High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning
Abstract
Abstract. Wind turbine applications that leverage nacelle-mounted Doppler lidar are hampered by several sources of uncertainty in the lidar measurement, affecting both bias and random errors. Two problems encountered especially for nacelle-mounted lidar are solid interference due to intersection of the line of sight with solid objects behind, within, or in front of the measurement volume and spectral noise due primarily to limited photon capture. These two uncertainties, especially that due to solid interference, can be reduced with high-fidelity retrieval techniques (i.e., including both quality assurance/quality control and subsequent parameter estimation). Our work compares three such techniques, including conventional thresholding, advanced filtering, and a novel application of supervised machine learning with ensemble neural networks, based on their ability to reduce uncertainty introduced by the two observed nonideal spectral features while keeping data availability high. The approach leverages data from a field experiment involving a continuous-wave (CW) SpinnerLidar from the Technical University of Denmark (DTU) that provided scans of a wide range of flows both unwaked and waked by a field turbine. Independent measurements from an adjacent meteorological tower within the sampling volume permit experimental validation of the instantaneous velocity uncertainty remaining after retrieval that stems from solid interference and strongmore »
- Authors:
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Wind Energy Technologies Office
- OSTI Identifier:
- 1905349
- Alternate Identifier(s):
- OSTI ID: 2311758
- Report Number(s):
- SAND-2023-10538J
Journal ID: ISSN 1867-8548
- Grant/Contract Number:
- NA-0003525; NA0003525
- Resource Type:
- Published Article
- Journal Name:
- Atmospheric Measurement Techniques (Online)
- Additional Journal Information:
- Journal Name: Atmospheric Measurement Techniques (Online) Journal Volume: 15 Journal Issue: 24; Journal ID: ISSN 1867-8548
- Publisher:
- Copernicus GmbH
- Country of Publication:
- Germany
- Language:
- English
- Subject:
- 47 OTHER INSTRUMENTATION
Citation Formats
Brown, Kenneth A., and Herges, Thomas G. High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning. Germany: N. p., 2022.
Web. doi:10.5194/amt-15-7211-2022.
Brown, Kenneth A., & Herges, Thomas G. High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning. Germany. https://doi.org/10.5194/amt-15-7211-2022
Brown, Kenneth A., and Herges, Thomas G. Fri .
"High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning". Germany. https://doi.org/10.5194/amt-15-7211-2022.
@article{osti_1905349,
title = {High-fidelity retrieval from instantaneous line-of-sight returns of nacelle-mounted lidar including supervised machine learning},
author = {Brown, Kenneth A. and Herges, Thomas G.},
abstractNote = {Abstract. Wind turbine applications that leverage nacelle-mounted Doppler lidar are hampered by several sources of uncertainty in the lidar measurement, affecting both bias and random errors. Two problems encountered especially for nacelle-mounted lidar are solid interference due to intersection of the line of sight with solid objects behind, within, or in front of the measurement volume and spectral noise due primarily to limited photon capture. These two uncertainties, especially that due to solid interference, can be reduced with high-fidelity retrieval techniques (i.e., including both quality assurance/quality control and subsequent parameter estimation). Our work compares three such techniques, including conventional thresholding, advanced filtering, and a novel application of supervised machine learning with ensemble neural networks, based on their ability to reduce uncertainty introduced by the two observed nonideal spectral features while keeping data availability high. The approach leverages data from a field experiment involving a continuous-wave (CW) SpinnerLidar from the Technical University of Denmark (DTU) that provided scans of a wide range of flows both unwaked and waked by a field turbine. Independent measurements from an adjacent meteorological tower within the sampling volume permit experimental validation of the instantaneous velocity uncertainty remaining after retrieval that stems from solid interference and strong spectral noise, which is a validation that has not been performed previously. All three methods perform similarly for non-interfered returns, but the advanced filtering and machine learning techniques perform better when solid interference is present, which allows them to produce overall standard deviations of error between 0.2 and 0.3 m s−1, or a 1 %–22 % improvement versus the conventional thresholding technique, over the rotor height for the unwaked cases. Between the two improved techniques, the advanced filtering produces 3.5 % higher overall data availability, while the machine learning offers a faster runtime (i.e., ∼ 1 s to evaluate) that is therefore more commensurate with the requirements of real-time turbine control. The retrieval techniques are described in terms of application to CW lidar, though they are also relevant to pulsed lidar. Previous work by the authors (Brown and Herges, 2020) explored a novel attempt to quantify uncertainty in the output of a high-fidelity lidar retrieval technique using simulated lidar returns; this article provides true uncertainty quantification versus independent measurement and does so for three techniques rather than one.},
doi = {10.5194/amt-15-7211-2022},
journal = {Atmospheric Measurement Techniques (Online)},
number = 24,
volume = 15,
place = {Germany},
year = {Fri Dec 16 00:00:00 EST 2022},
month = {Fri Dec 16 00:00:00 EST 2022}
}
https://doi.org/10.5194/amt-15-7211-2022
Works referenced in this record:
Modelling the spectral shape of continuous-wave lidar measurements in a turbulent wind tunnel
journal, March 2022
- van Dooren, Marijn Floris; Kidambi Sekar, Anantha Padmanabhan; Neuhaus, Lars
- Atmospheric Measurement Techniques, Vol. 15, Issue 5
Flywheel calibration of a continuous-wave coherent Doppler wind lidar
journal, February 2021
- Pedersen, Anders Tegtmeier; Courtney, Michael
- Atmospheric Measurement Techniques, Vol. 14, Issue 2
Towards better uncertainty estimates for turbulence statistics
journal, December 1996
- Benedict, L. H.; Gould, R. D.
- Experiments in Fluids, Vol. 22, Issue 2
Simulation of Coherent Doppler Lidar Performance in the Weak-Signal Regime
journal, June 1996
- Frehlich, Rod
- Journal of Atmospheric and Oceanic Technology, Vol. 13, Issue 3
The epsilon–skew–normal distribution for analyzing near-normal data
journal, February 2000
- Mudholkar, Govind S.; Hutson, Alan D.
- Journal of Statistical Planning and Inference, Vol. 83, Issue 2
Discrete spectral peak estimation in incoherent backscatter heterodyne lidar. I. Spectral accumulation and the Cramer-Rao lower bound
journal, January 1993
- Rye, B. J.; Hardesty, R. M.
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 31, Issue 1
A finite difference approach to despiking in-stationary velocity data - tested on a triple-lidar
journal, September 2016
- Forsting, A. R. Meyer; Troldborg, N.
- Journal of Physics: Conference Series, Vol. 753
Analysis of light detection and ranging wind speed measurements for wind turbine control: Analysis of LIDAR measurements
journal, February 2013
- Simley, Eric; Pao, Lucy Y.; Frehlich, Rod
- Wind Energy, Vol. 17, Issue 3
Lidar profilers in the context of wind energy-a verification procedure for traceable measurements: Lidar profilers in the context of wind energy
journal, December 2011
- Gottschall, J.; Courtney, M. S.; Wagner, R.
- Wind Energy, Vol. 15, Issue 1
Retrieving Winds in the Surface Layer over Land Using an Airborne Doppler Lidar
journal, April 2012
- Godwin, K. S.; De Wekker, S. F. J.; Emmitt, G. D.
- Journal of Atmospheric and Oceanic Technology, Vol. 29, Issue 4
A spinner-integrated wind lidar for enhanced wind turbine control: Spinner-integrated wind lidar for enhanced steering and control
journal, October 2012
- Mikkelsen, T.; Angelou, N.; Hansen, K.
- Wind Energy, Vol. 16, Issue 4
Shot noise adaptive bilateral filter
conference, October 2008
- Phelippeau, Harold; Talbot, Hugues; Akil, Mohamed
- 2008 9th International Conference on Signal Processing
Wind Measurements from Arc Scans with Doppler Wind Lidar
journal, November 2015
- Wang, H.; Barthelmie, R. J.; Clifton, A.
- Journal of Atmospheric and Oceanic Technology, Vol. 32, Issue 11
Quality Control and Flux Sampling Problems for Tower and Aircraft Data
journal, June 1997
- Vickers, Dean; Mahrt, L.
- Journal of Atmospheric and Oceanic Technology, Vol. 14, Issue 3
Lidar arc scan uncertainty reduction through scanning geometry optimization
journal, January 2016
- Wang, Hui; Barthelmie, Rebecca J.; Pryor, Sara C.
- Atmospheric Measurement Techniques, Vol. 9, Issue 4
Grand challenges in the science of wind energy
journal, October 2019
- Veers, Paul; Dykes, Katherine; Lantz, Eric
- Science, Vol. 366, Issue 6464
Representation of coherent structures and turbulence spectra from a virtual SpinnerLidar for future LES wake validation
journal, September 2020
- Brown, Kenneth; Hsieh, Alan; Herges, Thomas
- Journal of Physics: Conference Series, Vol. 1618, Issue 6
A statistical data screening procedure
journal, February 1993
- Hojstrup, J.
- Measurement Science and Technology, Vol. 4, Issue 2
Scopes and Challenges of Dual-Doppler Lidar Wind Measurements—An Error Analysis
journal, September 2013
- Stawiarski, Christina; Träumner, Katja; Knigge, Christoph
- Journal of Atmospheric and Oceanic Technology, Vol. 30, Issue 9
Modelling lidar volume-averaging and its significance to wind turbine wake measurements
journal, May 2017
- Meyer Forsting, A. R.; Troldborg, N.; Borraccino, A.
- Journal of Physics: Conference Series, Vol. 854
Neural Networks and the Bias/Variance Dilemma
journal, January 1992
- Geman, Stuart; Bienenstock, Elie; Doursat, René
- Neural Computation, Vol. 4, Issue 1
SWiFT site atmospheric characterization
report, January 2016
- Kelley, Christopher Lee; Ennis, Brandon Lee
Optimizing Lidars for Wind Turbine Control Applications—Results from the IEA Wind Task 32 Workshop
journal, June 2018
- Simley, Eric; Fürst, Holger; Haizmann, Florian
- Remote Sensing, Vol. 10, Issue 6
A Comparison of Some Error Estimates for Neural Network Models
journal, January 1996
- Tibshirani, Robert
- Neural Computation, Vol. 8, Issue 1
Estimating random errors due to shot noise in backscatter lidar observations
journal, January 2006
- Liu, Zhaoyan; Hunt, William; Vaughan, Mark
- Applied Optics, Vol. 45, Issue 18
Weibull Wind-Speed Distribution Parameters Derived from a Combination of Wind-Lidar and Tall-Mast Measurements Over Land, Coastal and Marine Sites
journal, November 2015
- Gryning, Sven-Erik; Floors, Rogier; Peña, Alfredo
- Boundary-Layer Meteorology, Vol. 159, Issue 2
How much flow information can a turbine-mounted lidar capture?
journal, September 2020
- Sekar, Anantha Padmanabhan Kidambi; Rott, Andreas; van Dooren, Marijn Floris
- Journal of Physics: Conference Series, Vol. 1618, Issue 3
Wind turbine aerodynamic measurements using a scanning lidar
journal, June 2018
- Kelley, C. L.; Herges, T. G.; Martinez, L. A.
- Journal of Physics: Conference Series, Vol. 1037
Residual uncertainty in processed line-of-sight returns from nacelle-mounted lidar due to spectral artifacts
journal, September 2020
- Brown, Kenneth; Herges, Thomas
- Journal of Physics: Conference Series, Vol. 1618
Multimodel validation of single wakes in neutral and stratified atmospheric conditions
journal, July 2020
- Doubrawa, Paula; Quon, Eliot W.; Martinez‐Tossas, Luis A.
- Wind Energy
Comparison of methods to derive radial wind speed from a continuous-wave coherent lidar Doppler spectrum
journal, January 2018
- Held, Dominique P.; Mann, Jakob
- Atmospheric Measurement Techniques, Vol. 11, Issue 11
Dynamic Data Filtering of Long-Range Doppler LiDAR Wind Speed Measurements
journal, June 2017
- Beck, Hauke; Kühn, Martin
- Remote Sensing, Vol. 9, Issue 6
Robust Lidar Data Processing and Quality Control Methods Developed for the SWiFT Wake Steering Experiment
journal, July 2019
- Herges, T. G.; Keyantuo, P.
- Journal of Physics: Conference Series, Vol. 1256
Lidar uncertainty and beam averaging correction
journal, January 2015
- Giyanani, A.; Bierbooms, W.; van Bussel, G.
- Advances in Science and Research, Vol. 12, Issue 1
Hub Height Ocean Winds over the North Sea Observed by the NORSEWInD Lidar Array: Measuring Techniques, Quality Control and Data Management
journal, September 2013
- Hasager, Charlotte; Stein, Detlef; Courtney, Michael
- Remote Sensing, Vol. 5, Issue 9
Testing and comparison of lidars for profile and turbulence measurements in wind energy
journal, May 2008
- Courtney, M.; Wagner, R.; Lindelöw, P.
- IOP Conference Series: Earth and Environmental Science, Vol. 1
Scanning Lidar Spatial Calibration and Alignment Method for Wind Turbine Wake Characterization
conference, January 2017
- Herges, Thomas G.; Maniaci, David C.; Naughton, Brian
- 35th Wind Energy Symposium
Understanding Robust and Exploratory Data Analysis.
journal, September 1984
- Stuart, Michael; Hoaglin, David C.; Mosteller, Frederick
- The Statistician, Vol. 33, Issue 3
Evaluation of three lidar scanning strategies for turbulence measurements
journal, January 2016
- Newman, Jennifer F.; Klein, Petra M.; Wharton, Sonia
- Atmospheric Measurement Techniques, Vol. 9, Issue 5
High-fidelity wind farm simulation methodology with experimental validation
journal, November 2021
- Hsieh, Alan S.; Brown, Kenneth A.; deVelder, Nathaniel B.
- Journal of Wind Engineering and Industrial Aerodynamics, Vol. 218
Retrieving wind statistics from average spectrum of continuous-wave lidar
journal, January 2013
- Branlard, E.; Pedersen, A. T.; Mann, J.
- Atmospheric Measurement Techniques, Vol. 6, Issue 7
Turbulence characterization from a forward-looking nacelle lidar
journal, March 2017
- Peña, Alfredo; Mann, Jakob; Dimitrov, Nikolay
- Wind Energy Science, Vol. 2, Issue 1
Wind lidar evaluation at the Danish wind test site in Høvsøre
journal, January 2006
- Smith, David A.; Harris, Michael; Coffey, Adrian S.
- Wind Energy, Vol. 9, Issue 1-2
Evaluation of Wind Speed Retrieval from Continuous-Wave Lidar Measurements of a Wind Turbine Wake Using Virtual Lidar Techniques
journal, July 2019
- Debnath, M.; Doubrawa, P.; Herges, T.
- Journal of Physics: Conference Series, Vol. 1256