Advanced Hydroinformatics: Machine Learning and Optimization for Water Resources(78 Special Publications)

Applying machine learning and optimization technologies to water management problems The rapid development of machine learning brings new possibilities for hydroinformatics research and practice with its ability to handle big data sets, identify patterns and anomalies in data, and provide more accurate forecasts. Advanced Hydroinformatics: Machine Learning and Optimization for Water Resources presents both original research and practical examples that demonstrate how machine learning can advance data analytics, accuracy of modeling and forecasting, and knowledge discovery for better water management. Volume highlights include: Overview of the application of artificial intelligence and machine learning techniques in hydroinformatics Advances in modeling hydrological systems Different data analysis methods and models for forecasting water resources New areas of knowledge discovery and optimization based on using machine learning techniques Case studies from North America, South America, the Caribbean, Europe, and Asia The American Geophysical Union promotes discovery in Earth and space science for the benefit of humanity. Its publications disseminate scientific knowledge and provide resources for researchers, students, and professionals.

Table of Contents:
Section I: Introduction to Hydroinformatics Applications 1. Hydroinformatics and Machine Learning (Gerald Corzo – theory on how to build models -> the area of hydroinformatics) a. Clustering, Classification and regresion b. Input variable selection c. Data models (calibration, validation, testing) d. Hyperparameters optimization e. Ensembles and committees 2. Neural networks and deep learning for water resources, applications using python (Gerald Corzo) a. Scikit-learn library b. Visualization through Bokeh c. Hydrological conceptual model d. Optimization e. Unverstainty analysis Section II: Modeling Extremes and Forecasting 3. Wavelet analysis for preprosecing neural network in forecasting flows; case study in Itaipu river basin,  Brasil (Daniel Vazquez -UNESCO Paraguay) 4. Deep learning for forecasting spatiotemporal patterns in Yuna river basin (Dom Rep) (Cecilia Emanueli IHE Delft) 5. Fuzzy Committee models applied to a spatial distributed hydrological models (Mostafa Farrag, University of Postdam) 6. A fuzzy committee model to forecast flows in Salvador (Jose del Valles Leon, Ministry of Salvador) 7. Operational flow forecasting with machine learning (Jacobine, Minister from Namibia ) 8. Flash flood forecasting generalization through a neural network model. (Juan Carlos Ramirez- Univ. Veracruz) Section III: Hydroinformatics for Water resources 9. Neural networks for tracking spatio temporal patterns of critical sources areas in agricultural best management practices; case study in Colombia (Natalia Uribe, IHE Delft) 10. Ensemble Models in  forecasting groundwater levels; (Alessandro Amaranto, University of Nebraska, USA) 11. Tracking extreme drought event using neural events from global hydrological models(Vitali Diaz, IHE Delft)) 12. Using machine learning for bias correction of 3d precipitation objects (Miguel Laverde, TU Delft) 13. Machine learning algorithms applied to simulate natural preventive drought management solutions (Ana Maria Paez, TU Delft) 14. Looking beyond spatial correlation in regional flood frequency analysis: exploring the potential of Generalized Least Squares and Top-kriging (Simeone Persiano, University of Bologna) 15. Analysis and modelling of a 9.3 kyr palaeoflood record: correlations, clustering, and cycle Annette Wit, Germand Center - DZHK)

About the Author :
Gerald A. Corzo Perez, IHE Delft Institute for Water Education, The Netherlands Dimitri P. Solomatine, IHE Delft Institute for Water Education, and Delft University of Technology, The Netherlands