Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?

Bodini, Nicola; Lundquist, Julie K.; Optis, Mike

doi:10.5194/gmd-13-4271-2020

Cited by 16 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A linear regression fit minimizes the error of the dependent variable from the linear fit. This inevitably gives more weight in reducing the errors at higher TKE values than at lower TKE values where the majority of the points were located, as noted by Bonin et al [47] and Bodini et al [50]. Since the TKE values can range two orders of magnitude, this could lead to a biased regression and lower values.…”

Section: Turbulent Kinetic Energy (Tke) Validationmentioning

confidence: 97%

Estimating atmospheric boundary layer turbulence in the marine environment using lidar systems with applications for offshore wind energy

Gurumurthy¹

2021

View full text Add to dashboard Cite

Estimating turbulence in the marine-atmospheric boundary layer is critical to many industrial, commercial and scientific fields, but of particular importance to the wind energy industry. Contributing to both the efficiency of energy extraction and the life-cycle cost of the turbine itself, turbulence in the atmospheric boundary layer is estimated within the wind energy industry as Turbulence Intensity (TI) and more recently by Turbulent Kinetic Energy (TKE). Traditional in-situ methods to measure turbulence are extremely difficult to deploy in the marine environment, resulting in a recent movement to and dependence on remote sensing methods. One type of remote sensing instrument, Doppler lidars, have shown to reliably estimate the wind speed and atmospheric turbulence while being cost effective and easily deployable, and hence are being increasingly utilized as a standard for wind energy assessments. In this thesis, the ability of lidars to measure turbulence up to a height of 200 m above mean sea level in the marine-atmospheric boundary layer was tested using a 7-month data set spanning winter to early summer. Lidar-based TI and TKE were estimated by three methods using observations from a highly validated lidar system and compared under both convective and stable atmospheric stability conditions. Convective periods were found to have higher turbulence at all the heights compared to stable conditions, while mean wind speed and shear were higher during stable conditions. The study period was characterized by generally low turbulent conditions with high turbulence events occurring at timescales of a few days. Mean vertical profiles of TKE were non-uniformly distributed in height during low turbulent conditions. During highly turbulent events, TKE increased more strongly with height. The definition of TI-following the industry or meteorology conventions-had no real effect on the results, and differences between cup or sonic anemometers and lidar TI values were small except at low wind speeds. All the three lidar-based TKE methods tested corresponded closely to independent estimates, and differences between the methods were small relative to the temporal variability of TKE observed at the offshore site.

show abstract

Section: Turbulent Kinetic Energy (Tke) Validationmentioning

confidence: 97%

Estimating atmospheric boundary layer turbulence in the marine environment using lidar systems with applications for offshore wind energy

Gurumurthy¹

2021

View full text Add to dashboard Cite

show abstract

“…Several papers were also recently published on the topic of emulating different parts of NWP models by machine learning [31][32][33][34]. Authors are using either benchmark solutions to provide reliable estimates of examined algorithms, or using observational data from special campaigns to train models on real and accurate data.…”

Section: Atmospheric Physics and Processesmentioning

confidence: 99%

Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives

2022

View full text Add to dashboard Cite

In this paper, we performed an analysis of the 500 most relevant scientific articles published since 2018, concerning machine learning methods in the field of climate and numerical weather prediction using the Google Scholar search engine. The most common topics of interest in the abstracts were identified, and some of them examined in detail: in numerical weather prediction research—photovoltaic and wind energy, atmospheric physics and processes; in climate research—parametrizations, extreme events, and climate change. With the created database, it was also possible to extract the most commonly examined meteorological fields (wind, precipitation, temperature, pressure, and radiation), methods (Deep Learning, Random Forest, Artificial Neural Networks, Support Vector Machine, and XGBoost), and countries (China, USA, Australia, India, and Germany) in these topics. Performing critical reviews of the literature, authors are trying to predict the future research direction of these fields, with the main conclusion being that machine learning methods will be a key feature in future weather forecasting.

show abstract

“…Using a gradient Richardson number is difficult because of the effect of terrain-induced flow speedup over the ridge affecting the shear terms (Menke et al, 2019). Bodini et al (2020) calculated the Obukhov length for Perdigão and found that it was not very powerful in predicting dissipation rate. Despite this, the Obukhov length is still useful for selecting stable and unstable case studies.…”

Section: Overview Of the Perdigão Campaignmentioning

confidence: 99%

Meso- to microscale modeling of atmospheric stability effects on wind turbine wake behavior in complex terrain

et al. 2022

Self Cite

View full text Add to dashboard Cite

Abstract. Terrain-induced flow phenomena modulate wind turbine performance and wake behavior in ways that are not adequately accounted for in typical wind turbine wake and wind plant design models. In this work, we simulate flow over two parallel ridges with a wind turbine on one of the ridges, focusing on conditions observed during the Perdigão field campaign in 2017. Two case studies are selected to be representative of typical flow conditions at the site, including the effects of atmospheric stability: a stable case where a mountain wave occurs (as in ∼ 50 % of the nights observed) and a convective case where a recirculation zone forms in the lee of the ridge with the turbine (as occurred over 50 % of the time with upstream winds normal to the ridgeline). We use the Weather Research and Forecasting Model (WRF), dynamically downscaled from the mesoscale (6.75 km resolution) to microscale large-eddy simulation (LES) at 10 m resolution, where a generalized actuator disk (GAD) wind turbine parameterization is used to simulate turbine wakes. We compare the WRF–LES–GAD model results to data from meteorological towers, lidars, and a tethered lifting system, showing good qualitative and quantitative agreement for both case studies. Significantly, the wind turbine wake shows different amounts of vertical deflection from the terrain and persistence downstream in the two stability regimes. In the stable case, the wake follows the terrain along with the mountain wave and deflects downwards by nearly 100 m below hub height at four rotor diameters downstream. In the convective case, the wake deflects above the recirculation zone over 40 m above hub height at the same downstream distance. Overall, the WRF–LES–GAD model is able to capture the observed behavior of the wind turbine wakes, demonstrating the model's ability to represent wakes over complex terrain for two distinct and representative atmospheric stability classes, and, potentially, to improve wind turbine siting and operation in hilly landscapes.

show abstract

Can machine learning improve the model representation of turbulent kinetic energy dissipation rate in the boundary layer for complex terrain?

Cited by 16 publications

References 43 publications

Estimating atmospheric boundary layer turbulence in the marine environment using lidar systems with applications for offshore wind energy

Estimating atmospheric boundary layer turbulence in the marine environment using lidar systems with applications for offshore wind energy

Machine Learning in Weather Prediction and Climate Analyses—Applications and Perspectives

Meso- to microscale modeling of atmospheric stability effects on wind turbine wake behavior in complex terrain

Contact Info

Product

Resources

About