Research Papers

Evaluating the Effectiveness of Mine Safety Enforcement Actions in Forecasting the Lost-Days Rate at Specific Worksites

[+] Author and Article Information
Jeremy M. Gernand

Department of Energy and Mineral Engineering,
The Pennsylvania State University,
University Park, PA 16802
e-mail: jmgernand@psu.edu

Manuscript received March 5, 2015; final manuscript received March 1, 2016; published online August 19, 2016. Assoc. Editor: Chimba Mkandawire.

ASME J. Risk Uncertainty Part B 2(4), 041002 (Aug 19, 2016) (6 pages) Paper No: RISK-15-1042; doi: 10.1115/1.4032929 History: Received March 05, 2015; Accepted March 01, 2016

The safety of mining in the United States has improved significantly over the past few decades, although it remains one of the more dangerous occupations. Following the Sago mine disaster in January 2006, federal legislation (The Mine Improvement and New Emergency Response [MINER] Act of 2006) tightened regulations and sought to strengthen the authority and safety-inspection practices of the Mine Safety and Health Administration (MSHA). While penalties and inspection frequency have increased, understanding of what types of inspection findings are most indicative of serious future incidents is limited. The most effective safety management and oversight could be accomplished by a thorough understanding of what types of infractions or safety inspection findings are most indicative of serious future personnel injuries. However, given the large number of potentially different and unique inspection findings, varied mine characteristics, and types of specific safety incidents, this question is complex in terms of the large number of potentially relevant input parameters. New regulations rely on increasing the frequency and severity of infraction penalties to encourage mining operations to improve worker safety, but without the knowledge of which specific infractions may truly be signaling a dangerous work environment. This paper seeks to inform the question: What types of inspection findings are most indicative of serious future incidents for specific types of mining operations? This analysis utilizes publicly available MSHA databases of cited infractions and reportable incidents. These inspection results are used to train machine learning Classification and Regression Tree (CART) and Random Forest (RF) models that divide the groups of mines into peer groups based on their recent infractions and other defining characteristics with the aim of predicting whether or not a fatal or serious disabling injury is more likely to occur in the following 12-month period. With these characteristics available, additional scrutiny may be appropriately directed at those mining operations at greatest risk of experiencing a worker fatality or disabling injury in the near future. Increased oversight and attention on these mines where workers are at greatest risk may more effectively reduce the likelihood of worker deaths and injuries than increased penalties and inspection frequency alone.

Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.


Hinze, J., and , and Godfrey, R., 2003, “An Evaluation of Safety Performance Measures for Construction Projects,” J. Constr. Res., 4(1), pp. 5–15. 10.1142/S160994510300025X
Kinilakodi, H., , Grayson, R. L., and , and Oyewole, S. A., 2012, “Evaluating Equivalence of the Safe Performance Index (SPI) to a Traditional Risk Analysis,” Open J. Saf. Sci. Technol., 2(2), pp. 47–54. 10.4236/ojsst.2012.22007
Cooke, D. L., 2003, “A System Dynamics Analysis of the Westray Mine Disaster,” Syst. Dyn. Rev., 19(2), pp. 139–166. 1099-1727 10.1002/(ISSN)1099-1727
Grayson, L., and , and Kinilakodi, H., 2012, “Underground Coal Mine Safety Performance: A Decade of Challenges and Improvements,” Coal Age, 117(1), pp. 50–51. 0009-9910
Rivas, T., , Paz, M., , Martín, J. E., , Matías, J. M., , García, J. F., and , and Taboada, J., 2011, “Explaining and Predicting Workplace Accidents Using Data-Mining Techniques,” Reliab. Eng. Syst. Saf., 96(7), pp. 739–747. 10.1016/j.ress.2011.03.006
Chen, S., and , and Wang, W., 2009, “Decision Tree Learning for Freeway Automatic Incident Detection,” Expert Syst. Appl., 36(2), pp. 4101–4105. 10.1016/j.eswa.2008.03.012
Gernand, J. M., and , and Casman, E. A., 2013, “Selecting Nanoparticle Properties to Mitigate Risks to Workers and the Public—A Machine Learning Modeling Framework to Compare the Pulmonary Risks of Nanomaterials,” International Mechanical Engineering Congress and Exposition (IMECE), ASME, San Diego, CA, pp. 1–20.
Gernand, J., and , and Casman, E., 2014, “A Meta-Analysis of Carbon Nanotube Pulmonary Toxicity Studies—How Physical Dimensions and Impurities Affect the Toxicity of Carbon Nanotubes,” Risk Anal., 34(3), pp. 583–597. 0272-4332 10.1111/risa.2014.34.issue-3 [PubMed]
MSHA, 2014, “MSHA Part 50 Data Files” [Online]. Available: http://www.msha.gov/OpenGovernmentData/OGIMSHA.asp# (Accessed: Jan. 3, 2014).
Breiman, L., , Friedman, J., , Stone, C., and , and Olshen, R. A., 1984, Classification and Regression Trees, Chapman and Hall/CRC, New York.
Breiman, L., 2001, “Random Forests,” Mach. Learn., 45(1), pp. 5–32. 0885-6125 10.1023/A:1010933404324
McVittie, D., , Banikin, H., and , and Brocklebank, W., 1997, “The Effects of Firm Size on Injury Frequency in Construction,” Saf. Sci., 27(1), pp. 19–23. 10.1016/S0925-7535(97)00048-9
Moses, L. N., and , and Savage, I., 1994, “The Effect of Firm Characteristics on Truck Accidents,” Accid. Anal. Prev., 26(2), pp. 173–179. 0001-4575 10.1016/0001-4575(94)90087-6 [PubMed]
Kniesner, T. J., and , and Leeth, J. D., 2004, “Data Mining Mining Data: MSHA Enforcement Efforts, Underground Coal Mine Safety, and New Health Policy Implications,” ASCE-ASME J. Risk Uncertainty Eng. Syst. Part B: Mech. Eng., 29(2), pp. 83–111. 10.1023/B:RISK.0000038939.25355.d8
Morantz, A. D., 2008, “Mining Mining Data: Bringing Empirical Analysis to Bear on the Regulation of Safety and Health in U.S. Mining,” West VA. Law Rev., 111.
Boden, L. I., and , and Gold, M., 1984, “The Accuracy of Self-Reported Regulatory Data: The Case of Coal Mine Dust,” Am. J. Ind. Med., 6(6), pp. 427–440. 0271-3586 10.1002/(ISSN)1097-0274 [PubMed]


Grahic Jump Location
Fig. 1

Example single-branch of a RT model showing that the rate of lost-time incidents is affected by the number of employees working at a particular site

Grahic Jump Location
Fig. 2

Variable importance from RT model indicating that the rate of lost-time injuries can be anticipated by the total worker time at a mine and the average penalty assessed by MSHA in the previous year

Grahic Jump Location
Fig. 3

Variable importance from RF model indicating that total penalties due and number of employees may be partial proxies for the two most important variables in RT model

Grahic Jump Location
Fig. 4

Changes in the lost-days rate per 100,000 workers based on previous year’s mine characteristics or enforcement actions including: (a) average assessed penalty per violation, (b) total worker-days per week at each mine, (c) total worker experience, and (d) total outstanding penalties

Grahic Jump Location
Fig. 5

Tornado sensitivity plot of the magnitude difference in lost-days rate for changes in each significant RF model variable from the minimum to maximum value (while all other variables held at their median values)




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Articles from Part A: Civil Engineering
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In