Advances in Streamflow Forecasting: From Traditional to Modern Approaches

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 background information and an overview of streamflow forecasting. The book concludes with a suggested way forward, looking ahead to future needs and challenges in further strengthening streamflow forecasting. This book is a vital resource for hydrologists optimizing water resource systems to mitigate the impact of destructive natural disasters, such as floods and droughts. Subsequent chapters describe various parametric stochastic-modeling 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, and much more. Provides the most authoritative outlook on stream forecasting for both flood and drought Covers all available methods of streamflow forecasting methods used in the literature and guides the audience to the best method and tool for them Includes multiple case studies (at least one for every method in each chapter) demonstrating the application of each method INDICE: 1. An Introduction to Streamflow Forecasting Section I. Parametric Methods 2. Auto-Regressive Moving Average (ARMA) Model 3. Auto-Regressive Integrated Moving Average (ARIMA) Model 4. Seasonal Auto-Regressive Integrated Moving Average (SARIMA), Deseasonalized Auto-Regressive Integrated Moving Average (DARMA), Periodic Auto-Regressive Moving Average (PARMA), Fractional Auto-Regressive Integrated Moving Average (FARIMA) 5. Comparison of Parametric Models Section II. Non-Parametric Methods 6. Multiple Linear Regression 7. Thomas-Fiering Model 8. Wavelet Analysis 9. Support Vector Machine (SVM) 10. Genetic Algorithm 11. Artificial Neural Network (ANN) 12. Adaptive Neuro Fuzzy Inference System (ANFIS) 13. Entropy Theory Section III. Hybrid Approaches 14. A Comparison of Stochastic Models with Artificial Neural Network Technique 15. Application of Hybrid Artificial Neural Network (ANN) model for streamflow Prediction 16. Application of Data driven techniques for streamflow forecasting 17. Adaptive neuro fuzzy inference system (ANFIS) to hydrologic time series modelling 18. A Way Forward

• ISBN: 978-0-12-820673-7
• Editorial: Elsevier
• Encuadernacion: Rústica
• Páginas: 450
• Fecha Publicación: 01/06/2021
• Nº Volúmenes: 1
• Idioma: Inglés