Practical Hydroinformatics

Hydroinformatics is an emerging subject that is expected to gather speed, momentum and critical mass throughout the forthcoming decades of the 21st century. This book provides a broad account of numerous advances in that field - a rapidly developing discipline covering the application of information and communication technologies, modelling and computational intelligence in aquatic environments. A systematic survey, classified according to the methods used (neural networks, fuzzy logic and evolutionary optimization, in particular) is offered, together with illustrated practical applications for solving various water-related issues. ...

Includes supplementary material: sn.pub/extras

Contenu
Hydroinformatics: Integrating Data and Models.- Some Future Prospects in Hydroinformatics.- Data-Driven Modelling: Concepts, Approaches and Experiences.- Artificial Neural Network Models.- Neural Network Hydroinformatics: Maintaining Scientific Rigour.- Neural Network Solutions to Flood Estimation at Ungauged Sites.- Rainfall-Runoff Modelling: Integrating Available Data and Modern Techniques.- Dynamic Neural Networks for Nonstationary Hydrological Time Series Modeling.- Visualisation of Hidden Neuron Behaviour in a Neural Network Rainfall-Runoff Model.- Correction of Timing Errors of Artificial Neural Network Rainfall-Runoff Models.- Data-Driven Streamflow Simulation: The Influence of Exogenous Variables and Temporal Resolution.- Groundwater Table Estimation Using MODFLOW and Artificial Neural Networks.- Neural Network Estimation of Suspended Sediment: Potential Pitfalls and Future Directions.- Models Based on Fuzzy Logic.- Fuzzy Logic-Based Approaches in Water Resource System Modelling.- Fuzzy Rule-Based Flood Forecasting.- Development of RainfallRunoff Models Using Mamdani-Type Fuzzy Inference Systems.- Using an Adaptive Neuro-fuzzy Inference System in the Development of a Real-Time Expert System for Flood Forecasting.- Building Decision Support Systems based on Fuzzy Inference.- Global and Evolutionary Optimization.- Global and Evolutionary Optimization for Water Management Problems.- Conditional Estimation of Distributed Hydraulic Conductivity in Groundwater Inverse Modeling: Indicator-Generalized Parameterization and Natural Neighbors.- Fitting Hydrological Models on Multiple Responses Using the Multiobjective Evolutionary Annealing-Simplex Approach.- Evolutionary-based Meta-modelling: The Relevance of Using Approximate Models in Hydroinformatics.- Hydrologic Model Calibration Using Evolutionary Optimisation.- Randomised Search Optimisation Algorithms and Their Application in the Rehabilitation of Urban Drainage Systems.- Neural Network Hydrological Modelling:An Evolutionary Approach.- Emerging Technologies.- Combining Machine Learning and Domain Knowledge in Modular Modelling.- Precipitation Interception Modelling Using Machine Learning Methods The Dragonja River Basin Case Study.- Real-Time Flood Stage Forecasting Using Support Vector Regression.- Learning Bayesian Networks from Deterministic RainfallRunoff Models and Monte Carlo Simulation.- Toward Bridging the Gap Between Data-Driven and Mechanistic Models: Cluster-Based Neural Networks for Hydrologic Processes.- Applications of Soft Computing to Environmental Hydroinformatics with Emphasis on Ecohydraulics Modelling.- Data-Driven Models for Projecting Ocean Temperature Profile from Sea Surface Temperature.- Model Integration.- Uncertainty Propagation in Ensemble Rainfall Prediction Systems used for Operational Real-Time Flood Forecasting.- OpenMI Real Progress Towards Integrated Modelling.- Hydroinformatics The Challenge for Curriculum and Research, and the Social Calibrationof Models.- A New Systems Approach to Flood Management in the Yangtze River, China.- Open Model Integration in Flood Forecasting.