Artificial Intelligence (AI) has demonstrated the ability to predict gas-related incidents in coal mines within a half-hour window, according to a recent study.
The Charles Darwin University research highlights how AI can reduce the risk of mining disasters, offering a critical solution to an industry fraught with gas explosion hazards.
The study, which focused on coal mines in China, tested ten machine learning algorithms to determine which AI methods could most accurately forecast changes in methane gas levels 30 minutes before they occur, enabling early detection and notification of potential dangers.
According to data reported by CDU, methane gas is a major contributor to mining accidents, with almost 60 per cent of coal mine disasters in China resulting from gas explosions or ignitions.
China, which produced 46 per cent of the world’s coal in 2020, operates over 3,200 coal mines with particularly high methane gas content, putting many at an elevated risk for such incidents.
Lead author of the study, Adjunct Associate Professor Niusha Shafiabady from the Faculty of Science and Technology at CDU, revealed that four of the ten machine learning algorithms tested achieved the best results.
“Linear Regression is one of the most efficient algorithms with better performance for short-term forecasting than others,” said Associate Professor Shafiabady.
“Random Forest frequently shows a statistically lower error performance and achieves the highest prediction accuracy. Support Vector Machine performs well and has a shorter computational time on small datasets but will require too much training time as the dataset size increases.”
She emphasised that these findings could help the coal mining industry minimize accident risks, protect workers, and mitigate financial losses.
“The findings of this study will help the coal mining industry to reduce the risk of accidents such as gas explosions, safeguard workers, and enhance the ability to prevent and mitigate disasters which will lead to financial losses in addition to potential losses of lives,” she added.
The research was conducted in collaboration with CDU, the University of Technology Sydney, Australian Catholic University, Shanxi Normal University, and Central Queensland University. The study, titled Comparative Study of Ten Machine Learning Algorithms for Short-Term Forecasting in Gas Warning Systems, was published in the journal Scientific Reports.
According to Associate Professor Shafiabady, who is also a researcher at Australian Catholic University’s Peter Faber Business School, the applications of AI in gas-related risk mitigation extend beyond the mining industry.
“This method works for all coal mines, and the same principles can apply to other industries such as aerospace, oil and gas, agriculture and more,” she said.
“This is an example of an application where AI can be used to save lives and mitigate health and safety risks.”
The findings build upon earlier research conducted by Associate Professor Shafiabady, which revealed that monitoring wind, gas density, and temperature fluctuations in coal mines can further help reduce the likelihood of disasters.
