Using Multitask Machine Learning to Type Clouds and Aerosols from Space-Based Photon-Counting Lidar Measurements

Chase A. Fuller; Patrick A. Selmer; Joseph Gomes; Matthew J. McGill

doi:10.3390/rs17162787

Back

Using Multitask Machine Learning to Type Clouds and Aerosols from Space-Based Photon-Counting Lidar Measurements

Journal article

Open access

Peer reviewed

Using Multitask Machine Learning to Type Clouds and Aerosols from Space-Based Photon-Counting Lidar Measurements

Chase A. Fuller, Patrick A. Selmer, Joseph Gomes and Matthew J. McGill

Remote sensing (Basel, Switzerland), Vol.17(16), 2787

08/12/2025

DOI: 10.3390/rs17162787

Files and links (1)

url

https://doi.org/10.3390/rs17162787View

Published (Version of record) Open Access

Abstract

Space-based, photon-counting lidar instruments are effective tools for observing cloud and aerosol layers in the atmosphere. Cloud phases and several different kinds of aerosols are presently identified and typed using sophisticated, fine-tuned classification algorithms that operate using processed lidar data. We present a deep neural network semantic segmentation model that was trained using raw, uncalibrated photon count data and data products from the Cloud/Aerosol Transport System’s (CATS) 1064 nm lidar. Our approach successfully types layers in complex scenes using only raw photon counts, bin altitudes, and ground surface type at 14 to 171 times the spatial resolution of the CATS operational data product. We observe comparable cloud detection and phase determination to the CATS operational algorithm while also exhibiting a 15-point improvement in finding tenuous aerosol layers. Because the model is lightweight, does not rely upon ancillary information, and is optimized to leverage GPU computing, it has the potential to be deployed on-instrument to perform cloud and aerosol typing in real time.

lidar

cloud

aerosol

deep learning

machine learning

image processing

Details

Title: Subtitle: Using Multitask Machine Learning to Type Clouds and Aerosols from Space-Based Photon-Counting Lidar Measurements
Creators: Chase A. Fuller - University of Iowa
Patrick A. Selmer - Science Systems and Applications
Joseph Gomes - University of Iowa
Matthew J. McGill - University of Iowa
Resource Type: Journal article
Publication Details: Remote sensing (Basel, Switzerland), Vol.17(16), 2787
DOI: 10.3390/rs17162787
ISSN: 2072-4292
eISSN: 2072-4292
Publisher: MDPI
Grant note: National Aeronautics and Space Administration (NASA)
This research was funded, in part, by National Aeronautics and Space Administration (NASA) grants 80NSSC23K0551 and 80NSSC23K0191.
Language: English
Date published: 08/12/2025
Academic Unit: Iowa Technology Institute; Physics and Astronomy; Chemical and Biochemical Engineering
Record Identifier: 9984946845202771

Metrics

1 Record Views