A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecasting

Abstract

Probabilistic forecasting is receiving growing attention nowadays in a variety of applied fields, including hydrology. Several machine learning concepts and methods are notably relevant towards addressing the major challenges of formalizing and optimizing probabilistic forecasting implementations, as well as the equally important challenge of identifying the most useful ones among these implementations. Nonetheless, practically-oriented reviews focusing on such concepts and methods, and on how these can be effectively exploited in the above-outlined essential endeavour, are currently missing from the probabilistic hydrological forecasting literature. This absence holds despite the pronounced intensification in the research efforts for benefitting from machine learning in this same literature. It also holds despite the substantial relevant progress that has recently emerged, especially in the field of probabilistic hydrological post-processing, which traditionally provides the hydrologists with probabilistic hydrological forecasting implementations. Herein, we aim to fill this specific gap. In our review, we emphasize key ideas and information that can lead to effective popularizations, as such an emphasis can support successful future implementations and further scientific developments. In the same forward-looking direction, we identify open research questions and propose ideas to be explored in the future.

References in corpus (26)

• XGBoost: A Scalable Tree Boosting System
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• To Explain or to Predict?
• Time Series Forecasting With Deep Learning: A Survey
• BART: Bayesian additive regression trees
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• A trans-disciplinary review of deep learning research for water resources scientists
• Explainable Machine Learning for Scientific Insights and Discoveries
• Boosting Algorithms: Regularization, Prediction and Model Fitting
• Using stacking to average Bayesian predictive distributions
• Highly comparative time-series analysis: The empirical structure of time series and their methods
• Highly comparative feature-based time-series classification
• Kaggle forecasting competitions: An overlooked learning opportunity
• Super ensemble learning for daily streamflow forecasting: Large-scale demonstration and comparison with multiple machine learning algorithms
• GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
• Boosting algorithms in energy research: A systematic review
• Distributional Regression Forests for Probabilistic Precipitation Forecasting in Complex Terrain
• Hydrological time series forecasting using simple combinations: Big data testing and investigations on one-year ahead river flow predictability
• Quantification of predictive uncertainty in hydrological modelling by harnessing the wisdom of the crowd: A large-sample experiment at monthly timescale
• FFORMPP: Feature-based forecast model performance prediction
• Quantification of predictive uncertainty in hydrological modelling by harnessing the wisdom of the crowd: Methodology development and investigation using toy models
• Why scoring functions cannot assess tail properties
• Massive feature extraction for explaining and foretelling hydroclimatic time series forecastability at the global scale
• Expectile-based hydrological modelling for uncertainty estimation: Life after mean
• Hydrological post-processing for predicting extreme quantiles
• Marginally-calibrated deep distributional regression