Skip to main content

Real Time Mine Fire Classification to Support Firefighter Decision Making


This paper presents a data-driven approach that can provide the most suitable decision to the mine firefighting personnel in real time during ongoing underground coal mine fires. The approach uses a feed-forward artificial neural network (ANN) to classify fires to provide the best decision considering only parameters measurable in underground coal mines. Additionally, the methodology along with the concepts that should be considered to elaborate a data-driven approach of this type are detailed. A total of 500 fire scenarios with different fire size, air velocity, fire growth rate, and entry dimensions were simulated in Fire Dynamics Simulator (FDS) and Fire and Smoke Simulator (FSSIM) for data generation to train and test the model. Results show that the ANN predicted fire classes with an accuracy and weighted-average F1-score equals to 97% and 96.7% for training and testing dataset, respectively. Results also show that 95% of ANN predictions of fire class change should not have a time gap greater than 18 s of the true fire class change for any fire position in the tunnel. Furthermore, the impact of fuel uncertainty during mine fires and how to address it is discussed in this paper. While the model presented in this work was designed to classify fires in a regular elongated coal mine entry, the same methodology could be applied to classify fires in other scenarios with similar geometry, such as road tunnels.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18

Availability of data and material

All datasets and codes used for supporting the conclusions of this article are available upon request at the following website:


  1. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mane D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viegas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2016) TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467

  2. Alwosheel A, van Cranenburgh S, Chorus CG (2018) Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis. J Choice Model 28:167–182.

    Article  Google Scholar 

  3. Brake DJ (2013) Fire modelling in underground mines using Ventsim Visual VentFIRE Software. In: The Australian Mine Ventilatoin Conference. Adelaide

  4. Buffington T, Cabrera JM, Kurzawski A, Ezekoye OA (2020) Deep-learning emulators of transient compartment fire simulations for inverse problems and room-scale calorimetry. Fire Technol.

    Article  Google Scholar 

  5. Chollet F (2015) Keras.

  6. Conti RS, Chasko LL, Wiehagen WJ, Lazzara CP (2000) An underground coal mine fire preparedness and response checklist: the instrument. Tech. rep, Pittsburgh

    Google Scholar 

  7. Conti RS, Chasko LL, Wiehagen WJ, Lazzara CP (2005) Fire response preparedness for underground mines. Tech rep, NIOSH

    Google Scholar 

  8. De Rosa MI (2004) Analysis of mine fires for all U.S. underground and surface coal mining categories: 1990-1999. National Institute for Occupational Safety and Health, Centers for Disease Control and Prevention pp. 1–36

  9. Floyd JE, Hunt SP, Williams FW, Tatem PA (2005) A network fire model for the simulation of fire growth and smoke spread in multiple compartments with complex ventilation. J Fire Prot Eng.

    Article  Google Scholar 

  10. Fridolf K, Andrée K, Nilsson D, Frantzich H (2014) The impact of smoke on walking speed. Fire Mater 38(7):744–759

    Article  Google Scholar 

  11. Gehandler J, Ingason H, Lönnermark A, Frantzich H, Strömgren M (2013) Performance-based requirements and recommendations for fire safety in road tunnels (FKR-BV12)

  12. Goodfellow I, Bengio Y, Courville A (2016) Deep learning.

  13. Grieco E, Bernardi M, Baldi G (2008) Pyrolysis Styrene - butadiene rubber pyrolysis: products, kinetics, modelling. J Anal Appl Pyrol 82:304–311.

    Article  Google Scholar 

  14. Hadjisophocleous G, Jia Q (2009) Comparison of FDS prediction of smoke movement in a 10-Storey building with experimental data. Fire Technol 45(2):163–177.

    Article  Google Scholar 

  15. Haghighat A, Luxbacher K (2018) Tenability analysis for improvement of firefighters‘ performance in a methane fire event at a coal mine working face. J Fire Sci 36(3):256–274.

    Article  Google Scholar 

  16. Hodges JL (2018) Predicting large domain multi-physics fire behavior using artificial neural networks. Phd dissertation, Virginia Tech

  17. Hodges JL, Lattimer BY, Luxbacher KD (2019) Compartment fire predictions using transpose convolutional neural networks. Fire Saf J 108(2018):102854.

    Article  Google Scholar 

  18. ICIS: Styrene-Butadiene Rubber (SBR) Uses and Outlook - ICIS Explore (2010).

  19. Ingason H (1995) Design fires in tunnels. In: Conference Proceedings of Asiaflam 95, pp. 77–86. Hong Kong

  20. Ingason H, Li YZ, Lönnermark A (2015) Tunnel fire ventilation. In: Tunnel fire dynamics, vol. 53, pp. 333–360. Springer New York, New York, NY.

  21. Kerber S, Milke JA (2007) Using FDS to simulate smoke layer interface height in a simple atrium. Fire Technol 43(1):45–75.

    Article  Google Scholar 

  22. Lattimer B, Hodges J, Lattimer A (2020) Using machine learning in physics-based simulation of fire. Fire Saf J 114:102991.

    Article  Google Scholar 

  23. Lee J, Lee S, You D (2018) Deep learning approach in multi-scale prediction of turbulent mixing-layer pp. 1–21. arXiv:1809.07021

  24. Lee S, You D (2017) Prediction of laminar vortex shedding over a cylinder using deep learning (Wu 2011). arXiv:1712.07854

  25. Li YZ, Ingason H (2017) Effect of cross section on critical velocity in longitudinally ventilated tunnel fires. Fire Saf J 91:303–311.

    Article  Google Scholar 

  26. Li YZ, Lei B, Ingason H (2010) Study of critical velocity and backlayering length in longitudinally ventilated tunnel fires. Fire Saf J 45(6–8):361–370.

    Article  Google Scholar 

  27. Lin JP, Chang CY (1996) Pyrolytic treatment of rubber waste: pyrolysis kinetics of styrene-butadiene rubber. J Chem Technol Biotechnol 66:7–14

    Article  Google Scholar 

  28. Maevski I (2011) Tenable Environment- Literature Review. In: Design fires in road tunnels, chap. Three, pp. 323–332.

  29. Maulik R, San O (2017) A neural network approach for the blind deconvolution of turbulent flows. J Fluid Mech 831:151–181.

    Article  MathSciNet  MATH  Google Scholar 

  30. McGrattan K, Hostikka S, Floyd J, Baum H, Rehm RG (2018) Fire dynamics simulator (Version 6), Technical Reference Guide. NIST - Spec. Publ.

  31. McGrattan KB, Forney GP (2004) Fire dynamics simulator (version 4): user’s guide. Tech. rep., National Institute of Standards and Technology, Gaithersburg, MD.

  32. Mcpherson MJ (1993) Chapter 21: Fires and explosions. In: Subsurface ventilation engineering, first edn

  33. Miyanawala TP, Jaiman RK (2017) An efficient deep learning technique for the Navier-Stokes equations: application to unsteady wake flow dynamics. arXiv:1710.09099

  34. NFPA: NFPA 502: Standard for Road Tunnels, Bridges, and Other Limited Access Highways (2020).

  35. NIOSH: 1988 OSHA PEL Project Documentation (1988).

  36. Oka Y, Atkinson GT (1995) Control of smoke flow in tunnel fires. Fire Saf J 25(4):305–322.

    Article  Google Scholar 

  37. Raissi M, Yazdani A, Karniadakis GE (2018) Hidden fluid mechanics: a Navier-Stokes informed deep learning framework for assimilating flow visualization data. arXiv:1808.04327

  38. Rowland JH, Harteis SP, Yuan L (2018) A survey of atmospheric monitoring systems in US underground coal mines. Min Eng 70(2):37–40

    Article  Google Scholar 

  39. Shen TS, Huang YH, Chien SW (2008) Using fire dynamic simulation (FDS) to reconstruct an arson fire scene. Build Environ 43(6):1036–1045.

    Article  Google Scholar 

  40. Tewarson: Chapter 4: generation of heat and chemical compounds in fires. In: SFPE Handbook of Fire Protection Engineering, Third Edition, chap. Section Th, pp. Section 3–111 (2002)

  41. Tewarson A, Jiang FH, Morikawa T (1993) Ventilation-controlled combustion of polymers. Combust Flame 169:151–169

    Article  Google Scholar 

  42. Thomas PH (1968) The movement of smoke in horizontal passages against an air flow. Fire Research Station (723)

  43. US Code of Federal Regulations: CFR, title 30 (mineral resources) part 75. Mandatory safety standards-underground coal mines (2016).

  44. Vauquelin O (2005) Parametrical study of the back flow occurrence in case of a buoyant release into a rectangular channel. Exp Thermal Fluid Sci 29(6):725–731.

    Article  Google Scholar 

  45. Wu Y, Bakar MZ (2000) Control of smoke flow in tunnel fires using longitudinal ventilation systems - a study of the critical velocity. Fire Saf J 35(4):363–390.

    Article  Google Scholar 

  46. Yu LX, Beji T, Maragkos G, Liu F, Weng MC, Merci B (2018) Assessment of numerical simulation capabilities of the fire dynamics simulator (FDS 6) for planar air curtain flows. Fire Technol 54(3):583–612.

    Article  Google Scholar 

  47. Yuan L, Litton CD (2007) Experimental study of flame spread on conveyor belts in a small-scale tunnel. National Institute for Occupational Safety and Health

  48. Yuan L, Mainiero RJ, Rowland JH, Thomas RA, Smith AC (2014) Numerical and experimental study on flame spread over conveyor belts in a large-scale tunnel. J Loss Prev Process Ind 30:55–62.

    Article  Google Scholar 

  49. Yuan L, Thomas RA, Zhou L (2017) Characterization of a mine fire using atmospheric monitoring system sensor data. Min Eng 69(6):57–62

    Article  Google Scholar 

Download references


This research was supported by Contract No. 200-2014-59669, awarded by the National Institute for Occupational Safety and Health (NIOSH). The findings and conclusions in this report are those of the authors and do not reflect the official policies of the Department of Health and Human Services; nor does mention of trade names, commercial practices, or organizations imply endorsement by the U.S. Government.


This research was funded by the National Institute Safety and Health (NIOSH) under contract No. 200-2014-59669.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Manuel J. Barros-Daza.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Barros-Daza, M.J., Luxbacher, K.D., Lattimer, B.Y. et al. Real Time Mine Fire Classification to Support Firefighter Decision Making. Fire Technol 58, 1545–1578 (2022).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Fire emergency response
  • ANN neural network
  • Mine fire classification
  • Mine firefighters