U.S. Department of EnergyOffice of Scientific and Technical Information
Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX
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 verticallymore »
- Authors:
- Publication Date:
- DOE Contract Number:
- AC05-00OR22725
- Research Org.:
- Atmospheric Radiation Measurement User Facility
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- Collaborations:
- PNNL, BNL, ANL, ORNL
- Subject:
- 54 ENVIRONMENTAL SCIENCES; Thermodynamic Cloud Phase
- OSTI Identifier:
- 2568095
- DOI:
- https://doi.org/10.5439/2568095
Citation Formats
Goldberger, Lexie, Levin, Maxwell, Zhang, Damao, Geiss, Andrew, and Harris, Carlandra. Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX. United States: N. p., 2025.
Web. doi:10.5439/2568095.
Goldberger, Lexie, Levin, Maxwell, Zhang, Damao, Geiss, Andrew, & Harris, Carlandra. Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX. United States. doi:https://doi.org/10.5439/2568095
Goldberger, Lexie, Levin, Maxwell, Zhang, Damao, Geiss, Andrew, and Harris, Carlandra. 2025.
"Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX". United States. doi:https://doi.org/10.5439/2568095. https://www.osti.gov/servlets/purl/2568095. Pub date:Tue Jun 10 00:00:00 UTC 2025
@article{osti_2568095,
title = {Thermodynamic Cloud Phase Classifications Using Machine Learning at NSA and ANX},
author = {Goldberger, Lexie and Levin, Maxwell and Zhang, Damao and Geiss, Andrew and Harris, Carlandra},
abstractNote = {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.},
doi = {10.5439/2568095},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Jun 10 00:00:00 UTC 2025},
month = {Tue Jun 10 00:00:00 UTC 2025}
}