Articles | Volume 14, issue 6
https://doi.org/10.5194/amt-14-4403-2021
https://doi.org/10.5194/amt-14-4403-2021
Research article
 | 
15 Jun 2021
Research article |  | 15 Jun 2021

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

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

Data sets

Doppler lidar observations of radial velocity, backscatter and signal-to-noise ratio at Southern Great Plains central facility R. K. Newsom and R. Krishnamurthy https://doi.org/10.5439/1025185

Surface Meteorological Instrumentation at Southern Great Plains central facility J. Kyrouac, M. Ritsche, N. Hickmon, and D. Holdridge https://doi.org/10.5439/1025220

Soil Temperature and Moisture Profiles at Southern Great Plains central facility D. Cook, J. Kyrouac, E. Keeler, R. Sullivan, and B. Ermold https://doi.org/10.5439/1256098

Surface Energy Balance System at Southern Great Plains central facility R. Sullivan, D. Cook, and E. Keeler https://doi.org/10.5439/1025274

Planetary Boundary Layer Height observations from Radiosondes at Southern Great Plains central facility L. Riihimaki, C. Sivaraman, and D. Zhang https://doi.org/10.5439/1150253

ECOR: 30-minute averaged surface vertical fluxes of momentum, sensible heat, and latent heat at Southern Great Plains central facility S. Biraud, D. Billesbach, and S. Chan https://adc.arm.gov/discovery/#/results/datastream::sgpco2flx25mC1.b1

Download
Short summary
Planetary boundary layer (PBL) height is a critical parameter in atmospheric models. Continuous PBL height measurements from remote sensing measurements are important to understand various boundary layer mechanisms, especially during daytime and evening transition periods. Due to several limitations in existing methodologies to detect PBL height from a Doppler lidar, in this study, a machine learning (ML) approach is tested. The ML model is observed to improve the accuracy by over 50 %.