Micropulse Lidar Cloud Mask Machine Learning VAP Released for SAIL, CAPE-k

 
Published: 14 November 2024
Five plots are stacked vertically, labeled from top to bottom as log10 NRB (preprocess_backscatter), LDR (preprocess_linear_depol_ratio), Cloud Mask (cloud_mask), Cloud Mask Confidence (cloud_mask_confidence), and Cloud Base and Top.
This sample quicklook plot from the SAIL ARM Mobile Facility site shows the log of the normalized relative backscatter (log10 NRB), linear depolarization ratio (LDR), and cloud mask from the MPLCMASKML value-added product for March 16, 2022. In addition, the plot contains the machine learning model’s confidence in its prediction, as well as cloud base and cloud top. Plot is provided by Erol Cromwell, Pacific Northwest National Laboratory.

The Micropulse Lidar Cloud Mask Machine Learning value-added product (MPLCMASKML VAP) is now available for the 2021–2023 Surface Atmosphere Integrated Field Laboratory (SAIL) campaign. Scientists can also access MPLCMASKML data from the ongoing Cloud And Precipitation Experiment at kennaook (CAPE-k), which the Atmospheric Radiation Measurement (ARM) user facility is conducting until September 2025.

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.

For SAIL, MPLCMASKML production data are available from September 1, 2021, to June 15, 2023—the full duration of the campaign—for the ARM Mobile Facility site in Gothic, Colorado.

The CAPE-k MPLCMASKML production data are available from April 15, 2024, to about a week before the current date for the ARM Mobile Facility site at kennaook / Cape Grim, Tasmania.

Scientists can use the new MPLCMASKML data now. The VAP will be automated to run for future campaigns.

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

Access the data in the ARM Data Center. (To download the data, first create an ARM account.)

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.