Journal cover Journal topic
Atmospheric Measurement Techniques An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

IF value: 3.668
IF3.668
IF 5-year value: 3.707
IF 5-year
3.707
CiteScore value: 6.3
CiteScore
6.3
SNIP value: 1.383
SNIP1.383
IPP value: 3.75
IPP3.75
SJR value: 1.525
SJR1.525
Scimago H <br class='widget-line-break'>index value: 77
Scimago H
index
77
h5-index value: 49
h5-index49
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 %.
Preprints
https://doi.org/10.5194/amt-2020-439
https://doi.org/10.5194/amt-2020-439

  17 Dec 2020

17 Dec 2020

Review status: this preprint is currently under review for the journal AMT.

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

Raghavendra Krishnamurthy1, Rob K. Newsom1, Larry K. Berg1, Heng Xiao1, Po-Lun Ma1, and David D. Turner2 Raghavendra Krishnamurthy et al.
  • 1Pacific Northwest National Laboratory, ASGC Division, Richland, 99354, USA
  • 2National Oceanic and Atmospheric Administration / Global Systems Laboratory, Boulder, 80305, USA

Abstract. 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.

Raghavendra Krishnamurthy et al.

 
Status: open (until 11 Feb 2021)
Status: open (until 11 Feb 2021)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Raghavendra Krishnamurthy et al.

Raghavendra Krishnamurthy et al.

Viewed

Total article views: 261 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
171 86 4 261 3 5
  • HTML: 171
  • PDF: 86
  • XML: 4
  • Total: 261
  • BibTeX: 3
  • EndNote: 5
Views and downloads (calculated since 17 Dec 2020)
Cumulative views and downloads (calculated since 17 Dec 2020)

Viewed (geographical distribution)

Total article views: 289 (including HTML, PDF, and XML) Thereof 287 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 25 Jan 2021
Publications Copernicus
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 %.
Citation