Micropulse Lidar Cloud Mask Machine Learning VAP Now In Production

 
Published: 24 February 2023

This sample quicklook plot from the Southern Great Plains atmospheric observatory shows the log of the normalized relative backscatter (log10 NRB), linear depolarization ratio (LDR), and cloud mask from the MPLCMASKML value-added product for January 1, 2015. In addition, the plot contains the machine learning model’s confidence in its prediction, and cloud base and cloud top.
This sample quicklook plot from the Southern Great Plains atmospheric observatory shows the log of the normalized relative backscatter (log10 NRB), linear depolarization ratio (LDR), and cloud mask from the MPLCMASKML value-added product for January 1, 2015. In addition, the plot contains the machine learning model’s confidence in its prediction, and cloud base and cloud top.

The Micropulse Lidar Cloud Mask Machine Learning value-added product (MPLCMASKML VAP) has moved from evaluation to production. This transition increases the data availability for active Atmospheric Radiation Measurement (ARM) user facility sites operating fast-switching polarized micropulse lidars from the beginning of instrument operations at each site to the present day.

In addition, production data are provided for all ARM mobile deployments included in the initial evaluation release.

MPLCMASKML uses a machine learning model that can produce pixel-to-pixel predictions of clouds in lidar images (Cromwell and Flynn 2019). The VAP gives users the predictions from the model, the cloud mask generated from the prediction output, the number of cloud layers, and the cloud layer boundaries. This ARM data announcement describes the differences between MPLCMASKML and the original MPLCMASK product.

MPLCMASKML production data are available for the following ARM sites and date ranges:

The MPLCMASKML team plans to have data for the SGP, ENA, and NSA caught up to the present day and automatically running daily by mid-March.

Future data will come from the 2019–2020 Multidisciplinary Drifting Observatory for the Study of Arctic Climate (MOSAiC) expedition. Eventually, all available ARM fast-switching polarized micropulse lidar data will be processed with MPLCMASKML.

More information about MPLCMASKML is available on the VAP web page.

Access the data in the ARM Data Center. (Go here to create an account to download the data.)

To share your experience using the data or to ask questions, contact ARM translator Damao Zhang, assistant translator Donna Flynn, or VAP developer Erol Cromwell.

To cite the MPLCMASKML data, please use doi:10.5439/1637940.

Reference: Cromwell E and D Flynn. 2019. “Lidar Cloud Detection With Fully Convolutional Networks.” In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 619-627, doi:10.1109/WACV.2019.00071.

# # #


ARM is a DOE Office of Science user facility operated by nine DOE national laboratories.