“Data-Driven Modeling: Using MATLAB® in Water Resources and Environmental Engineering” provides a systematic account of major concepts and methodologies for data-driven models and presents a unified framework that makes the subject more accessible to and applicable for researchers and practitioners. It integrates important theories and applications of data-driven models and uses them to deal with a wide range of problems in the field of water resources and environmental engineering such as hydrological forecasting, flood analysis, water quality monitoring, regionalizing climatic data, and general function approximation. The book presents the statistical-based models including basic statistical analysis, nonparametric and logistic regression methods, time series analysis and modeling, and support vector machines. It also deals with the analysis and modeling based on artificial intelligence techniques including static and dynamic neural networks, statistical neural networks, fuzzy inference systems, and fuzzy regression. The book also discusses hybrid models as well as multi-model data fusion to wrap up the covered models and techniques. The source files of relatively simple and advanced programs demonstrating how to use the models are presented together with practical advice on how to best apply them. The programs, which have been developed using the MATLAB® unified platform, can be found on extras.springer.com. The main audience of this book includes graduate students in water resources engineering, environmental engineering, agricultural engineering, and natural resources engineering. This book may be adapted for use as a senior undergraduate and graduate textbook by focusing on selected topics. Alternatively, it may also be used as a valuable resource book for practicing engineers, consulting engineers, scientists and others involved in water resources and environmental engineering.

Changing climatic conditions, global warming trends, global population increase, water-related conflicts, and water shortages have resulted in changes in the water cycle, and hydrologic processes which were once thought to be simple are now known to be highly nonlinear. This compels the development of more sophisticated tools for enhanced and intensive water resources management. Data-driven tools have gained in popularity in recent years and have spawned a plethora of applications in water resources. Despite enjoying tremendous success in small-scale studies, there are very few applications to field-scale problems so far because various issues must be understood in order to make data-driven tools more practical to hydrologic applications. In the current research, three problem areas in hydrologic modeling have been identified that limit the applicability of data-driven tools: parameter specification, missing or incomplete data, and data compatibility. Each of these is studied in the present research, and solutions are provided. A new multiobjective calibration procedure in the form of Multiobjective Particle Swarm Optimization (MOPSO) is developed and tested. A solution to the problem of missing data is found through local least square imputation methodology. Furthermore, a downscaling algorithm is developed for the scale reconciliation problem. These tools are examined in various applications such as soil moisture forecasting, streamflow estimation, groundwater level forecasting, and downscaling of remotely sensed soil moisture. The current research only focuses on data-driven tools, and hence all the problems are examined in this same context. At the same time, the tools that are developed might well be appropriate for other modeling applications. This research addresses significant problems in the use of data-driven modeling tools so that they can be more effectively used in water resources management and hydrologic science. The results from the research show that the techniques developed and demonstrated here are sound and can help to remove some of the limitations in the use of data-driven tools, making them more attractive for application in hydrologic sciences.

This book explores a new realm in data-based modeling with applications to hydrology. Pursuing a case study approach, it presents a rigorous evaluation of state-of-the-art input selection methods on the basis of detailed and comprehensive experimentation and comparative studies that employ emerging hybrid techniques for modeling and analysis. Advanced computing offers a range of new options for hydrologic modeling with the help of mathematical and data-based approaches like wavelets, neural networks, fuzzy logic, and support vector machines. Recently machine learning/artificial intelligence techniques have come to be used for time series modeling. However, though initial studies have shown this approach to be effective, there are still concerns about their accuracy and ability to make predictions on a selected input space.

This volume include over 30 chapters, written by experts from around the world. It examines drought and all of the fundamental principles relating to drought and water scarcity. It includes coverage of the causes of drought, occurences, preparations, drought vulnerability assessments, societal implications, and more.

MATLAB® is used in a wide range of geoscientific applications, e.g. for image processing in remote sensing, for creating and processing digital elevation models, and for analyzing time series. This book introduces readers to MATLAB-based data analysis methods used in the geosciences, including basic statistics for univariate, bivariate and multivariate datasets, time-series analysis, signal processing, the analysis of spatial and directional data, and image analysis. The revised and updated Fifth Edition includes seven new sections, and the majority of the chapters have been rewritten and significantly expanded. New sections include error analysis, the problem of classical linear regression of log-transformed data, aligning stratigraphic sequences, the Normalized Difference Vegetation Index, Aitchison’s log-ratio transformation, graphical representation of spherical data, and statistics of spherical data. The book also includes numerous examples demonstrating how MATLAB can be used on datasets from the earth sciences. The supplementary electronic material (available online through SpringerLink) contains recipes that include all the MATLAB commands featured in the book and the sample data.

Data assimilation is a process of fusing data with a model for the singular purpose of estimating unknown variables. It can be used, for example, to predict the evolution of the atmosphere at a given point and time. This book examines data assimilation methods including Kalman filtering, artificial intelligence, neural networks, machine learning, and cognitive computing.

Advances in Streamflow Forecasting: From Traditional to Modern Approaches covers the three major data-driven approaches of streamflow forecasting including traditional approach of statistical and stochastic time-series modelling with their recent developments, stand-alone data-driven approach such as artificial intelligence techniques, and modern hybridized approach where data-driven models are combined with preprocessing methods to improve the forecast accuracy of streamflows and to reduce the forecast uncertainties. This book starts by providing the background information, overview, and advances made in streamflow forecasting. The overview portrays the progress made in the field of streamflow forecasting over the decades. Thereafter, chapters describe theoretical methodology of the different data-driven tools and techniques used for streamflow forecasting along with case studies from different parts of the world. Each chapter provides a flowchart explaining step-by-step methodology followed in applying the data-driven approach in streamflow forecasting. This book addresses challenges in forecasting streamflows by abridging the gaps between theory and practice through amalgamation of theoretical descriptions of the data-driven techniques and systematic demonstration of procedures used in applying the techniques. Language of this book is kept simple to make the readers understand easily about different techniques and make them capable enough to straightforward replicate the approach in other areas of their interest. This book will be vital for hydrologists when optimizing the water resources system, and to mitigate the impact of destructive natural disasters such as floods and droughts by implementing long-term planning (structural and nonstructural measures), and short-term emergency warning. Moreover, this book will guide the readers in choosing an appropriate technique for streamflow forecasting depending upon the given set of conditions. - Contributions from renowned researchers/experts of the subject from all over the world to provide the most authoritative outlook on streamflow forecasting - Provides an excellent overview and advances made in streamflow forecasting over the past more than five decades and covers both traditional and modern data-driven approaches in streamflow forecasting - Includes case studies along with detailed flowcharts demonstrating a systematic application of different data-driven models in streamflow forecasting, which helps understand the step-by-step procedures

This book provides a comprehensive guide on how geographic information systems (GIS) can be used to optimize solar energy resources. A collection of the latest cutting-edge research is presented which seeks to address the most pressing issues faced by policymakers regarding the planning and exploitation of solar energy. Scientifically robust models are developed to guide researchers on identifying optimum sites for the implementation of solar energy projects. Each methodology presented is accompanied by global case studies, ranging from the small islands of Hawaii and Mauritius to larger countries such as India and Spain. This book is primarily targeted to researchers aspiring to unveil and optimize the solar resource potential of their countries for the benefit of a wider audience, ranging from architects, agro-industrialists, climatologists, and energy experts.

The objective of this book is to introduce the basic concepts of big data computing and then to describe the total solution of big data problems using HPCC, an open-source computing platform. The book comprises 15 chapters broken into three parts. The first part, Big Data Technologies, includes introductions to big data concepts and techniques; big data analytics; and visualization and learning techniques. The second part, LexisNexis Risk Solution to Big Data, focuses on specific technologies and techniques developed at LexisNexis to solve critical problems that use big data analytics. It covers the open source High Performance Computing Cluster (HPCC Systems®) platform and its architecture, as well as parallel data languages ECL and KEL, developed to effectively solve big data problems. The third part, Big Data Applications, describes various data intensive applications solved on HPCC Systems. It includes applications such as cyber security, social network analytics including fraud, Ebola spread modeling using big data analytics, unsupervised learning, and image classification. The book is intended for a wide variety of people including researchers, scientists, programmers, engineers, designers, developers, educators, and students. This book can also be beneficial for business managers, entrepreneurs, and investors.