Cited by Enhancing probabilistic hydrological predictions with mixture density Networks: Accounting for heteroscedasticity and Non-Gaussianity

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

Georgia Papacharalampous, Hristos Tyralis

Frontiers in Water, Journal Year: 2022, Volume and Issue: 4

Published: Oct. 5, 2022

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 formalizing optimizing probabilistic implementations, as well equally important challenge identifying most useful ones among these implementations. Nonetheless, practically-oriented reviews focusing on such methods, how can be effectively exploited above-outlined essential endeavour, currently missing from hydrological literature. This absence holds despite pronounced intensification research efforts for benefitting this same It also substantial progress that has recently emerged, especially field post-processing, which traditionally provides hydrologists with Herein, we aim to fill specific gap. In our review, emphasize key ideas information lead effective popularizations, an emphasis support successful future implementations further scientific developments. forward-looking direction, identify open questions propose explored future.

Language: Английский

Citations

Improve streamflow simulations by combining machine learning pre-processing and post-processing DOI

Yuhang Zhang, Aizhong Ye, Jinyang Li

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132904 - 132904

Published: Feb. 1, 2025

Language: Английский

Citations

Deep Huber quantile regression networks DOI

Hristos Tyralis, Georgia Papacharalampous, Nilay Doğulu

et al.

Neural Networks, Journal Year: 2025, Volume and Issue: 187, P. 107364 - 107364

Published: March 5, 2025

Language: Английский

Citations

Estimation of groundwater storage loss using surface–subsurface hydrologic modeling in an irrigated agricultural region DOI

Salam A. Abbas, Ryan T. Bailey, Jeremy T. White

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 11, 2025

Abstract In the Mississippi alluvial plain (MAP) area, demand for groundwater resources from aquifer agricultural irrigation has led to significant reductions in groundwater-level elevation over time. this study, we use hydrologic model SWAT + quantify long-term changes storage within MAP United States, wherein is used extensively irrigation. We apply a linear quantile regression method perform trend analysis wet, dry, and average conditions 1982–2020 period. The uses gwflow module simulate groundwater-surface water interactions physically based spatially distributed manner, with pumping linked field-based demand. Results indicate trends fluxes. wet conditions, decline are noted head (–18.0 mm/yr.) evapotranspiration (–0.7 mm/yr.). Under dry (–28.0 mm/yr.), recharge (–5.5 discharge For decreases include (–20.6 (–6 (–9.3 This underscores significance of local management solutions.

Language: Английский

Citations

A post-processing machine learning framework for bias-correcting National Water Model outputs by accounting for dominant streamflow drivers DOI

Savalan Naser Neisary,

Ryan Johnson, Muddasser Alam

et al.

Environmental Modelling & Software, Journal Year: 2025, Volume and Issue: unknown, P. 106459 - 106459

Published: April 1, 2025

Language: Английский

Citations

Merging Satellite and Gauge-Measured Precipitation Using LightGBM With an Emphasis on Extreme Quantiles DOI

Hristos Tyralis, Georgia Papacharalampous, Nikolaos Doulamis

et al.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2023, Volume and Issue: 16, P. 6969 - 6979

Published: Jan. 1, 2023

Knowing the actual precipitation in space and time is critical hydrological modelling applications, yet spatial coverage with rain gauge stations limited due to economic constraints. Gridded satellite datasets offer an alternative option for estimating by covering uniformly large areas, albeit related estimates are not accurate. To improve estimates, machine learning applied merge gauge-based measurements gridded products. In this context, observed plays role of dependent variable, while data play predictor variables. Random forests dominant algorithm relevant applications. those predictions settings, point (mostly mean or median conditional distribution) variable issued. The aim manuscript solve problem probabilistic prediction emphasis on extreme quantiles interpolation settings. Here we propose, issuing using Light Gradient Boosting Machine (LightGBM). LightGBM a boosting algorithm, highlighted prize-winning entries forecasting competitions. assess LightGBM, contribute large-scale application that includes merging daily contiguous US PERSIANN GPM-IMERG data. We focus probability distribution where outperforms quantile regression (QRF, variant random forests) terms score at quantiles. Our study offers understanding settings learning.

Language: Английский

Citations

A Probabilistic Runoff Prediction Model Based on Improved Long Short-Term Memory and Interval Correction DOI

Shuang Zhu, Maoyu Zhang, Chao Wang

et al.

Journal of Hydrologic Engineering, Journal Year: 2024, Volume and Issue: 29(4)

Published: April 30, 2024

Accurate and reliable runoff prediction is essential for the efficient operation of hydropower systems. This paper presented a probability model that utilizes an enhanced long short-term memory (LSTM) network. The incorporates combination network, quantile regression module interval correction module. proposed LSTM network to effectively capture time-series characteristics data. By incorporating module, allows predictions without need prior assumptions. Furthermore, inclusion helps refine results, leading improved accuracy narrower interval. integration these three modules greatly enhances precision brings estimates closer true distribution. Jinsha River Lancang were selected evaluate performance because availability long-term data, geographical representation, socioeconomic importance. results demonstrate superior compared with other existing models. Moreover, enables obtaining probabilistic appropriate intervals high reliability.

Language: Английский

Citations

An Integrated Approach for Optimizing Streamflow Prediction in Mid-High Latitude Catchments by Employing Terrestrial Ecosystem Modelling and Interpretable Machine Learning DOI

Hao Zhou, Jing Tang, Stefan Olin

et al.

Published: Jan. 1, 2024

Language: Английский

Citations

Combinations of distributional regression algorithms with application in uncertainty estimation of corrected satellite precipitation products DOI

Georgia Papacharalampous, Hristos Tyralis, Nikolaos Doulamis

et al.

Machine Learning with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 100615 - 100615

Published: Dec. 1, 2024

Language: Английский

Citations

Enhancing probabilistic hydrological predictions with mixture density Networks: Accounting for heteroscedasticity and Non-Gaussianity DOI

Dayang Li, Lucy Marshall, Yan Zhou

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 641, P. 131737 - 131737

Published: July 31, 2024

Language: Английский

Citations