Preprints
https://doi.org/10.5194/amt-2021-123
https://doi.org/10.5194/amt-2021-123

  21 May 2021

21 May 2021

Review status: a revised version of this preprint was accepted for the journal AMT and is expected to appear here in due course.

The University of Washington Ice-Liquid Discriminator (UWILD) improves single particle phase classifications of hydrometeors within Southern Ocean clouds using machine learning

Rachel Atlas1, Johannes Mohrmann1, Joseph Finlon1, Jeremy Lu1,, Ian Hsiao1,, Robert Wood1, and Minghui Diao2 Rachel Atlas et al.
  • 1Department of Atmospheric Sciences, University of Washington
  • 2Department of Meteorology and Climate Science, San Jose State University
  • These authors contributed equally to this work.

Abstract. Mixed-phase Southern Ocean clouds are challenging to simulate and their representation in climate models is an important control on climate sensitivity. In particular, the amount of supercooled liquid and frozen mass that they contain in the present climate is a predictor of their planetary feedback in a warming climate. The recent Southern Ocean Clouds, Radiation and Aerosol Transport Experimental Study (SOCRATES) vastly increased the amount of in-situ data available from mixed-phase Southern Ocean clouds useful for model evaluation. Bulk measurements distinguishing liquid and ice water content are not available from SOCRATES so single particle phase classifications from the Two-Dimensional Stereo (2D-S) probe are invaluable for quantifying mixed-phase cloud properties. Motivated by the presence of large biases in existing phase discrimination algorithms, we develop a novel technique for single particle phase classification of binary 2D-S images using a random forest algorithm, which we refer to as the University of Washington Ice-Liquid Discriminator (UWILD). UWILD uses 14 parameters computed from binary image data, as well as particle inter-arrival time, to predict phase. We use liquid-only and ice-dominated time periods within the SOCRATES dataset as training and testing data. This novel approach to model training avoids major pitfalls associated with using manually labelled data, including reduced model generalizability and high labor costs. We find that UWILD is well calibrated and has an overall accuracy of 95% compared to 72% and 78% for two existing phase classification algorithms that we compare it with. UWILD improves classifications of small ice crystals and large liquid drops in particular and has more flexibility than the other algorithms to identify both liquid-dominated and ice-dominated regions within the SOCRATES dataset. UWILD misclassifies a small percentage of large liquid drops as ice. Such misclassified particles are typically associated with model confidence below 75% and can easily be filtered out of the dataset. UWILD phase classifications show that particles with area-equivalent diameter (Deq) < 0.17 mm are mostly liquid at all temperatures sampled, down to −40°C. Larger particles (Deq > 0.17 mm) are predominantly frozen at all temperatures below 0 °C. Between 0 °C and 5 °C, there are roughly equal numbers of frozen and liquid mid-size particles (0.17 < Deq < 0.33 mm) and larger particles (Deq > 0.33 mm) are mostly frozen. We also use UWILD's phase classifications to estimate sub 1-Hz phase heterogeneity and we show examples of meter-scale cloud phase heterogeneity in the SOCRATES dataset.

Rachel Atlas et al.

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-123', Darrel Baumgardner, 16 Jun 2021
    • AC1: 'Reply on RC1', Rachel Atlas, 14 Aug 2021
  • RC2: 'Comment on amt-2021-123', Annika Lauber, 02 Jul 2021
    • AC2: 'Reply on RC2', Rachel Atlas, 14 Aug 2021

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on amt-2021-123', Darrel Baumgardner, 16 Jun 2021
    • AC1: 'Reply on RC1', Rachel Atlas, 14 Aug 2021
  • RC2: 'Comment on amt-2021-123', Annika Lauber, 02 Jul 2021
    • AC2: 'Reply on RC2', Rachel Atlas, 14 Aug 2021

Rachel Atlas et al.

Model code and software

UWILD and Analysis Codes Johannes Mohrmann, Joseph A. Finlon, Jeremy Lu, Ian Hsiao, Rachel Atlas https://doi.org/10.5281/zenodo.4732532

Rachel Atlas et al.

Viewed

Total article views: 521 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
355 149 17 521 6 3
  • HTML: 355
  • PDF: 149
  • XML: 17
  • Total: 521
  • BibTeX: 6
  • EndNote: 3
Views and downloads (calculated since 21 May 2021)
Cumulative views and downloads (calculated since 21 May 2021)

Viewed (geographical distribution)

Total article views: 414 (including HTML, PDF, and XML) Thereof 414 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 20 Sep 2021
Download
Short summary
Many clouds with temperatures between 0 °C and −40 °C contain both liquid and ice particles and the ratio of liquid to ice particles influences how the clouds interact with radiation and moderate Earth's climate. Here, we use a machine learning method called random forest to classify images of individual cloud particles as either liquid or ice. We apply our algorithm to images captured by aircraft within clouds overlying the Southern Ocean and we find that it outperforms two existing algorithms.