On the estimation of boundary layer heights: a machine learning approach

Krishnamurthy, Raghavendra; Newsom, Rob K.; Berg, Larry K.; Xiao, Heng; Ma, Po-Lun; Turner, David D.

The planetary boundary layer height (inline-formulazi) is a key parameter used in atmospheric models for estimating the exchange of heat, momentum, and moisture between the surface and the free troposphere. Near-surface atmospheric and subsurface properties (such as soil temperature, relative humidity, etc.) are known to have an impact on inline-formulazi. Nevertheless, precise relationships between these surface properties and inline-formulazi are less well known and not easily discernible from the multi-year dataset. Machine learning approaches, such as random forest (RF), which use a multi-regression framework, help to decipher some of the physical processes linking surface-based characteristics to inline-formulazi. In this study, a 4-year dataset from 2016 to 2019 at the Southern Great Plains site is used to develop and test a machine learning framework for estimating inline-formulazi. Parameters derived from Doppler lidars are used in combination with over 20 different surface meteorological measurements as inputs to a RF model. The model is trained using radiosonde-derived inline-formulazi values spanning the period from 2016 through 2018 and then evaluated using data from 2019. Results from 2019 showed significantly better agreement with the radiosonde compared to estimates derived from a thresholding technique using Doppler lidars only. Noteworthy improvements in daytime inline-formulazi estimates were observed using the RF model, with a 50 % improvement in mean absolute error and an inline-formulaR2 of greater than 85 % compared to the Tucker method inline-formulazi. We also explore the effect of inline-formulazi uncertainty on convective velocity scaling and present preliminary comparisons between the RF model and inline-formulazi estimates derived from atmospheric models.



Krishnamurthy, Raghavendra / Newsom, Rob K. / Berg, Larry K. / et al: On the estimation of boundary layer heights: a machine learning approach. 2021. Copernicus Publications.


12 Monate:

Grafik öffnen


Rechteinhaber: Raghavendra Krishnamurthy et al.

Nutzung und Vervielfältigung: