Elsevier Advances in Streamflow Forecasting: From Traditional to Modern Approaches

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. Review Explores various methodological approaches for making streamflow forecasts to optimize water resource systems and mitigate natural disaster impacts From the Back Cover Advances in Streamflow Forecasting: From Traditional to Modern Approaches covers the three major approaches of streamflow forecasting, including traditional methods such as stochastic time-series modeling, data-driven techniques, and modern techniques of hybrid methods. The book starts by providing the background information and overview of streamflow forecasting. Chapters 2-5 describe various parametric stochastic-modelling methods such as auto-regressive moving average (ARMA), auto-regressive integrated moving average (ARIMA), seasonal auto-regressive integrated moving average (SARIMA), de-seasonalized auto-regressive integrated moving average (DARIMA), periodic auto-regressive moving average (PARMA) for simulation and forecasting the streamflow time series. It also includes the comparison of parametric methods to evaluate the best-fitted model for streamflow forecasting. Chapters 6-13 explain the advance stage of development and verification of streamflow forecasting models involving artificial intelligence methods. In this section, brief theoretical details and applications of non-parametric methods such as multiple linear regression, Thomas-Fiering model, wavelet analysis, support vector machine (SVM), genetic algorithm (GA), artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) are illustrated, and comparisons between parametric methods such as stochastic models and non-parametric or artificial intelligence methods are considered .Finally, Chapters 14-17 include the recent hybrid approaches used to improve the forecast accuracy, and to reduce the uncertainties in streamflow forecasting. The book concludes with a suggested way forward, looking ahead to future needs and challenges in further strengthening streamflow forecasting. This boo