Preprints
https://doi.org/10.5194/egusphere-2024-376
https://doi.org/10.5194/egusphere-2024-376
13 Feb 2024
 | 13 Feb 2024
Status: this preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).

Deep-Learning-derived Planetary Boundary Layer Height from Conventional Meteorological Measurements

Tianning Su and Yunyan Zhang

Abstract. The planetary boundary layer (PBL) height (PBLH) is an important parameter for various meteorological and climate studies. This study presents a multi-structure deep neural network (DNN) model, designed to estimate PBLH by integrating morning temperature profiles with surface meteorological observations. The DNN model is developed by leveraging a rich dataset of PBLH derived from long-standing radiosonde records and augmented with high-resolution micro-pulse lidar and Doppler lidar observations. We access the performance of the DNN with an ensemble of ten members, each featuring distinct hidden layer structures, which collectively yield a robust 27-year PBLH dataset over the Southern Great Plains from 1994 to 2020. The influence of various meteorological factors on PBLH is rigorously analyzed through the importance test. Moreover, the DNN model's accuracy is evaluated against radiosonde observations and juxtaposed with conventional remote sensing methodologies, including Doppler lidar, ceilometer, Raman lidar, and Micro-pulse lidar. The DNN model exhibits reliable performance across diverse conditions and demonstrates lower biases relative to remote sensing methods. In addition, the DNN model, originally trained over a plain region, demonstrates remarkable adaptability when applied to the heterogeneous terrains and climates encountered during the GoAmazon (Tropical Rainforest) and CACTI (Middle Latitude Mountain) campaigns. These findings demonstrate the effectiveness of deep learning models in estimating PBLH, enhancing our understanding of boundary layer dynamics with implications for enhancing the representation of PBL in weather forecasting and climate modeling.

Tianning Su and Yunyan Zhang

Status: open (until 26 Mar 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Tianning Su and Yunyan Zhang
Tianning Su and Yunyan Zhang

Viewed

Total article views: 176 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
131 41 4 176 1 1
  • HTML: 131
  • PDF: 41
  • XML: 4
  • Total: 176
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 13 Feb 2024)
Cumulative views and downloads (calculated since 13 Feb 2024)

Viewed (geographical distribution)

Total article views: 170 (including HTML, PDF, and XML) Thereof 170 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 Feb 2024
Download
Short summary
The planetary boundary layer is critical to our climate system. This study uses a deep learning approach to estimate the planetary boundary layer height from the conventional meteorological measurements. By training data from comprehensive field observations, our model examines the influence of various meteorological factors on PBLH and demonstrates effectiveness across different scenarios, offering a reliable tool for understanding boundary layer dynamics.