Bayesian data analysis and modelling linked with machine learning offers a new tool for handling geotechnical data. This book presents recent advancements made by the author in the area of probabilistic geotechnical site characterization. Two types of correlation play central roles in geotechnical site characterization: cross-correlation among soil properties and spatial-correlation in the underground space. The book starts with the introduction of Bayesian notion of probability “degree of belief”, showing that well-known probability axioms can be obtained by Boolean logic and the definition of plausibility function without the use of the notion “relative frequency”. It then reviews probability theories and useful probability models for cross-correlation and spatial correlation. Methods for Bayesian parameter estimation and prediction are also presented, and the use of these methods demonstrated with geotechnical site characterization examples. Bayesian Machine Learning in Geotechnical Site Characterization suits consulting engineers and graduate students in the area.

"Bayesian data analysis and modelling linked with machine learning offers a new tool for handling geotechnical data. Geodata is distinctively multivariate, unique, sparse, incomplete, possibly corrupted, and spatial variable, so conventional methods may deliver unreliable results. The powerful methods can be widely applied, as with site characterization, foundation design, underground stratification, soil property estimation, inverse method, observational method, and liquefaction estimation, and are espcially useful for large and complex projects where cost is a major factor"--

Uncertainty, Modeling, and Decision Making in Geotechnics shows how uncertainty quantification and numerical modeling can complement each other to enhance decision-making in geotechnical practice, filling a critical gap in guiding practitioners to address uncertainties directly. The book helps practitioners acquire a working knowledge of geotechnical risk and reliability methods and guides them to use these methods wisely in conjunction with data and numerical modeling. In particular, it provides guidance on the selection of realistic statistics and a cost-effective, accessible method to address different design objectives, and for different problem settings, and illustrates the value of this to decision-making using realistic examples. Bringing together statistical characterization, reliability analysis, reliability-based design, probabilistic inverse analysis, and physical insights drawn from case studies, this reference guide from an international team of experts offers an excellent resource for state-of-the-practice uncertainty-informed geotechnical design for specialist practitioners and the research community.

To coordinate the contradiction between economic development and climate change, countries all over the world are vigorously developing renewable energy. Among all renewable energy sources, onshore solar energy, hydro energy and wind energy are limited by the land and environment. The marine is rich in various energies, including marine wind energy, wave energy, tidal energy and marine biomass energy, marine oil and mineral resources. In the development of marine energy, various offshore structures are generally adopted and constructed including offshore wind turbines, wave energy power generation devices, offshore oil and gas exploitation platforms, etc. The safety and reliability of these structures are vital for marine (renewable) energy development. In the meanwhile, marine energy development involves multiple disciplines, which are related to marine biology, chemistry, ecology and the environment. The interdisciplinary studies on these topics are also of significance in marine energy development. In addition, human activities (e.g. marine policy, marine transportation planning, environmental management, economic assessment, and culture) influence the development process of marine energy, which also needs to be investigated.

This textbook systematically introduces the theories, methods, and algorithms for geotechnical reliability analysis. There are a lot of illustrative examples in the textbook such that readers can easily grasp the concepts and theories related to geotechnical reliability analysis. A unique feature of the textbook is that computer codes are also provided through carefully designed examples such that the methods and the algorithms described in the textbook can be easily understood. In addition, the computer codes are flexible and can be conveniently extended to analyze different types of realistic problems with little additional efforts.

Model Uncertainties in Foundation Design is unique in the compilation of the largest and the most diverse load test databases to date, covering many foundation types (shallow foundations, spudcans, driven piles, drilled shafts, rock sockets and helical piles) and a wide range of ground conditions (soil to soft rock). All databases with names prefixed by NUS are available upon request. This book presents a comprehensive evaluation of the model factor mean (bias) and coefficient of variation (COV) for ultimate and serviceability limit state based on these databases. These statistics can be used directly for AASHTO LRFD calibration. Besides load test databases, performance databases for other geo-structures and their model factor statistics are provided. Based on this extensive literature survey, a practical three-tier scheme for classifying the model uncertainty of geo-structures according to the model factor mean and COV is proposed. This empirically grounded scheme can underpin the calibration of resistance factors as a function of the degree of understanding – a concept already adopted in the Canadian Highway Bridge Design Code and being considered for the new draft for Eurocode 7 Part 1 (EN 1997-1:202x). The helical pile research in Chapter 7 was recognised by the 2020 ASCE Norman Medal.

This book focuses on the application of machine learning in slope stability assessment. The contents include: overview of machine learning approaches, the mainstream smart in-situ monitoring techniques, the applications of the main machine learning algorithms, including the supervised learning, unsupervised learning, semi- supervised learning, reinforcement learning, deep learning, ensemble learning, etc., in slope engineering and landslide prevention, introduction of the smart in-situ monitoring and slope stability assessment based on two well-documented case histories, the prediction of slope stability using ensemble learning techniques, the application of Long Short-Term Memory Neural Network and Prophet Algorithm in Slope Displacement Prediction, displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks, seismic stability analysis of slopes subjected to water level changes using gradient boosting algorithms, efficient reliability analysis of slopes in spatially variable soils using XGBoost, efficient time-variant reliability analysis of Bazimen landslide in the Three Gorges Reservoir Area using XGBoost and LightGBM algorithms, as well as the future work recommendation.The authors also provided their own thoughts learnt from these applications as well as work ongoing and future recommendations.