INTELLIGENT EARLY-WARNING AND DECISION-MAKING FOR COALFIELD FIRE RISK BASED ON RANDOM FOREST: A CASE STUDY OF ABANDONED GOAFS IN NORTHERN CHINA
Keywords:
Coalfield fire, Radon measurement, Thermal infrared imaging, Random forest, Risk early warningAbstract
Coalfield fire risk identification is challenged by the strong concealment of goafs, the development of surface fissures, the unclear distribution of residual coal in abandoned workings, and uncertainties associated with multi-source detection data. Conventional approaches based on a single temperature threshold or expert empirical judgement are therefore insufficient for accurate early warning. To address field problems observed in an abandoned goaf of a coal mine in northern China, including temperature anomalies, abnormal CO concentrations at small-mine openings, smoke emissions from surface fissures, and the potential hydraulic or fracture connection between upper and lower goafs, this study develops an intelligent coalfield fire risk early-warning model based on the random forest algorithm. Thermal infrared imaging, isotopic radon measurements, and geological-goaf spatial information were used as the primary data sources. Surface temperature anomalies were extracted from UAV-based thermal infrared images, gas-migration signals along underground fracture pathways were obtained using alpha-cup radon measurements, and spatial-distance features to Jurassic abandoned-goaf boundaries and small-mine openings were quantified. Using expert interpretation results and field-observed anomaly points as labels, a random forest classification model was established to quantitatively classify coalfield fire risk levels in the study area. The results show that thermal anomaly features directly represent surface temperature responses, radon anomaly features effectively reveal concealed fractures and gas-migration pathways, and geological and goaf-related spatial features characterize the controlling conditions for fire development. Fusion of the three types of features substantially improves the stability and interpretability of coalfield fire risk identification. The proposed model provides a scientific basis for delineating temperature anomalies in abandoned goafs, optimizing verification borehole layout, zoning fire prevention and control measures, and ensuring safe longwall panel retreat.References
[1] Nath S, Agarwal S, Pandey G N. Evaluation of Knowledge Gaps in Mathematical Applications of Thermal Image Processing Techniques for Fire Prevention. ACM Computing Surveys, 2017, 50(1): 1–43. DOI: 10.1145/3009967.
[2] Chen Y, Liao S, Qin D.Study on inversion of coal seam temperature in mining area --Pingshuo mining area of Shanxi Province. E3S Web of Conferences, 2020, 165: 03014. DOI: 10.1051/e3sconf/202016503014.
[3] Yan S, Shi K, Li Y, et al. Integration of satellite remote sensing data in underground coal fire detection: A case study of the Fukang region, Xinjiang, China. Frontiers of Earth Science, 2019, 14(1): 1–12. DOI: 10.1007/s11707-019-0757-9.
[4] He X, Yang X, Luo Z, et al. Application of unmanned aerial vehicle (UAV) thermal infrared remote sensing to identify coal fires in the Huojitu coal mine in Shenmu city, China. Scientific Reports, 2020, 10(1). DOI: 10.1038/s41598-020-70964-5.
[5] Zhang B, Xiao F, Jin W. Burnt coal field detection via magnetic exploration. Environmental Earth Sciences, 2023, 82(7). DOI: 10.1007/s12665-023-10843-0.
[6] Ma Z, Qin B, Shi Q, et al. The location analysis and efficient control of hidden coal spontaneous combustion disaster in coal mine goaf: A case study. Process Safety and Environmental Protection, 2024, 184: 66–78. DOI: 10.1016/j.psep.2024.01.054.
[7] Hu H, Xing Z, Chen M. Application of Surface Drilling Grouting in Fire Extinguishing of Small Mine Goaf. In Safety in Coal Mines, 2019.
[8] Duan S, Fang L, Shi Q, et al. Application of Rapid Identification Technology in Shallow Coal Seam Fire Detection. Combustion Science and Technology, 2023, 197(7): 1535–1549. DOI: 10.1080/00102202.2023.2288218.
[9] Zhou B, Wu J, Wang J, et al. Surface-based radon detection to identify spontaneous combustion areas in small abandoned coal mine gobs: Case study of a small coal mine in China. Process Safety and Environmental Protection, 2018, 119: 223–232. DOI: 10.1016/j.psep.2018.08.011.
[10] Zhou W, Wang J, Zhou C, et al. Technology of Detecting Spontaneous Combustion Source in Goaf of Coal Mine by Isotopic Measurement of Polonium. In Safety in Coal Mines, 2019.
[11] Yu B, She J, Liu G, et al. Coal fire identification and state assessment by integrating multitemporal thermal infrared and InSAR remote sensing data: A case study of Midong District, Urumqi, China. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 190: 144–164. DOI: 10.1016/j.isprsjprs.2022.06.007.
[12] Karanam V, Motagh M, Garg S, et al. Multi-sensor remote sensing analysis of coal fire induced land subsidence in Jharia Coalfields, Jharkhand, India. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102439. DOI: 10.1016/j.jag.2021.102439.
[13] Zou J, Zhang R, Zhou F, et al. Hazardous Area Reconstruction and Law Analysis of Coal Spontaneous Combustion and Gas Coupling Disasters in Goaf Based on DEM-CFD. ACS Omega, 2023, 8(2): 2685–2697. DOI: 10.1021/acsomega.2c07236.
[14] Zheng Y, Li S, Xue S, et al. Study on the evolution characteristics of coal spontaneous combustion and gas coupling disaster region in goaf. Fuel, 2023, 349: 128505. DOI: 10.1016/j.fuel.2023.128505.