Extracting and Predicting Rock Mechanical Behavior Based on Microseismic Spatio-temporal Response in an Ultra-thick Coal Seam Mine

A thorough excavation of the deep ultra-thick mines is highly challenging in rock engineering, which mainly depends on the rheological properties of coal-rock mass, high-stress concentrations, and complex geological conditions. Under heterogeneous settings, a detailed understanding of microseismic (MS) spatio-temporal response to rock mechanical behavior is essential for the efficient and safe-yield of deep ultra-thick mines. This paper utilizes real-time passive seismological data of 36 months in an ultra-thick coal mine through LLTCC mining to quantify the coal-rock mass mechanical behavior. In the post-processing of geophysical data, Power Spectral Density (PSD) was performed and the MS source parameters were computed containing over 18,000 events. The events were classified into different energy-levels to evaluate the increased-pressure rock mass. The Gaussian results reveal that the distribution of MS events coincides with the increased rock pressure. The high energy events (>= 50,000 J) accounted for 57.93% of the microseismic-induced earthquakes. Moreover, the cloud energy density maps were obtained to identify the zones of high-stress concentration and enhanced seismicity. It is inferred that the overburden pressure and intense fracturing developed the high-stress concentration zones during excavation. Furthermore, the temporal parameters computed from MS data show that sharp-rise and sharp-drop variation can be regarded as early warning indicators for increased rock pressure. High deviation in energy and frequency also evidenced the increased rock pressure and micro-fractures to macro-fracture development. Based on these precursory parameters, a comprehensive early warning method was proposed. Besides, 3D visualization of the fracturing process and identification of new faults assisted in the accurate evaluation of the ultra-thick mine. Several risk zones were identified based on the seismic energy and fractures correlation. Finally, with the help of a deep learning LSTM approach, a prominent peak in time-series data is predicted that defines the increased rock pressure and further characterizes the coal-rock mechanical response. Compared with the existing studies, our integrated geophysical and mine engineering workflow can provide accurate insights to depict the rock mass mechanical behavior of the deep mines as an aid for disaster prediction and early warning.