Zhongqiang Liu

TL;DR: An overview of some soft computing techniques as well as their applications in underground excavations is presented and a case study is adopted to compare the predictive performances ofsoft computing techniques including eXtreme Gradient Boosting, Multivariate Adaptive Regression Splines, and Support Vector Machine in estimating the maximum lateral wall deflection induced by braced excavation.

TL;DR: Wang et al. as discussed by the authors proposed a dynamic model to predict landslide displacement, based on time series analysis and long short-term memory (LSTM) neural network, which can be used to effectively predict the displacement of step-wise landslides in the Three Gorges Reservoir Area (TGRA), the Baishuihe landslide and Bazimen landslide.

TL;DR: P predictive models for assessing surface settlement caused by EPB tunneling were established based on extreme gradient boosting (XGBoost), artificial neural network, support vector machine, and multivariate adaptive regression spline, demonstrating acceptable accuracy of the model in predicting ground settlement.

TL;DR: In this article, a three-level framework for multi-risk assessment that accounts for possible hazard and risk interactions is proposed, where the first level is a flow chart that guides the user in deciding whether a multi-hazard and risk approach is required.

TL;DR: The results show that the ‘ensemble’ GBRT machine learning model yielded the most promising results for the spatial prediction of shallow landslides, with a 95% probability of landslide detection and 87% prediction efficiency.