Approximation in scour depth around spur dikes using novel hybrid ensemble data-driven model DOI Creative Commons
Balraj Singh,

Vijay K. Minocha

Water Science & Technology, Год журнала: 2024, Номер 89(4), С. 962 - 975

Опубликована: Янв. 29, 2024

Abstract The scouring process near spur dikes poses a threat to riverbank stability, making it crucial for river engineering accurately calculate the maximum scour depth. However, determining depth has been challenging due intricacy of phenomena surrounding these structures. This research introduces reliable ensemble data-driven model by hybridizing random tree (RT) using additive regression (AR), bagging (B), and subspace (RSS) predicting depths around dikes. A database 154 experimental observations was collected from literature, with 103 51 used training testing subsets, respectively. dimensionless analysis performed on dataset, selecting four variables as input (v/vs, y/l, l/d50, Fd50) ds/l response variables. performance comparison demonstrates that B_AR_RT better coefficient determination (R2) 0.9693, root mean square error (RMSE) 0.1305, Nash–Sutcliffe efficiency (NSE) 0.9692. Finally, best hybrid done previous studies, sensitivity is determine most influential parameter

Язык: Английский

Global wind energy resources decline under climate change DOI Creative Commons
A. Martinez, G. Iglesias

Energy, Год журнала: 2023, Номер 288, С. 129765 - 129765

Опубликована: Ноя. 28, 2023

Wind energy is poised to play a major role in the transition. The objective of this work investigate effects climate change on global wind resources. For purpose, multi-model ensemble constructed with selected Global Climate Models. considered through most recent scenarios, Shared Socioeconomic Pathways. We find significant decline resources by 2100 relative current levels. particularly evident mid-latitudes Northern Hemisphere – heavily populated regions where it matters especially, given need for renewable production increase substantially decarbonise supply. Exceptions do exist, but tropical and polar regions, far less populated. Depending climate-change scenario region, changes may exceed 30 % average power density values. Additionally, we uncover variability regardless scenario, which be expected affect its integration into electricity networks. Recognising these important planning transition and, more specifically, contribution energy.

Язык: Английский

Процитировано

63

A new perspective of wind speed forecasting: Multi-objective and model selection-based ensemble interval-valued wind speed forecasting system DOI Open Access
Hao Yan, Xiaodi Wang, Jianzhou Wang

и другие.

Energy Conversion and Management, Год журнала: 2023, Номер 299, С. 117868 - 117868

Опубликована: Ноя. 16, 2023

Язык: Английский

Процитировано

26

Future global offshore wind energy under climate change and advanced wind turbine technology DOI Creative Commons
Christopher Jung, Leon Sander, Dirk Schindler

и другие.

Energy Conversion and Management, Год журнала: 2024, Номер 321, С. 119075 - 119075

Опубликована: Сен. 21, 2024

Язык: Английский

Процитировано

13

Machine learning and statistical approaches for wind speed estimation at partially sampled and unsampled locations; review and open questions DOI Creative Commons
Freddy Houndekindo, Taha B. M. J. Ouarda

Energy Conversion and Management, Год журнала: 2025, Номер 327, С. 119555 - 119555

Опубликована: Янв. 27, 2025

Язык: Английский

Процитировано

2

Introducing new morphometric parameters to improve urban canopy air flow modeling: A CFD to machine-learning study in real urban environments DOI Creative Commons

Jonas Wehrle,

Christopher Jung,

Marco G. Giometto

и другие.

Urban Climate, Год журнала: 2024, Номер 58, С. 102173 - 102173

Опубликована: Окт. 28, 2024

Язык: Английский

Процитировано

4

LSTM and Transformer-based framework for bias correction of ERA5 hourly wind speeds DOI Creative Commons
Freddy Houndekindo, Taha B. M. J. Ouarda

Energy, Год журнала: 2025, Номер unknown, С. 136498 - 136498

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0

Assessing the Performance of Regional Climate Model Wind Speeds Over Canada DOI Creative Commons
M. G. Morris, Emilia Diaconescu

International Journal of Climatology, Год журнала: 2025, Номер unknown

Опубликована: Май 21, 2025

ABSTRACT Human‐induced climate change is reshaping wind patterns across Canada, posing significant challenges for sectors such as energy and infrastructure planning. This study assesses the capability of regional models (RCMs) in simulating near‐surface speed (WS) Canada by analysing outputs from various RCM ensembles, which downscale CMIP5 global model (GCM) output, including NA‐CORDEX multi‐model ensemble (at 0.22° resolution) CanRCM4 single‐model large 0.44° resolution). These are compared against observational data, two reanalysis data sets (ERA5 AgERA5), GCM ensembles CMIP6. The evaluation examines models' ability to replicate historical WS distributions, biases mean extreme WS, trends temporal variability. findings reveal that, despite higher spatial resolution RCMs, their added value over limited, raising concerns about reliability RCM‐derived projections services without further bias adjustment or statistical downscaling. inability both RCMs GCMs accurately simulate diminishes confidence future projections, potentially leading inadequate risk assessments insufficient preparation impacts on vital like infrastructure.

Язык: Английский

Процитировано

0

Future changes of global Annual and Seasonal Wind-Energy Production in CMIP6 projections considering air density variation DOI Creative Commons
Ganix Esnaola, Alain Ulazia, Jon Sáenz

и другие.

Energy, Год журнала: 2024, Номер 307, С. 132706 - 132706

Опубликована: Авг. 6, 2024

This study investigates the effects of climate change on future global wind-energy production, one main pillars decarbonization strategies, including two generally disregarded aspects: sub-daily variability and variable air density. Estimation production by turbines remains almost unexplored for last generation scenarios, that is, Shared Socioeconomic Pathways (SSPs), as previous evaluations have mostly focused Wind Power Density (WPD). A complete view changes in resources was presented, wind, density, WPD Annual/Seasonal Energy Production (AEP/SEP) statistically significant four different SSPs large Multi-model Ensembles. Air density decreases 1%–4% all SSPs, over seasons everywhere modulating wind negatively. Changes AEP/SEP were comparable, with wider areas affected stronger expected former. In most optimistic SSP they range from 5% to 25%, 45% or higher pessimistic. locations, specially oceans, energy is decrease remain unaltered; however, increased are Arctic, Southern Ocean, other narrower areas, such Bay Guinea southern Brazil.

Язык: Английский

Процитировано

3

Mapping future offshore wind resources in the South China Sea under climate change by regional climate modeling DOI
Junyi He, Pak Wai Chan, Q.S. Li

и другие.

Renewable and Sustainable Energy Reviews, Год журнала: 2023, Номер 188, С. 113865 - 113865

Опубликована: Окт. 12, 2023

Язык: Английский

Процитировано

6

Approximation in scour depth around spur dikes using novel hybrid ensemble data-driven model DOI Creative Commons
Balraj Singh,

Vijay K. Minocha

Water Science & Technology, Год журнала: 2024, Номер 89(4), С. 962 - 975

Опубликована: Янв. 29, 2024

Abstract The scouring process near spur dikes poses a threat to riverbank stability, making it crucial for river engineering accurately calculate the maximum scour depth. However, determining depth has been challenging due intricacy of phenomena surrounding these structures. This research introduces reliable ensemble data-driven model by hybridizing random tree (RT) using additive regression (AR), bagging (B), and subspace (RSS) predicting depths around dikes. A database 154 experimental observations was collected from literature, with 103 51 used training testing subsets, respectively. dimensionless analysis performed on dataset, selecting four variables as input (v/vs, y/l, l/d50, Fd50) ds/l response variables. performance comparison demonstrates that B_AR_RT better coefficient determination (R2) 0.9693, root mean square error (RMSE) 0.1305, Nash–Sutcliffe efficiency (NSE) 0.9692. Finally, best hybrid done previous studies, sensitivity is determine most influential parameter

Язык: Английский

Процитировано

0