"During the last few decades, many environmental and hydrological problems have been represented and studied through data analysis and machine learning models. Machine learning evolves rapidly with new algorithms and new tools. Nowadays, complex problems are analyzed by identifying and explaining patterns and anomalies of measured or simulated data. Understanding hydrological characteristics and subsequently predicting spatiotemporal hydrological events has developed largely. Temporal information is sometimes limited; spatial information, on the other hand, has increased in recent years due to technological advances including the availability of remote sensing data. These developments have motivated new research efforts to include data in model representation and analysis. Also, current trends and variability of hydrological extremes call for novel approaches of spatio-temporal and machine learning analysis to assess, predict, and manage water-related and/or interlinked hazards including the assessment of uncertainties"-- Provided by publisher.