About this Research Topic
In this research topic, we would like to solicit articles contributing to the ongoing efforts for improved probabilistic prediction and forecasting in hydrology. This contribution could be made either by presenting original research outputs or by providing detailed literature reviews. We would like to extend a special welcome to articles focusing on the latest machine and statistical learning developments. The same applies to articles presenting detailed comparisons and assessments of methods, and to articles investigating how models from different categories can be merged (e.g., in probabilistic hydrological post-processing contexts) for maximizing the benefits and reducing the risks in probabilistic prediction and forecasting in hydrology.
Overall, we would like to solicit articles that rotate around themes and concepts such as the following:
• Development and detailed assessment of new probabilistic prediction and forecasting methods in various hydrological contexts, including (but not limited to) rainfall, surface water and groundwater modelling.
• Comparisons and large-scale benchmarking of different methods of this specific type.
• Combinations of different types of models, such as process-based, stochastic, machine learning and deep learning models, for obtaining probabilistic predictions and forecasts.
• Ensemble learning methods for obtaining performance improvements in probabilistic hydrological prediction and forecasting.
• Emphasis on extreme events, such as droughts and floods.
• Detailed applications at various temporal resolutions.
• Applications of explainable machine learning in probabilistic hydrological prediction and forecasting.
Keywords: Bayesian, Benchmarking, Extremes, Big Data, Deep Learning, Droughts, Ensemble Learning, Explainable Machine Learning, Hydrological Uncertainty, Machine Learning, Predictability, Predictive Uncertainty, Process-based Models, Statistical Learning, Uncertainty, Water Resources Engineering, Floods
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.