This article describes a case study of the failure mechanisms and the support design technology for fractured rock mass drifts in Xinli Gold Mine. Based on field investigation, the geology characteristics, failure types, influencing factors, support types, and their failure types were analyzed. The rock mass classification, rock mass physical and mechanical parameters were obtained by using Q, RMR, and GSI systems. The zoning of surrounding rock, stability analysis and zoning support schemes design were carried out based on rock mass classification results. The pretension is designed by China underground mine experiences and verified by numerical simulation. RS2 was used to compare the plastic zone under pre- and post-support conditions. The plastic zone is significantly reduced after support is installed, which indicates that the designed support schemes can effectively control the failure of surrounding rock. In view of difficulties in the excavation and support of fractured rock mass, the short excavation and short support technology was proposed to ensure the success excavation of the drift in fractured rock mass. The field application shows that the short excavation and support technology are effective.

  PublisherOA PDFDOI

• Underground Rock Mass Behavior Prior to the Occurrence of Mining Induced Seismic Events

  Geotechnics · 2022-09-05 · 3 citations

  articleOpen access

  The variations of seismic velocity prior to the occurrence of major seismic events are an indicator of the rock mass performance subjected to mining-induced stress. There have been no prior field-scale studies to examine stress change within the rockmass volume immediately prior to potentially damaging mining-induced seismicity. Monitoring stress change is critical for mine stability and operation safety and eventually improves production by optimizing mine designs and mining practices. In this study, five major seismic events that occurred in a narrow-vein mine were used as case studies in order to investigate any significant changes in P-wave velocity distribution, on a daily basis, within a week of seismic events with Mw > 1; if observed, such changes could provide a warning to mine engineers and workers. It was observed there was no consistent significant velocity change of more than 1% within 200 m of the hypocenters within 6 days prior to the events. Additionally, the influence of blasting in the week of the occurrence of events was investigated however no recognizable trend was observed between blasting and changes in the seismic velocity distribution within the rock mass on the day of a blast or the following day.

  PublisherOA PDFDOI

• GEOPHYSICS GUIDED DEEP IMPUTATION NETWORKS FOR PREDICTING 3D GEOSPATIAL DATA

  Abstracts with programs - Geological Society of America · 2022-01-01

  article
  PublisherDOI

Recent grants

• CAREER: Stress Redistribution Imaging for Rock Failure Prediction

  NSF · $402k · 2002–2008

Frequent coauthors

• Xu Ma

  Heilongjiang University of Technology

  11 shared

• Kray Luxbacher

  University of Arizona

  10 shared

• Brent Slaker

  National Institute for Occupational Safety and Health

  9 shared

• Nino Ripepi

  7 shared

• James E. McClure

  6 shared

• Setareh Ghaychi Afrouz

  Virginia Tech

  6 shared

• Michael M. Murphy

  National Institute for Occupational Safety and Health

  6 shared

• Ben Fahrman

  Virginia Tech

  5 shared

Education

• PhD, Mining and Minerals Engineering

  Virginia Tech

  1999

• MS, Civil Engineering - Geotechnical

  University of Colorado - Denver

  1993

• BS, Geophysical Engineering

  Colorado School of Mines

  1986