Using an Artificial Neural Network to Improve Operational Wind Prediction in a Small Unresolved Valley

Sinclair Chinyoka aMeteorology and Air Quality Section, Wageningen University, Wageningen, Netherlands

Search for other papers by Sinclair Chinyoka in
Current site
Google Scholar
PubMed
Close
https://orcid.org/0000-0002-5922-8179
,
Thierry Hedde bCEA, DES, IRESNE, DTN Laboratory for Environmental Transfer Modeling, Cadarache, Saint-Paul-lés-Durance, France

Search for other papers by Thierry Hedde in
Current site
Google Scholar
PubMed
Close
, and
Gert-Jan Steeneveld aMeteorology and Air Quality Section, Wageningen University, Wageningen, Netherlands

Search for other papers by Gert-Jan Steeneveld in
Current site
Google Scholar
PubMed
Close
Restricted access

We are aware of a technical issue preventing figures and tables from showing in some newly published articles in the full-text HTML view.
While we are resolving the problem, please use the online PDF version of these articles to view figures and tables.

Abstract

This study improves surface wind predictions in an unresolved valley using an artificial neural network (ANN). Forecasting winds in complex terrain with a mesoscale model is challenging. This study assesses the quality of 3-km wind forecasts by the Weather Research and Forecasting (WRF) Model and the potential of postprocessing by an ANN within the 1–2-km-wide Cadarache valley in southeast France. Operational wind forecasts for 110 m above ground level and the near-surface vertical potential temperature gradient with a lead time of 24–48 h were used as ANN input. Observed horizontal wind components at 10 m within the valley were used as targets during ANN training. We use the directional accuracy (DACC45, wind direction error ≤ 45°) and mean absolute error to evaluate the WRF direct model output and the ANN results. By postprocessing, the score for DACC45 improves from 56% in the WRF direct model output to 79% after applying the ANN. Furthermore, the ANN performed well during the day and night, but poorly during the morning and afternoon transitions. The ANN improves the DACC45 at 10 m even for poor WRF forecasts (direction bias ≥ 45°) from 42% to 72%. A shorter lead time and finer grid spacing (1 km) showed negligible impact, which suggests that a 3-km grid spacing and a 24–48-h lead time is effective and relatively cheap to apply. We find that WRF performs well in near-neutral conditions and poorly in other atmospheric stability conditions. The ANN posttreatment consistently improves the wind forecast for all stability classes to a DACC45 of about 80%. The study demonstrates the ability to improve Cadarache valley wind forecasts using an ANN as postprocessing for WRF daily forecasts.

© 2021 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Gert-Jan Steeneveld, Gert-Jan.Steeneveld@wur.nl

Abstract

This study improves surface wind predictions in an unresolved valley using an artificial neural network (ANN). Forecasting winds in complex terrain with a mesoscale model is challenging. This study assesses the quality of 3-km wind forecasts by the Weather Research and Forecasting (WRF) Model and the potential of postprocessing by an ANN within the 1–2-km-wide Cadarache valley in southeast France. Operational wind forecasts for 110 m above ground level and the near-surface vertical potential temperature gradient with a lead time of 24–48 h were used as ANN input. Observed horizontal wind components at 10 m within the valley were used as targets during ANN training. We use the directional accuracy (DACC45, wind direction error ≤ 45°) and mean absolute error to evaluate the WRF direct model output and the ANN results. By postprocessing, the score for DACC45 improves from 56% in the WRF direct model output to 79% after applying the ANN. Furthermore, the ANN performed well during the day and night, but poorly during the morning and afternoon transitions. The ANN improves the DACC45 at 10 m even for poor WRF forecasts (direction bias ≥ 45°) from 42% to 72%. A shorter lead time and finer grid spacing (1 km) showed negligible impact, which suggests that a 3-km grid spacing and a 24–48-h lead time is effective and relatively cheap to apply. We find that WRF performs well in near-neutral conditions and poorly in other atmospheric stability conditions. The ANN posttreatment consistently improves the wind forecast for all stability classes to a DACC45 of about 80%. The study demonstrates the ability to improve Cadarache valley wind forecasts using an ANN as postprocessing for WRF daily forecasts.

© 2021 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Gert-Jan Steeneveld, Gert-Jan.Steeneveld@wur.nl
Save
  • Abadi, M., and Coauthors, 2015: TensorFlow: Large-scale machine learning on heterogeneous systems. TensorFlow, accessed 5 January 2021, http://tensorflow.org/.

  • Barlow, J., and Coauthors, 2017: Developing a research strategy to better understand, observe, and simulate urban atmospheric processes at kilometer to subkilometer scales. Bull. Amer. Meteor. Soc., 98, ES261ES264, https://doi.org/10.1175/BAMS-D-17-0106.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bastin, S., P. Drobinski, A. Dabas, P. Delville, O. Reitebuch, and C. Werner, 2005: Impact of the Rhône and Durance valleys on sea-breeze circulation in the Marseille area. Atmos. Res., 74, 303328, https://doi.org/10.1016/j.atmosres.2004.04.014.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bauer, H.-S., S. K. Muppa, V. Wulfmeyer, A. Behrendt, K. Warrach-Sagi, and F. Späth, 2020: Multi-nested WRF simulations for studying planetary boundary layer processes on the turbulence-permitting scale in a realistic mesoscale environment. Tellus, 72A, 128, https://doi.org/10.1080/16000870.2020.1761740.

    • Search Google Scholar
    • Export Citation
  • Benjamin, S., J. M. Brown, G. Manikin, and G. Mann, 2007: The RTMA background—Hourly downscaling of RUC data to 5-km detail. Proc. 22nd Conf. on Weather Analysis and Forecasting/18th Conf. on Numerical Weather Prediction, Park City, UT, Amer. Meteor. Soc., 4A.6, http://ams.confex.com/ams/pdfpapers/124825.pdf.

  • Bergstra, J., and Y. Bengio, 2012: Random search for hyper-parameter optimization. J. Mach. Learn. Res., 13, 281305.

  • Berthou, S., and Coauthors, 2016: Influence of submonthly air–sea coupling on heavy precipitation events in the western Mediterranean basin. Quart. J. Roy. Meteor. Soc., 142, 453471, https://doi.org/10.1002/qj.2717.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bilgili, M., B. Sahin, and A. Yasar, 2007: Application of artificial neural networks for the wind speed prediction of target station using reference stations data. Renew. Energy, 32, 23502360, https://doi.org/10.1016/j.renene.2006.12.001.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bosveld, F., and Coauthors, 2014: The third GABLS intercomparison case for evaluation studies of boundary-layer models. Part B: Results and process understanding. Bound.-Layer Meteor., 152, 157187, https://doi.org/10.1007/s10546-014-9919-1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Chinta, S., and C. Balaji, 2020: Calibration of WRF model parameters using multiobjective adaptive surrogate model-based optimization to improve the prediction of the Indian summer monsoon. Climate Dyn., 55, 631650, https://doi.org/10.1007/s00382-020-05288-1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Chollet, F., and Coauthors, 2015: Keras. GitHub, accessed 11 December 2020, https://github.com/fchollet/keras.

  • Cros, B., and Coauthors, 2004: The ESCOMPTE program: An overview. Atmos. Res., 69, 241279, https://doi.org/10.1016/j.atmosres.2003.05.001.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • De Bode, M., P. Roubin, T. Hedde, and P. Durand, 2020: High-resolution simulations over a sub-kilometre scale valley during stable night conditions. 22nd EGU General Assembly 2020, online event, SAO/NASA Astrophysics Data System, https://ui.adsabs.harvard.edu/abs/2020EGUGA..22.4751D/abstract.

    • Crossref
    • Export Citation
  • Duine, G.-J., T. Hedde, P. Roubin, and P. Durand, 2016: A simple method based on routine observations to nowcast down-valley flows in shallow, narrow valleys. J. Appl. Meteor. Climatol., 55, 14971511, https://doi.org/10.1175/JAMC-D-15-0274.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Duine, G.-J., T. Hedde, P. Roubin, P. Durand, M. Lothon, F. Lohou, P. Augustin, and M. Fourmentin, 2017: Characterization of valley flows within two confluent valleys under stable conditions: Observations from the KASCADE field experiment. Quart. J. Roy. Meteor. Soc., 143, 18861902, https://doi.org/10.1002/qj.3049.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dupuy, F., 2018: Amélioration de la connaissance et de la prévision des vents de vallée en conditions stables: Expérimentation et modélisation statistique avec réseau de neurones artificiels. Ph.D. dissertation, Université Toulouse 3-Paul Sabatier, 208 pp.

  • Dupuy, F., G.-J. Duine, P. Durand, T. Hedde, P. Roubin, and E. Pardyjak, 2019: Local-scale valley wind retrieval using an artificial neural network applied to routine weather observations. J. Appl. Meteor. Climatol., 58, 10071022, https://doi.org/10.1175/JAMC-D-18-0175.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Dupuy, F., G.-J. Duine, P. Durand, T. Hedde, E. Pardyjak, and P. Roubin, 2021: Valley winds at the local scale: Correcting routine weather forecast using artificial neural networks. Atmosphere, 12, 128, https://doi.org/10.3390/atmos12020128.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Durán, P., S. Basu, C. Meißner, and M. S. Adaramola, 2020: Automated classification of simulated wind field patterns from multiphysics ensemble forecasts. Wind Energy, 23, 898914, https://doi.org/10.1002/we.2462.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Efron, B., 1992: Bootstrap methods: Another look at the jackknife. Breakthroughs in Statistics, S. Kotz and N. L. Johnson, Eds., Springer, 569–593, https://doi.org/10.1007/978-1-4612-4380-9_41.

    • Crossref
    • Export Citation
  • Gardner, M., and S. Dorling, 1998: Artificial neural networks (the multilayer perceptron)—A review of applications in the atmospheric sciences. Atmos. Environ., 32, 26272636, https://doi.org/10.1016/S1352-2310(97)00447-0.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Goodarzi, L., M. E. Banihabib, and A. Roozbahani, 2019: A decision-making model for flood warning system based on ensemble forecasts. J. Hydrol., 573, 207219, https://doi.org/10.1016/j.jhydrol.2019.03.040.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Haiden, T., A. Kann, C. Wittmann, G. Pistotnik, B. Bica, and C. Gruber, 2011: The Integrated Nowcasting through Comprehensive Analysis (INCA) system and its validation over the eastern Alpine region. Wea. Forecasting, 26, 166183, https://doi.org/10.1175/2010WAF2222451.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • He, K., X. Zhang, S. Ren, and J. Sun, 2015: Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. 2015 IEEE Int. Conf. on Computer Vision (ICCV), Santiago, Chile, Institute of Electrical and Electronics Engineers, 1026–1034, https://doi.org/10.1109/ICCV.2015.123.

    • Crossref
    • Export Citation
  • Hoang, P., V. Bourdin, Q. Liu, G. Caruso, and V. Archambault, 2014: Coupling optical and thermal models to accurately predict PV panel electricity production. Sol. Energy Mater. Sol. Cells, 125, 325338, https://doi.org/10.1016/j.solmat.2013.11.032.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Holtslag, A. A. M., and Coauthors, 2013: Stable atmospheric boundary layers and diurnal cycles: Challenges for weather and climate models. Bull. Amer. Meteor. Soc., 94, 16911706, https://doi.org/10.1175/BAMS-D-11-00187.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hong, S.-Y., K.-S. Lim, J.-H. Kim, J.-J. Lim, and J. Dudhia, 2006: WRF Single-Moment 6-Class Microphysics Scheme (WSM6). Asia-Pac. J. Atmos. Sci., 42, 129151.

    • Search Google Scholar
    • Export Citation
  • Jiménez, P. A., J. Dudhia, J. F. González-Rouco, J. P. Montávez, E. García-Bustamante, J. Navarro, J. Vilà-Guerau de Arellano, and A. Muñoz-Roldán, 2013: An evaluation of WRF’s ability to reproduce the surface wind over complex terrain based on typical circulation patterns. J. Geophys. Res., 118, 76517669, https://doi.org/10.1002/jgrd.50585.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kain, J. S., 2004: The Kain–Fritsch convective parameterization: An update. J. Appl. Meteor., 43, 170181, https://doi.org/10.1175/1520-0450(2004)043<0170:TKCPAU>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kalverla, P. C., G.-J. Duine, G.-J. Steeneveld, and T. Hedde, 2016: Evaluation of the Weather Research and Forecasting Model in the Durance valley complex terrain during the KASCADE field campaign. J. Appl. Meteor. Climatol., 55, 861882, https://doi.org/10.1175/JAMC-D-15-0258.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kim, K. H., S.-B. Lee, D. Woo, and G.-N. Bae, 2015: Influence of wind direction and speed on the transport of particle-bound PAHS in a roadway environment. Atmos. Pollut. Res., 6, 10241034, https://doi.org/10.1016/j.apr.2015.05.007.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lauret, P., M. Diagne, and M. David, 2014: A neural network post-processing approach to improving NWP solar radiation forecasts. Energy Procedia, 57, 10441052, https://doi.org/10.1016/j.egypro.2014.10.089.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Lothon, M., and Coauthors, 2014: The BLLAST field experiment: Boundary-layer late afternoon and sunset turbulence. Atmos. Chem. Phys., 14, 10 93110 960, https://doi.org/10.5194/acp-14-10931-2014.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ludwig, F., J. Livingston, and R. M. Endlich, 1991: Use of mass conservation and critical dividing streamline concepts for efficient objective analysis of winds in complex terrain. J. Appl. Meteor. Climatol., 30, 14901499, https://doi.org/10.1175/1520-0450(1991)030<1490:UOMCAC>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Matsui, T., S. Q. Zhang, S. E. Lang, W. K. Tao, C. Ichoku, and C. D. Peters-Lidard, 2018: Impact of radiation frequency, precipitation radiative forcing, and radiation column aggregation on convection-permitting West African monsoon simulations. Climate Dyn., 55, 193213, https://doi.org/10.1007/s00382-018-4187-2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Mlawer, E. J., S. J. Taubman, P. D. Brown, M. J. Iacono, and S. A. Clough, 1997: Radiative transfer for inhomogeneous atmospheres: RRTM, a validated correlated-k model for the longwave. J. Geophys. Res., 102, 16 66316 682, https://doi.org/10.1029/97JD00237.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Moosavi, A., V. Rao, and A. Sandu, 2021: Machine learning based algorithms for uncertainty quantification in numerical weather prediction models. J. Comput. Sci., 50, 101295, https://doi.org/10.1016/j.jocs.2020.101295.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • More, A., and M. Deo, 2003: Forecasting wind with neural networks. Mar. Struct., 16, 3549, https://doi.org/10.1016/S0951-8339(02)00053-9.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Oliver, J. E., and R. W. Fairbridge, 2005: Mountain and valley winds. Encyclopedia of World Climatology, J. E. Oliver, Ed., Springer, 516–517, https://doi.org/10.1007/1-4020-3266-8_144.

    • Crossref
    • Export Citation
  • Powers, J. G., and Coauthors, 2017: The Weather Research and Forecasting Model: Overview, system efforts, and future directions. Bull. Amer. Meteor. Soc., 98, 17171737, https://doi.org/10.1175/BAMS-D-15-00308.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ramachandran, P., B. Zoph, and Q. V. Le, 2017: Searching for activation functions. http://arxiv.org/abs/1710.05941.

  • Ramasamy, P., S. Chandel, and A. K. Yadav, 2015: Wind speed prediction in the mountainous region of India using an artificial neural network model. Renew. Energy, 80, 338347, https://doi.org/10.1016/j.renene.2015.02.034.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Rodrigo, J. S., E. Cantero, B. García, F. Borbón, U. Irigoyen, S. Lozano, P. M. Fernande, and R. A. Chávez, 2015: Atmospheric stability assessment for the characterization of offshore wind conditions. J. Phys., 625, 012044, https://doi.org/10.1088/1742-6596/625/1/012044.

    • Search Google Scholar
    • Export Citation
  • Sabatier, T., A. Paci, G. Canut, Y. Largeron, A. Dabas, J.-M. Donier, and T. Douffet, 2018: Wintertime local wind dynamics from scanning Doppler lidar and air quality in the Arve river valley. Atmosphere, 9, 118, https://doi.org/10.3390/atmos9040118.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Santos-Alamillos, F. J., D. Pozo-Vázquez, J. A. Ruiz-Arias, V. Lara-Fanego, and J. Tovar-Pescador, 2013: Analysis of WRF Model wind estimate sensitivity to physics parameterization choice and terrain representation in Andalusia (southern Spain). J. Appl. Meteor. Climatol., 52, 15921609, https://doi.org/10.1175/JAMC-D-12-0204.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Schlager, C., G. Kirchengast, J. Fuchsberger, A. Kann, and H. Truhetz, 2019: A spatial evaluation of high-resolution wind fields from empirical and dynamical modeling in hilly and mountainous terrain. Geosci. Model Dev., 12, 28552873, https://doi.org/10.5194/gmd-12-2855-2019.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Serafin, S., and Coauthors, 2018: Exchange processes in the atmospheric boundary layer over mountainous terrain. Atmosphere, 9, 102, https://doi.org/10.3390/atmos9030102.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Skamarock, W. C., and Coauthors, 2019: A description of the Advanced Research WRF model version 4. NCAR Tech. Note NCAR/TN-556+STR, 145 pp., https://doi.org/10.5065/1dfh-6p97.

    • Crossref
    • Export Citation
  • Sukoriansky, S., B. Galperin, and V. Perov, 2006: A quasi-normal scale elimination model of turbulence and its application to stably stratified flows. Nonlinear Processes Geophys., 13, 922, https://doi.org/10.5194/npg-13-9-2006.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Tewari, M., and Coauthors, 2016: Implementation and verification of the united Noah land surface model in the WRF model. 20th Conf. on Weather Analysis and Forecasting/16th Conf. on Numerical Weather Prediction, Seattle, WA, Amer. Meteor. Soc., 14.2a, https://ams.confex.com/ams/84Annual/techprogram/paper_69061.htm.

  • Weigel, A. P., F. K. Chow, and M. W. Rotach, 2007: The effect of mountainous topography on moisture exchange between the “surface” and the free atmosphere. Atmospheric Boundary Layers, A. Baklanov and B. Grisogono, Eds., Springer, 71–88, https://doi.org/10.1007/978-0-387-74321-9_6.

    • Crossref
    • Export Citation
  • Whiteman, C. D., and Coauthors, 2008: Metcrax 2006: Meteorological experiments in Arizona’s Meteor Crater. Bull. Amer. Meteor. Soc., 89, 16651680, https://doi.org/10.1175/2008BAMS2574.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Wyngaard, J. C., 2004: Toward numerical modeling in the “Terra Incognita.” J. Atmos. Sci., 61, 18161826, https://doi.org/10.1175/1520-0469(2004)061<1816:TNMITT>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 305 0 0
Full Text Views 1246 935 346
PDF Downloads 416 117 8