Improving predictions of hydrological low-flow indices in ungaged basins using machine learning

Worland, Scott C.; Farmer, William; Kiang, Julie E.

doi:10.1016/j.envsoft.2017.12.021

Cited by 94 publications

(62 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two main ways to apply hydrological signatures in regionalization. The first is to directly perform regionalization of hydrological signatures (especially FDCs) from donor catchments to target catchments, which has been more frequently implemented in the post‐PUB (Atieh, Taylor, Sattar, & Gharabaghi, 2017; Chouaib et al, 2019; Gyawali, Griffis, Watkins, & Fennessey, 2015; Kult, Fry, Gronewold, & Choi, 2014; Ochoa‐Tocachi et al, 2016; Pugliese et al, 2016; Qamar et al, 2016; Viglione et al, 2013; Worland, Farmer, & Kiang, 2018; Zhang et al, 2018). The superiority of regionalizing the hydrological signature is that it can directly characterize the hydrological characteristics in many aspects and scales, but it is particularly important to select the appropriate hydrological signature for specific research (Addor et al, 2018).…”

Section: Hydrological Regionalization Methodsmentioning

confidence: 99%

Regionalization of hydrological modeling for predicting streamflow in ungauged catchments: A comprehensive review

et al. 2020

View full text Add to dashboard Cite

Runoff prediction in ungauged and scarcely gauged catchments is a key research field in surface water hydrology. There have been numerous studies before and since the launch of the predictions in ungauged basins (PUB) initiative by the International Association of Hydrological Sciences in 2003. This study critically reviews and assesses the decadal progress in the regionalization of hydrological modeling, which is the major tool for PUB, from 2000 to 2019. This paper found that the journal publications have noticeably increased in terms of PUB in the past 7 years, and research countries have been expanded dramatically since 2013. The regionalization methods are grouped into three categories including similarity-based, regression-based, and hydrological signature-based. There are more detailed researches focusing on the interdisciplinary and profound improvement of each regionalization method. Namely, tremendous efforts have been made and lots of improvements have been carried out in the parameterization domain for the post-PUB period. However, there is still plenty of room to improve the prediction capability in data-sparse regions (e.g., further verification and proof of multi-modeling adaptation and uncertainties description). This paper also discusses possible research directions in the future, including PUB in a changing environment and better utilization of multi-source remote-sensing information.

show abstract

Section: Hydrological Regionalization Methodsmentioning

confidence: 99%

Regionalization of hydrological modeling for predicting streamflow in ungauged catchments: A comprehensive review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Where the primary objective is to minimise the difference between the MMC solution and observed data (i.e. maximise the predictive performance), without explicitly accounting for model or parameter uncertainty, the use of multiple linear regression (Doblas-Reyes et al, 2005) or machine learning algorithms (Lima et al, 2015;Worland et al, 2018) to 'learn' the optimal set weights to apply to each MMC input model is a popular approach (Marshall et al, 2007). The use of algorithms such as artificial neural networks (ANNs) (Shamseldin et al, 1997;Xiong et al, 2001) or gene expression programming (GEP) ( Barbulescu and Bautu, 2010;Bărbulescu and Băutu, 2009;Fernando et al, 2012) to define non-linear weighting schemes have proven to be particularly effective.…”

Section: Introductionmentioning

confidence: 99%

Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models

Zaherpour

Mount

Gosling

et al. 2019

Environmental Modelling & Software

View full text Add to dashboard Cite

This study presents a novel application of machine learning to deliver optimised, multi-model combinations (MMCs) of Global Hydrological Model (GHM) simulations. We exemplify the approach using runoff simulations from five GHMs across 40 large global catchments. The benchmarked, median performance gain of the MMC solutions is 45% compared to the best performing GHM and exceeds 100% when compared to the EM. The performance gain offered by MMC suggests that future multimodel applications consider reporting MMCs, alongside the EM and intermodal range, to provide endusers of GHM ensembles with a better contextualised estimate of runoff. Importantly, the study highlights the difficulty of interpreting complex, non-linear MMC solutions in physical terms. This indicates that a pragmatic approach to future MMC studies based on machine learning methods is required, in which the allowable solution complexity is carefully constrained.

show abstract

“…Erdal and Karakurt (2013) developed gradient boosted regression trees and ANNs for predicting daily streamflow and found gradient boosted ANNs to have higher performance than the regression tree counterparts. Worland et al (2018) use gradient boosted regression trees to predict annual minimum 7-day streamflow at 224 unregulated sites; performance is found to be competitive with several other types of data-driven models. Zhang et al (2019) use the Online XGBoost gradient boosting algorithm for regression tree models to simulate streamflow and found that it outperformed many other data-driven and lumped hydrological models.…”

Section: Least Squares Boostingmentioning

confidence: 99%

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

Snieder¹,

Abogadil²,

Khan³

2020

Preprint

View full text Add to dashboard Cite

Abstract. Data-driven flow forecasting models, such as Artificial Neural Networks (ANNs), are increasingly used for operational flood warning systems. However, flow distributions are highly imbalanced, resulting in poor prediction accuracy on high flows, both in terms of amplitude and timing error. Resampling and ensemble techniques have shown to improve model performance of imbalanced datasets such as streamflow. In this research, we systematically evaluate and compare three resampling: random undersampling (RUS), random oversampling (ROS), and SMOTER; and four ensemble techniques: randomised weights and biases, bagging, adaptive boosting (AdaBoost), least squares boosting (LSBoost); on their ability to improve high flow prediction accuracy using ANNs. The methods are implemented both independently and in combined, hybrid techniques. While some of these combinations have been explored in the broader machine learning literature, this research contains many of the first instances of these algorithms to address the imbalance problem inherent in flood and high flow forecasting models. Specifically, the implementation of ROS, and new approaches for SMOTER, LSBOOST, and SMOTER-AdaBoost are presented in this research. Data from two Canadian watersheds (the Bow River in Alberta, and the Don River in Ontario), representing distinct hydrological systems, are used as the basis for the comparison of the methods. The models are evaluated on overall performance and on high flows. The results of this research indicate that resampling produces marginal improvements to high flow prediction accuracy, whereas ensemble methods produce more substantial improvements, with or without a resampling method. Compared to simple ANN flow forecast models, the use of ensemble methods is recommended to reduce the amplitude and timing error in highly imbalanced flow datasets.

show abstract

Improving predictions of hydrological low-flow indices in ungaged basins using machine learning

Cited by 94 publications

References 65 publications

Regionalization of hydrological modeling for predicting streamflow in ungauged catchments: A comprehensive review

Regionalization of hydrological modeling for predicting streamflow in ungauged catchments: A comprehensive review

Exploring the value of machine learning for weighted multi-model combination of an ensemble of global hydrological models

Resampling and ensemble techniques for improving ANN-based high streamflow forecast accuracy

Contact Info

Product

Resources

About