Microseismic Location in Hardrock Metal Mines by Machine Learning Models Based on Hyperparameter Optimization Using Bayesian Optimizer.

In recent years, with the gradual depletion of shallow mineral resources, the exploitation of deep mineral resources has become an inevitable trend. Microseismic monitoring is one of the main methods to solve high stress concentration problems such as rockbursts, roof caving and water inrush in deep mine. An accurate and fast microseismic location method is the basis of microseismic monitoring. At present, machine learning (ML) has become an important auxiliary method in the field of microseismic monitoring due to its powerful feature expression ability. Compared with other microseismic positioning methods, ML can construct a more objective positioning model. This paper uses three ML models including deep neural network (DNN), random forest (RF),and support vector regression (SVR) to construct a microseismic position method to search for the microseismic source. The travel time difference between stations is used as the input of the ML model. Since the number of field data sets is not enough to complete the training of the model, this paper uses a synthetic data set with a specific speed model as the training set and uses the field data set for testing. In order to analyze the location accuracy, we compare them with three traditional microseismic location methods. To improve the positioning performance of ML models, this paper uses a Bayesian optimizer (BO) to adjust their hyperparameters. The experimental results show that the performance of the ML model adjusted by the BO has been significantly improved. The positioning accuracy order of the three ML models is DNN > RF > SVR > traditional location method. The average positioning accuracies of the DNN inside and outside the sensors array are 27.81 m and 145.96 m, respectively. For the model proposed in this paper, the positioning accuracy inside the sensors array is significantly higher than that outside the array, which is similar to the traditional positioning method. In addition, the model has a certain tolerance to the error of the speed model. Highlights: Utilization of machine learning (ML) for accurate and objective microseismic source location. Comparative analysis of three ML models (DNN, RF, SVR) and traditional methods. Enhancement of ML model performance using Bayesian optimizer for hyperparameter tuning. Significant improvement in positioning accuracy with DNN model inside and outside the sensor array. Tolerance to speed model errors in the proposed ML-based microseismic positioning method. [ABSTRACT FROM AUTHOR]