Reliable estimates of peak particle velocity (PPV) from blasting-induced vibrations at a construction site play a crucial role in minimizing damage to nearby structures and maximizing blasting efficiency. However, reliably estimating PPV can be challenging due to complex connections between PPV and influential factors such as ground conditions. While many efforts have been made to estimate PPV reliably, discrepancies remain between measured and predicted PPVs. Here, we analyzed various methods for assessing PPV with several key relevant factors and 1191 monitored field blasting records at 50 different open-pit sites across South Korea to minimize the discrepancies. Eight prediction models are used based on artificial neural network, conventional empirical formulas, and multivariable regression analyses. Seven influential factors were selected to develop the prediction models, including three newly included and four already formulated in empirical formulas. The three newly included factors were identified to have a significant influence on PPV, as well as the four existing factors, through a sensitivity analysis. The measured and predicted PPVs were compared to evaluate the performances of prediction models. The assessment of PPVs by an artificial neural network yielded the lowest errors, and site factors, K and m were proposed for preliminary open-pit blasting designs.

The prediction of settlement during tunneling presents multiple challenges, as such settlement is governed by not only the local geology but also construction methods and practices, such as tunnel boring machine (TBM). To avoid undesirable settlement, engineers must predict the settlement under given conditions. The widely used methods are analytical solutions, empirical solutions, and numerical solutions. Analytical or empirical solutions, however, have limitations, which cannot incorporate the major causes of subsidence, such as unexpected geological conditions and TBM operational issues, among which cutterhead pressure and thrust force-related factors are the most influential. In settlement prediction, to utilize the machine data of TBM, two phases of long short-term memory (LSTM) models are devised. The first LSTM model is designed to capture the features affecting surface settlement. The second model is for the prediction of subsidence against the extracted features. One thing to note is that predicted subsidence is the evolution of settlement along TBM drive rather than its maximum value. The proposed deep-learning models are capable of predicting the subsidence of training and test sets with excellent accuracy, anticipating that it could be an effective tool for real-world tunneling and other underground construction projects.