Articles | Volume 5, issue 2
Research article
17 Apr 2020
Research article |  | 17 Apr 2020

The importance of round-robin validation when assessing machine-learning-based vertical extrapolation of wind speeds

Nicola Bodini and Mike Optis

Data sets

Atmospheric Radiation Measurement (ARM) user facility. Doppler Lidar (DLAUX) R. Newsom and R. Krishnamurthy

Atmospheric Radiation Measurement (ARM) user facility. Eddy Correlation Flux Measurement System (30ECOR) R. Sullivan and E. Keeler

Atmospheric Radiation Measurement (ARM) user facility. Carbon Dioxide Flux Measurement Systems (30CO2FLX4M) S. Biraud, D. Billesbach, and S. Chan

Short summary
An accurate assessment of the wind resource at hub height is necessary for an efficient and bankable wind farm project. Conventional techniques for wind speed vertical extrapolation include a power law and a logarithmic law. Here, we propose a round-robin validation to assess the benefits that a machine-learning-based approach can provide in vertically extrapolating wind speed at a location different from the training site – the most practically useful application for the wind energy industry.
Final-revised paper