On the estimation of boundary layer heights: A machine learning approach
The planetary boundary-layer height (zi) 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 zi. Nevertheless, precise relationships between these surface properties and zi are less well known and not easily discernable from the long-term data. Machine learning approaches, such as Random Forest, which use a multi-regression framework, help to decipher some of the physical processes linking surface-based characteristics to zi. In this study, a multi-year dataset from 2016 to 2019 at the Southern Great Plains site is used to develop and test a machine learning framework for estimating zi. 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 zi 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. Noteworthy improvements in daytime zi estimates was observed using the RF model, where a 50 % improvement in mean absolute error compared to lidar-only zi estimates and provided an R2 of greater than 85 %. We also explore the effect of zi uncertainty on convective velocity scaling and present preliminary comparisons between the RF model and zi estimates derived from atmospheric models.