Abstract: Deep coal mining can trigger microseismic(MS)events, which threaten the personal safety of workers and damage infrastructure, so quantitative prediction of the time, energy, and location(TEL)of MS events is crucial for the prevention of microseismic events.A method of applying spatio-temporal graph convolutional network(STGCN)to predict the TEL of MS events induced by deep coal energy mining is described.The neighbor matrix of sensor network is determined by the distance between MS sensors, the sensor network graph is constructed, and the spatio-temporal details in the graph are extracted using the GCN,and the model is examined based on the on-site MS monitoring data.The results show that the cosine similarity(C)is above 0.90 and the mean relative error(MRE)is below 0.08,and the model has a good prediction effect on the TEL of MS events, which is crucial for ensuring the safety and operational efficiency of deep coal mining.