Featured Application This work is intended to provide additional approaches for analyzing and interpreting dam monitoring data.Abstract Pore water pressure (PWP) response is significant for evaluating the earth dams' stability, and PWPs are, therefore, generally monitored. However, due to the soil heterogeneity and its non-linear behavior within earths, the PWP is usually difficult to estimate and predict accurately in order to detect a pathology or anomaly in the behavior of an embankment dam. This study endeavors to tackle this challenge through the application of diverse machine learning (ML) techniques in estimating the PWP within an existing earth dam. The methods employed include random forest (RF) combined with simulated annealing (SA), multilayer perceptron (MLP), standard recurrent neural networks (RNNs), and gated recurrent unit (GRU). The prediction capability of these techniques was gauged using metrics such as the coefficient of determination (R2), mean square error (MSE), and CPU training time. It was found that all the considered ML methods could give satisfactory results for the PWP estimation. Upon comparing these methods within the case study, the findings suggest that, in this study, multilayer perceptron (MLP) gives the most accurate PWP prediction, achieving the highest coefficient of determination (R2 = 0.99) and the lowest mean square error (MSE = 0.0087) metrics. A sensitivity analysis is then presented to evaluate the models' robustness and the hyperparameter's influence on the performance of the prediction model.

The paper summarises a series of research studies aimed at investigating the response of framed structures to tunnelling in coarse-grained soils. The activities were developed with a twofold objective: on the one hand, an extensive experimental campaign of centrifuge tests was designed and carried out in order to obtain a consistent set of data, although for simple geometric configurations of the structure and of the tunnel-to-structure relative position; on the other, attention was paid to the essential elements to be included in the numerical simulations, essentially in terms of tunnel excavation simulation procedures, adopted detail in the schematisation of the structural components and constitutive laws to describe the non-linear soil and structural response. Validation of numerical models, based on experimental results, allowed them to be used to extend the analysis to further configurations and to fully define the modification factors of the maximum angular distortion of the span as a function of the relative soil-structure shear stiffness. In addition to the direct comparison with the centrifuge data, the numerical strategy was also validated against in situ observations carried out over a stretch of the Milan metro line 5. This case study was also used to perform a numerical exercise, through inverse analysis and meta-modelling procedures, to optimize the position of the monitoring sensors for a possible real-time calibration of the soil constitutive and TBM-EPB machine parameters used in the numerical modelling.

Development of digital twins is emerging rapidly in geotechnical engineering, and it often requires real-time updating of numerical models (e.g., finite element model) using multiple sources of monitoring data (e.g., settlement and pore water pressure data). Conventional model updating, or calibration, often involves repeated executions of the numerical model, using monitoring data from a specific source or at limited spatial locations only. This leads to a critical research need of real-time model updating and predictions using a numerical model improved continuously by multi-source monitoring data. To address this need, a physics-informed machine learning method called multi-source sparse dictionary learning (MS-SDL) is proposed in this study. Originated from signal decomposition and compression, MS-SDL utilizes results from a suite of numerical models as basis functions, or dictionary atoms, and employs multi-source monitoring data to select a limited number of important atoms for predicting multiple, spatiotemporally varying geotechnical responses. As monitoring data are collected sequentially, no repeated evaluations of computational numerical models are needed, and an automatic and real-time model calibration is achieved for continuously improving model predictions. A real project in Hong Kong is presented to illustrate the proposed approach. Effect of monitoring data from different sources is also investigated.