Rockburst is a common dynamic geological hazard, severely restricting the development and utilization of underground space and resources. As the depth of excavation and mining increases, rockburst tends to occur frequently. Hence, it is necessary to carry out a study on rockburst prediction. Due to the nonlinear relationship between rockburst and its influencing factors, artificial intelligence was introduced. However, the collected data were typically imbalanced. Single algorithms trained by such data have low recognition for minority classes. In order to handle the problem, this paper employed stacking technique of ensemble learning to establish rockburst prediction models. In total, 246 sets of data were collected. In the preprocessing stage, three data mining techniques including principal component analysis, local outlier factor and expectation maximization algorithm were used for dimension reduction, outlier detection and outlier substitution, respectively. Then, the pre-processed data were split into a training set (75%) and a test set (25%) with stratified sampling. Based on the four classical single intelligent algorithms, namely k-nearest neighbors (KNN), support vector machine (SVM), deep neural network (DNN) and recurrent neural network (RNN), four ensemble models (KNN–RNN, SVM–RNN, DNN–RNN and KNN–SVM–DNN–RNN) were built by stacking technique of ensemble learning. The prediction performance of eight models was evaluated, and the differences between single models and ensemble models were analyzed. Additionally, a sensitivity analysis was conducted, revealing the importance of input variables on the models. Finally, the impact of class imbalance on the prediction accuracy and fitting effect of models was quantitatively discussed. The results showed that stacking technique of ensemble learning provides a new and promising way for rockburst prediction, which exhibits unique advantages especially when using imbalanced data.
The evolution of the East Asian summer monsoon(EASM) during the Holocene has long been of significant interest.Knowledge of past EASM variability not only increases our understanding of monsoon dynamics on a long timescale,but it also provides an environmental and climatic background for research into Chinese cultural development.However,the timing of the EASM maximum remains controversial.The popular concept of an "early Holocene maximum" is mainly based on speleothemδ~(18)O(δ~(18)O_c) records from caves in southern China;however,the interpretation of δ~(18)O_C as a reliable proxy for EASM intensity is being increasingly challenged.The present paper is a critical review of the climatic significance of the δ~(18)O_C record from China.Firstly,we suggest that precipitation in northern China is an appropriate index of EASM intensity,the variation of which clearly indicates a mid-Holocene monsoon maximum.Secondly,an interregional comparison demonstrates that the precipitation record in northern China is quite different from that in southern China on a range of timescales,and is inconsistent with the spatial similarity exhibited by speleothem oxygen isotope records.Furthermore,both modeling and observational data show that the δ~(18)O_C records from southern China indeed reflect changes in precipitation δ~(18)O(δ~(18)O_P) rather than precipitation amount,and therefore that their use as an EASM proxy is inappropriate.Finally,we address several significant monsoon-related issues-including the driving mechanism of the EASM on an orbital timescale,the climatic significance of speleothem oxygen isotopes,and the relationship between atmospheric circulation and precipitation in monsoonal regions. 相似文献
