"Migration to urban areas is expected to approach 68% of the world population in 2050, according to UN estimates (Nations, 2018). Maintaining sustainable water distribution networks is imperative for transporting clean water to consumers, thereby ensuring public health. In addition, water distribution networks are essential infrastructures worldwide. Their structural safety is critical to ensure that treated water does not leak into the ground, wasting millions of tax dollars. Understanding the factors that affect the operational performance of a given water distribution system can help prioritize maintenance and predict the approximate service life of the pipelines such that replacement can be appropriately planned. Artificial intelligence (AI) for modeling and predicting the failure of water pipes has become advantageous in recent years. AI and machine learning approaches are fundamental, predictive models that help decision-makers develop strategies that mitigate the risk of failure by labeling pipes requiring immediate repair within a water distribution network. However, the failure process of water distribution pipelines remains ambiguous, and it may occur for ''unknown reasons.''The intellectual contribution of this dissertation is to bridge the gap in the theoretical knowledge between critical factors and the deterioration of water distribution infrastructure. This dissertation also proposes new machine learning paradigms based on ensemble and deep learning to predict the failure of water distribution pipelines under various environmental and climatic conditions. To achieve the objectives of this dissertation, pipe failure data are collected from two municipalities in Canada, the City of London and Sainte-Foy in London and Quebec, respectively. In addition, climate data are amassed from the Environment and Climate Change Canada (ECCC) for the cities mentioned above. This dissertation research uncovers the effects of essential factors affecting the failure prediction of water pipelines. Of these essential factors, important ones to note are air temperature, minimum antecedent precipitation index, and evaporation. The results demonstrate that the failure process depends mainly on the climate conditions of the geographical location of water pipes. Furthermore, the results prove that the proposed approaches can leverage insightful knowledge even with limited exposure to training tasks. The results also demonstrate that the proposed approaches are flexible to limited, high-dimensional, and partially observed data. Moreover, the results show that these prediction methods can complement other statistical and state-of-the-art machine learning models. Lastly, the results validate the potential implementations of the proposed models for decision-making in water distribution networks"--

Applications of Machine Learning in Hydroclimatology is a comprehensive exploration of the transformative potential of machine learning for addressing critical challenges in water resources management. The book explores how artificial intelligence can unravel the complexities of hydrological systems, providing researchers and practitioners with cutting-edge tools to model, predict, and manage these systems with greater precision and effectiveness. It thoroughly examines the modeling of hydrometeorological extremes, such as floods and droughts, which are becoming increasingly difficult to predict due to climate change. By leveraging AI-driven methods to forecast these extremes, the book offers innovative approaches that enhance predictive accuracy. It emphasizes the importance of analyzing non-stationarity and uncertainty in a rapidly evolving climate landscape, illustrating how statistical and frequency analyses can improve hydrological forecasts. Moreover, the book explores the impact of climate change on flood risks, drought occurrences, and reservoir operations, providing insights into how these phenomena affect water resource management. To provide practical solutions, the book includes case studies that showcase effective mitigation measures for water-related challenges. These examples highlight the use of machine learning techniques such as deep learning, reinforcement learning, and statistical downscaling in real-world scenarios. They demonstrate how artificial intelligence can optimize decision-making and resource management while improving our understanding of complex hydrological phenomena. By utilizing machine learning architectures tailored to hydrology, the book presents physics-guided models, data-driven techniques, and hybrid approaches that can be used to address water management issues. Ultimately, Applications of Machine Learning in Hydroclimatology empowers researchers, practitioners, and policymakers to harness machine learning for sustainable water management. It bridges the gap between advanced AI technologies and hydrological science, offering innovative solutions to tackle today's most pressing challenges in water resources.

This Book includes selected papers that has been published in the Water journal Special Issue (SI) on Water Supply and Water Scarcity. Moreover, an overview of the SI is included. The papers selected for publication in the SI include review and research papers on water history, on water management issues under water scarcity regimes, on rainwater harvesting, on water quality and degradation, and on climatic variability impacts on water resources. Overall, the issue identify and highlight the main challenges in water sector, and particularly in management and protection of water resources and in use of alternative (non-conventional) water resources, especially in areas with demographic change and climate vulnerability in order to achieve sustainable and secure water supply. Furthermore, general guidelines and possible solutions for an improved and sophisticated water management system are proposed and discussed, such as the adoption of advanced technological solutions and practices that improve water-use efficiency and the use of alternative water resources, to address the growing environmental and health issues and to reduce the emerging conflicts among water users.

Computers in Earth and Environmental Sciences: Artificial Intelligence and Advanced Technologies in Hazards and Risk Management addresses the need for a comprehensive book that focuses on multi-hazard assessments, natural and manmade hazards, and risk management using new methods and technologies that employ GIS, artificial intelligence, spatial modeling, machine learning tools and meta-heuristic techniques. The book is clearly organized into four parts that cover natural hazards, environmental hazards, advanced tools and technologies in risk management, and future challenges in computer applications to hazards and risk management. Researchers and professionals in Earth and Environmental Science who require the latest technologies and advances in hazards, remote sensing, geosciences, spatial modeling and machine learning will find this book to be an invaluable source of information on the latest tools and technologies available. Covers advanced tools and technologies in risk management of hazards in both the Earth and Environmental Sciences Details the benefits and applications of various technologies to assist researchers in choosing the most appropriate techniques for purpose Expansively covers specific future challenges in the use of computers in Earth and Environmental Science Includes case studies that detail the applications of the discussed technologies down to individual hazards

The Bulletin of the Atomic Scientists is the premier public resource on scientific and technological developments that impact global security. Founded by Manhattan Project Scientists, the Bulletin's iconic "Doomsday Clock" stimulates solutions for a safer world.

The Technical Paper addresses the issue of freshwater. Sealevel rise is dealt with only insofar as it can lead to impacts on freshwater in coastal areas and beyond. Climate, freshwater, biophysical and socio-economic systems are interconnected in complex ways. Hence, a change in any one of these can induce a change in any other. Freshwater-related issues are critical in determining key regional and sectoral vulnerabilities. Therefore, the relationship between climate change and freshwater resources is of primary concern to human society and also has implications for all living species. -- page vii.

"Ensemble methods have been called the most influential development in Data Mining and Machine Learning in the past decade. They combine multiple models into one usually more accurate than the best of its components. Ensembles can provide a critical boost to industrial challenges -- from investment timing to drug discovery, and fraud detection to recommendation systems -- where predictive accuracy is more vital than model interpretability. Ensembles are useful with all modeling algorithms, but this book focuses on decision trees to explain them most clearly. After describing trees and their strengths and weaknesses, the authors provide an overview of regularization -- today understood to be a key reason for the superior performance of modern ensembling algorithms. The book continues with a clear description of two recent developments: Importance Sampling (IS) and Rule Ensembles (RE). IS reveals classic ensemble methods -- bagging, random forests, and boosting -- to be special cases of a single algorithm, thereby showing how to improve their accuracy and speed. REs are linear rule models derived from decision tree ensembles. They are the most interpretable version of ensembles, which is essential to applications such as credit scoring and fault diagnosis. Lastly, the authors explain the paradox of how ensembles achieve greater accuracy on new data despite their (apparently much greater) complexity."--Publisher's website.