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

Journal metrics

Journal metrics

  • IF value: 3.400 IF 3.400
  • IF 5-year value: 3.841 IF 5-year
    3.841
  • CiteScore value: 3.71 CiteScore
    3.71
  • SNIP value: 1.472 SNIP 1.472
  • IPP value: 3.57 IPP 3.57
  • SJR value: 1.770 SJR 1.770
  • Scimago H <br class='hide-on-tablet hide-on-mobile'>index value: 70 Scimago H
    index 70
  • h5-index value: 49 h5-index 49
Discussion papers
https://doi.org/10.5194/amt-2019-409
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-2019-409
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 20 Nov 2019

Submitted as: research article | 20 Nov 2019

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Atmospheric Measurement Techniques (AMT).

A Machine Learning-Based Cloud Detection and Thermodynamic Phase Classification Algorithm using Passive Spectral Observations

Chenxi Wang1,2, Steven Platnick2, Kerry Meyer2, Zhibo Zhang3, and Yaping Zhou1,2 Chenxi Wang et al.
  • 1Joint Center for Earth Systems Technology, Universityof Maryland Baltimore County, Baltimore, MD, USA
  • 2NASA Goddard Space Flight Center, Greenbelt, MD, USA
  • 3Department of Physics, Universityof Maryland Baltimore County, Baltimore, MD, USA

Abstract. We trained two Random Forest (RF) machine-learning models for cloud mask and cloud thermodynamic phase detection using spectral observations from VIIRS on Suomi-NPP (SNPP). Observations from CALIOP were carefully selected to provide reference labels. The two RF models were trained for all-day and daytime-only conditions using a 4-year collocated VIIRS/CALIOP dataset from 2013 to 2016. Due to the orbit difference, the collocated CALIOP and SNPP VIIRS training samples cover a broad viewing zenith angle range, which is a great benefit to overall model performance. The all-day model uses 3 VIIRS infrared (IR) bands (8.6, 11, and 12 μm) and the daytime model uses 5 Near-IR (NIR) and Shortwave-IR (SWIR) bands (0.86, 1.24, 1.38, 1.64 and 2.25 μm) together with the 3 IR bands to detect clear, liquid water, and ice cloud pixels. Up to 7 surface types, namely, ocean/water, forest, cropland, grassland, snow/ice, barren/desert, and shrubland, were considered separately to enhance performance for both models. Detection of cloudy pixels and thermodynamic phase with the two RF models were compared against collocated CALIOP products from 2017. It is shown that the two RF models have high accuracy rates in comparison with the CALIOP reference for both cloud detection and thermodynamic phase. For cloud detection, the accuracy rates of the daytime RF model are higher than 92%thinsp;% for all surface types, while the accuracy rates of the all-day RF model decrease by 3~8%thinsp;%, depending on surface type. For cloud thermodynamic phase, both RF models agree well with CALIOP, except over barren/desert regions. Other existing SNPP VIIRS and Aqua MODIS cloud mask and phase products are also evaluated, with results showing that the two RF models and the MODIS MYD06 optical property phase product are the top 3 algorithms with respect to lidar observations during the daytime. During the nighttime, the RF all-day model works best for both cloud detection and phase, in particular for pixels over snow/ice surfaces. The present RF models can be extended to other similar passive instruments if training samples can be collected from CALIOP or other lidars. However, the quality of reference labels and potential sampling issues that may impact model performance would need further attention.

Chenxi Wang et al.
Interactive discussion
Status: open (until 15 Jan 2020)
Status: open (until 15 Jan 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Chenxi Wang et al.
Data sets

VIIRS VNP02MOD Calibrated Radiances VIIRS characterization Support Team (VCST)/MODIS Adaptive Processing System (MODAPS) https://doi.org/10.5067/VIIRS/VNP02MOD.001

CALIOP CAL_LID_L2_01kmCLay-Standard-V4-20 Citing Data from the NASA Langley Research Center's Atmospheric Science Data Center (ASDC) Distributed Active Archive Center (DAAC) https://doi.org/10.5067/CALIOP/CALIPSO/LID_L2_01KmCLay-Standard-V4-20

CALIOP CAL_LID_L2_05kmCLay-Standard-V4-20 Citing Data from the NASA Langley Research Center's Atmospheric Science Data Center (ASDC) Distributed Active Archive Center (DAAC) https://doi.org/10.5067/CALIOP/CALIPSO/LID_L2_05kmCLay-Standard-V4-20

CALIOP CAL_LID_L2_05kmALay-Standard-V4-20 Citing Data from the NASA Langley Research Center's Atmospheric Science Data Center (ASDC) Distributed Active Archive Center (DAAC) https://doi.org/10.5067/CALIOP/CALIPSO/LID_L2_05kmALay-Standard-V4-20

Chenxi Wang et al.
Viewed  
Total article views: 220 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
174 45 1 220 1 1
  • HTML: 174
  • PDF: 45
  • XML: 1
  • Total: 220
  • BibTeX: 1
  • EndNote: 1
Views and downloads (calculated since 20 Nov 2019)
Cumulative views and downloads (calculated since 20 Nov 2019)
Viewed (geographical distribution)  
Total article views: 92 (including HTML, PDF, and XML) Thereof 92 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 13 Dec 2019
Publications Copernicus
Download
Short summary
A machine-learning (ML) based approach that can be used for cloud mask and phase detection is developed. An all-day model uses infrared (IR) observations and a daytime model uses shortwave and IR observations from passive instrument (VIIRS) are trained separately for different surface types. The training datasets are selected by using reference pixel types from collocated space lidar (CALIOP). The ML approach is validated carefully and the overall performance is better than traditional methods.
A machine-learning (ML) based approach that can be used for cloud mask and phase detection is...
Citation