Quantile-Based Hydrological Modelling

Tyralis, Hristos; Papacharalampous, Georgia

doi:10.3390/w13233420

Cited by 20 publications

(8 citation statements)

References 93 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other machine and statistical learning algorithms that could be exploited in a straightforward manner in this regard can be found in Papacharalampous et al [61] (see also the references therein) and fall into the larger category of quantile regression algorithms. Most of these algorithms base their training on the quantile loss (alternatively referred to as the "pinball loss") function, the utilization of which was also proposed by Tyralis and Papacharalampous [62] for converting (even more) interpretable models into probabilistic ones.…”

Section: Discussionmentioning

confidence: 99%

Time Series Features for Supporting Hydrometeorological Explorations and Predictions in Ungauged Locations Using Large Datasets

Papacharalampous

Tyralis

2022

Water

Self Cite

View full text Add to dashboard Cite

Regression-based frameworks for streamflow regionalization are built around catchment attributes that traditionally originate from catchment hydrology, flood frequency analysis and their interplay. In this work, we deviated from this traditional path by formulating and extensively investigating the first regression-based streamflow regionalization frameworks that largely emerge from general-purpose time series features for data science and, more precisely, from a large variety of such features. We focused on 28 features that included (partial) autocorrelation, entropy, temporal variation, seasonality, trend, lumpiness, stability, nonlinearity, linearity, spikiness, curvature and others. We estimated these features for daily temperature, precipitation and streamflow time series from 511 catchments and then merged them within regionalization contexts with traditional topographic, land cover, soil and geologic attributes. Precipitation and temperature features (e.g., the spectral entropy, seasonality strength and lag-1 autocorrelation of the precipitation time series, and the stability and trend strength of the temperature time series) were found to be useful predictors of many streamflow features. The same applies to traditional attributes such as the catchment mean elevation. Relationships between predictor and dependent variables were also revealed, while the spectral entropy, the seasonality strength and several autocorrelation features of the streamflow time series were found to be more regionalizable than others.

show abstract

Section: Discussionmentioning

confidence: 99%

Time Series Features for Supporting Hydrometeorological Explorations and Predictions in Ungauged Locations Using Large Datasets

Papacharalampous

Tyralis

2022

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…Expectile regression with neural networks by implementing the expectile loss function has been proposed by Jiang et al (2017). Huber quantile regression with neural networks has been proposed by Tyralis et al (2023). Quantile regression neural networks and expectile regression neural networks are edge cases of Huber quantile neural networks.…”

Section: Quantile and Expectile Regressionmentioning

confidence: 99%

A review of predictive uncertainty estimation with machine learning

Tyralis,

Papacharalampous

2024

Artif Intell Rev

View full text Add to dashboard Cite

Predictions and forecasts of machine learning models should take the form of probability distributions, aiming to increase the quantity of information communicated to end users. Although applications of probabilistic prediction and forecasting with machine learning models in academia and industry are becoming more frequent, related concepts and methods have not been formalized and structured under a holistic view of the entire field. Here, we review the topic of predictive uncertainty estimation with machine learning algorithms, as well as the related metrics (consistent scoring functions and proper scoring rules) for assessing probabilistic predictions. The review covers a time period spanning from the introduction of early statistical (linear regression and time series models, based on Bayesian statistics or quantile regression) to recent machine learning algorithms (including generalized additive models for location, scale and shape, random forests, boosting and deep learning algorithms) that are more flexible by nature. The review of the progress in the field, expedites our understanding on how to develop new algorithms tailored to users’ needs, since the latest advancements are based on some fundamental concepts applied to more complex algorithms. We conclude by classifying the material and discussing challenges that are becoming a hot topic of research.

show abstract

“…Indeed, more abstract inspirations sourced from this field can also lead to useful practical solutions. Characteristic examples of such inspirations are the concepts of "quantile-based hydrological modeling" (Tyralis and Papacharalampous, 2021b) and "expectile-based hydrological modeling" . These concepts offer the most direct and straightforward probabilistic hydrological forecasting solutions using processbased rainfall-runoff models.…”

Section: Quantile Expectile Distributional and Other Regression Algor...mentioning

confidence: 99%

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

Papacharalampous

Tyralis

2022

Front. Water

Self Cite

View full text Add to dashboard Cite

Probabilistic forecasting is receiving growing attention nowadays in a variety of applied fields, including hydrology. Several machine learning concepts and methods are notably relevant toward 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 endeavor, 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.

show abstract

Quantile-Based Hydrological Modelling

Cited by 20 publications

References 93 publications

Time Series Features for Supporting Hydrometeorological Explorations and Predictions in Ungauged Locations Using Large Datasets

Time Series Features for Supporting Hydrometeorological Explorations and Predictions in Ungauged Locations Using Large Datasets

A review of predictive uncertainty estimation with machine learning

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

Contact Info

Product

Resources

About