Extending the wind profile beyond the surface layer by combining physical and machine learning approaches

Liu, Boming; Ma, Xin; Guo, Jianping; Wen, Renqiang; Li, Hui; Jin, Shikuan; Ma, Yingying; Guo, Xiaoran; Gong, Wei

doi:https://doi.org/10.5194/acp-24-4047-2024

Articles | Volume 24, issue 7

https://doi.org/10.5194/acp-24-4047-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/acp-24-4047-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 24, issue 7

Research article

|

04 Apr 2024

Research article |

| 04 Apr 2024

Extending the wind profile beyond the surface layer by combining physical and machine learning approaches

Boming Liu, Xin Ma, Jianping Guo, Renqiang Wen, Hui Li, Shikuan Jin, Yingying Ma, Xiaoran Guo, and Wei Gong

Supplement

https://doi.org/10.5194/acp-24-4047-2024-supplement

Data sets

Radiosonde observation data National Meteorological Science Data Center http://www.nmic.cn/data/cdcdetail/dataCode/B.0011.0001C.html

ERA5 hourly data on single levels from 1959 to present ECMWF https://cds.climate.copernicus.eu/cdsapp#!/dataset/reanalysis-era5-single-levels?tab=overview

Doppler Lidar Horizontal Wind Profiles Atmospheric Radiation Measurement (ARM) user facility data https://adc.arm.gov/discovery/#/results/instrument_class_code::dlprof-wind

Download

Article (6561 KB)
Full-text XML

Short summary

Accurate wind profile estimation, especially for the lowest few hundred meters of the atmosphere, is of great significance for the weather, climate, and renewable energy sector. We propose a novel method that combines the power-law method with the random forest algorithm to extend wind profiles beyond the surface layer. Compared with the traditional algorithm, this method has better stability and spatial applicability and can be used to obtain the wind profiles on different land cover types.