Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning
The Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP), on-board the Cloud–Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) platform, is an elastic backscatter lidar that has been providing vertical profiles of the spatial, optical, and microphysical properties of clouds...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/1/10 |
| _version_ | 1797543710739660800 |
|---|---|
| author | Shan Zeng Ali Omar Mark Vaughan Macarena Ortiz Charles Trepte Jason Tackett Jeremy Yagle Patricia Lucker Yongxiang Hu David Winker Sharon Rodier Brian Getzewich |
| author_facet | Shan Zeng Ali Omar Mark Vaughan Macarena Ortiz Charles Trepte Jason Tackett Jeremy Yagle Patricia Lucker Yongxiang Hu David Winker Sharon Rodier Brian Getzewich |
| author_sort | Shan Zeng |
| collection | DOAJ |
| description | The Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP), on-board the Cloud–Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) platform, is an elastic backscatter lidar that has been providing vertical profiles of the spatial, optical, and microphysical properties of clouds and aerosols since June 2006. Distinguishing between feature types (i.e., clouds vs. aerosol) and subtypes (e.g., ice clouds vs. water clouds and dust aerosols from smoke) in the CALIOP measurements is currently accomplished using layer-integrated measurements acquired by co-polarized (parallel) and cross-polarized (perpendicular) 532 nm channels and a single 1064 nm channel. Newly developed deep machine learning (DML) semantic segmentation methods now have the ability to combine observations from multiple channels with texture information to recognize patterns in data. Instead of focusing on a limited set of layer integrated values, our new DML feature classification technique uses the full scope of range-resolved information available in the CALIOP attenuated backscatter profiles. In this paper, one of the convolutional neural networks (CNN), SegNet, a fast and efficient DML model, is used to distinguish aerosol subtypes directly from the CALIOP profiles. The DML method is a 2D range bin-to-range bin aerosol subtype classification algorithm. We compare our new DML results to the classifications generated by CALIOP’s 1D layer-to-layer operational retrieval algorithm. These two methods, which take distinctly different approaches to aerosol classification, agree in over 60% of the comparisons. Higher levels of agreement are found in homogeneous scenes containing only a single aerosol type (i.e., marine, stratospheric aerosols). Disagreement between the two techniques increases in regions containing mixture of different aerosol types. The multi-dimensional texture information leveraged by the DML method shows advantages in differentiating between aerosol types based on their classification scores, as well as in distinguishing vertical distributions of aerosol types within individual layers. However, untangling mixtures of aerosol subtypes is still challenging for both the DML and operational algorithms. |
| first_indexed | 2024-03-10T13:48:32Z |
| format | Article |
| id | doaj.art-89fb78b017494d2a9156949f357289c6 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T13:48:32Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-89fb78b017494d2a9156949f357289c62023-11-21T02:20:57ZengMDPI AGAtmosphere2073-44332020-12-011211010.3390/atmos12010010Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine LearningShan Zeng0Ali Omar1Mark Vaughan2Macarena Ortiz3Charles Trepte4Jason Tackett5Jeremy Yagle6Patricia Lucker7Yongxiang Hu8David Winker9Sharon Rodier10Brian Getzewich11Science Systems and Applications, Inc., Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USAScience Systems and Applications, Inc., Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USAScience Systems and Applications, Inc., Hampton, VA 23666, USANASA Langley Research Center, Hampton, VA 23666, USAThe Cloud–Aerosol Lidar with Orthogonal Polarization (CALIOP), on-board the Cloud–Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) platform, is an elastic backscatter lidar that has been providing vertical profiles of the spatial, optical, and microphysical properties of clouds and aerosols since June 2006. Distinguishing between feature types (i.e., clouds vs. aerosol) and subtypes (e.g., ice clouds vs. water clouds and dust aerosols from smoke) in the CALIOP measurements is currently accomplished using layer-integrated measurements acquired by co-polarized (parallel) and cross-polarized (perpendicular) 532 nm channels and a single 1064 nm channel. Newly developed deep machine learning (DML) semantic segmentation methods now have the ability to combine observations from multiple channels with texture information to recognize patterns in data. Instead of focusing on a limited set of layer integrated values, our new DML feature classification technique uses the full scope of range-resolved information available in the CALIOP attenuated backscatter profiles. In this paper, one of the convolutional neural networks (CNN), SegNet, a fast and efficient DML model, is used to distinguish aerosol subtypes directly from the CALIOP profiles. The DML method is a 2D range bin-to-range bin aerosol subtype classification algorithm. We compare our new DML results to the classifications generated by CALIOP’s 1D layer-to-layer operational retrieval algorithm. These two methods, which take distinctly different approaches to aerosol classification, agree in over 60% of the comparisons. Higher levels of agreement are found in homogeneous scenes containing only a single aerosol type (i.e., marine, stratospheric aerosols). Disagreement between the two techniques increases in regions containing mixture of different aerosol types. The multi-dimensional texture information leveraged by the DML method shows advantages in differentiating between aerosol types based on their classification scores, as well as in distinguishing vertical distributions of aerosol types within individual layers. However, untangling mixtures of aerosol subtypes is still challenging for both the DML and operational algorithms.https://www.mdpi.com/2073-4433/12/1/10CALIPSOCALIOPaerosol subtypeconvolutional neural networksmachine learning |
| spellingShingle | Shan Zeng Ali Omar Mark Vaughan Macarena Ortiz Charles Trepte Jason Tackett Jeremy Yagle Patricia Lucker Yongxiang Hu David Winker Sharon Rodier Brian Getzewich Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning Atmosphere CALIPSO CALIOP aerosol subtype convolutional neural networks machine learning |
| title | Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning |
| title_full | Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning |
| title_fullStr | Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning |
| title_full_unstemmed | Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning |
| title_short | Identifying Aerosol Subtypes from CALIPSO Lidar Profiles Using Deep Machine Learning |
| title_sort | identifying aerosol subtypes from calipso lidar profiles using deep machine learning |
| topic | CALIPSO CALIOP aerosol subtype convolutional neural networks machine learning |
| url | https://www.mdpi.com/2073-4433/12/1/10 |
| work_keys_str_mv | AT shanzeng identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT aliomar identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT markvaughan identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT macarenaortiz identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT charlestrepte identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT jasontackett identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT jeremyyagle identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT patricialucker identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT yongxianghu identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT davidwinker identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT sharonrodier identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning AT briangetzewich identifyingaerosolsubtypesfromcalipsolidarprofilesusingdeepmachinelearning |