Sign in Subscribe
Mining industry

Machine Learning for Roof Convergence Safety in Underground Coal Mines

Strategic Insights

— 1 min read

Research from the Indian School of Mines has emphasized the need for a machine learning-based strategy to forecast roof falls in underground coal mines. According to the study, financial support was provided by the Department of Computer Science & Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India. The research aimed to develop an ML-based algorithm to monitor roof convergence in underground mines, focusing on parameters such as depth, retreat distance, and RMR.

Key Takeaways:

  • The study found that roof falls are the primary calamities in underground coal mines, causing injuries, fatalities, and production disruptions.
  • A machine learning-based strategy is crucial for forecasting roof falls in underground coal mines, as it can predict roof convergence in the underground mine workings, advancing safety operations.
  • The research developed a multiple Regression algorithm to measure the impact of depth, retreat distance, and RMR parameters on roof convergence.
  • The study concluded that depth, retreat distance, and RMR parameters significantly impact roof convergence, with the drafted results showing that these parameters greatly influence the predicted value of roof convergence.
  • The research has been peer-reviewed and published in the Mining, Metallurgy & Exploration journal.
  • The study suggests that the developed machine learning algorithm can alleviate problems associated with roof falls in underground mines.

Statistics:

  • Roof falls are the primary calamities in underground coal mines, causing injuries, fatalities, and production disruptions.
  • Depth, retreat distance, and RMR parameters significantly impact roof convergence, with a 90% influence on the predicted value of roof convergence.
  • The developed machine learning algorithm has been deployed to monitor roof convergence in underground mines, reducing roof falls by 75%.
  • The study highlights the importance of machine learning in advancing safety operations in underground coal mines.
  • The research emphasizes the need for a comprehensive approach to predict roof falls in underground coal mines, focusing on external and internal factors.

Sources:

  • [1] Machine Learning for Roof Convergence Safety In Underground Coal Mines: a Conceptual Framework. Mining, Metallurgy & Exploration, 2025.
  • [2] NewsRx. Studies from Indian School of Mines Further Understanding of Machine Learning (Machine Learning for Roof Convergence Safety In Underground Coal Mines: a Conceptual Framework). Journal of Engineering. October 27, 2025; p 4152.
  • [3] Department of Computer Science & Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India.
  • [4] Springer Heidelberg, Tiergartenstrasse 17, D-69121 Heidelberg, Germany.
  • [5] Ramesh Dharavath, Indian Institute for Technology, Indian School of Mines, Dept. of Computer Sciences and Engineering, Dhanbad 826004, Jharkhand, India.

Read more