Preprints
https://doi.org/10.5194/egusphere-2025-1501
https://doi.org/10.5194/egusphere-2025-1501
07 May 2025
 | 07 May 2025

Classifying Thermodynamic Cloud Phase Using Machine Learning Models

Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang

Abstract. Vertically resolved thermodynamic cloud phase classifications are essential for studies of atmospheric cloud and precipitation processes. The Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) THERMOCLDPHASE Value-Added Product (VAP) uses a multi-sensor approach to classify thermodynamic cloud phase by combining lidar backscatter and depolarization, radar reflectivity, Doppler velocity, spectral width, microwave radiometer-derived liquid water path, and radiosonde temperature measurements. The measured voxels are classified as ice, snow, mixed-phase, liquid (cloud water), drizzle, rain, and liq_driz (liquid+drizzle). We use this product as the ground truth to train three machine learning (ML) models to predict the thermodynamic cloud phase from multi-sensor remote sensing measurements taken at the ARM North Slope of Alaska (NSA) observatory: a random forest (RF), a multilayer perceptron (MLP), and a convolutional neural network (CNN) with a U-Net architecture. Evaluations against the outputs of the THERMOCLDPHASE VAP with one year of data show that the CNN outperforms the other two models, achieving the highest test accuracy, F1-score, and mean Intersection over Union (IOU). Analysis of ML confidence scores shows ice, rain, and snow have higher confidence scores, followed by liquid, while mixed, drizzle, and liq_driz have lower scores. Feature importance analysis reveals that the mean Doppler velocity and vertically resolved temperature are the most influential datastreams for ML thermodynamic cloud phase predictions. The ML models’ generalization capacity is further evaluated by applying them at another Arctic ARM site in Norway using data taken during the ARM Cold-Air Outbreaks in the Marine Boundary Layer Experiment (COMBLE) field campaign. Finally, we evaluate the ML models’ response to simulated instrument outages and signal degradation.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share

Journal article(s) based on this preprint

16 Oct 2025
Classifying thermodynamic cloud phase using machine learning models
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang
Atmos. Meas. Tech., 18, 5393–5414, https://doi.org/10.5194/amt-18-5393-2025,https://doi.org/10.5194/amt-18-5393-2025, 2025
Short summary
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-1501', Anonymous Referee #1, 27 May 2025
    • AC1: 'Reply on RC1', Lexie Goldberger, 11 Jul 2025
  • RC2: 'Comment on egusphere-2025-1501', Anonymous Referee #2, 29 May 2025
    • AC2: 'Reply on RC2', Lexie Goldberger, 11 Jul 2025

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-1501', Anonymous Referee #1, 27 May 2025
    • AC1: 'Reply on RC1', Lexie Goldberger, 11 Jul 2025
  • RC2: 'Comment on egusphere-2025-1501', Anonymous Referee #2, 29 May 2025
    • AC2: 'Reply on RC2', Lexie Goldberger, 11 Jul 2025

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Lexie Goldberger on behalf of the Authors (11 Jul 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (13 Jul 2025) by Gianfranco Vulpiani
RR by Anonymous Referee #1 (14 Jul 2025)
ED: Publish subject to minor revisions (review by editor) (22 Jul 2025) by Gianfranco Vulpiani
AR by Lexie Goldberger on behalf of the Authors (01 Aug 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (01 Aug 2025) by Gianfranco Vulpiani
AR by Damao Zhang on behalf of the Authors (09 Aug 2025)  Manuscript 

Journal article(s) based on this preprint

16 Oct 2025
Classifying thermodynamic cloud phase using machine learning models
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang
Atmos. Meas. Tech., 18, 5393–5414, https://doi.org/10.5194/amt-18-5393-2025,https://doi.org/10.5194/amt-18-5393-2025, 2025
Short summary
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang
Lexie Goldberger, Maxwell Levin, Carlandra Harris, Andrew Geiss, Matthew D. Shupe, and Damao Zhang

Viewed

Total article views: 907 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
805 79 23 907 33 29 48
  • HTML: 805
  • PDF: 79
  • XML: 23
  • Total: 907
  • Supplement: 33
  • BibTeX: 29
  • EndNote: 48
Views and downloads (calculated since 07 May 2025)
Cumulative views and downloads (calculated since 07 May 2025)

Viewed (geographical distribution)

Total article views: 973 (including HTML, PDF, and XML) Thereof 973 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 16 Oct 2025
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
This study leverages machine learning models to classify cloud thermodynamic phases using multi-sensor remote sensing data collected at the Department of Energy Atmospheric Radiation Measurement North Slope of Alaska observatory. We evaluate model performance, feature importance, application of the model to another observatory, and quantify how the models respond to instrument outages.
Share