Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS
Abstract
Satellite remote sensing plays a pivotal role in characterizing hydrometeorological components including cloud types and their associated precipitation. The Cloud Profiling Radar (CPR) on the Polar Orbiting CloudSat satellite has provided a unique dataset to characterize cloud types. However, data from this nadir-looking radar offers limited capability for estimating precipitation because of the narrow satellite swath coverage and low temporal frequency. We use these high-quality observations to build a Deep Neural Network Cloud-Type Classification (DeepCTC) model to estimate cloud types from multispectral data from the Advanced Baseline Imager (ABI) onboard the GOES-16 platform. The DeepCTC model is trained and tested using coincident data from both CloudSat and ABI over the CONUS region. Evaluations of DeepCTC indicate that the model performs well for a variety of cloud types including Altostratus, Altocumulus, Cumulus, Nimbostratus, Deep Convective and High clouds. However, capturing low-level clouds remains a challenge for the model. Results from simulated GOES-16 ABI imageries of the Hurricane Harvey event show a large-scale perspective of the rapid and consistent cloud-type monitoring is possible using the DeepCTC model. Additionally, assessments using half-hourly Multi-Radar/Multi-Sensor (MRMS) precipitation rate data (for Hurricane Harvey as a case study) show the ability of DeepCTC in identifying rainy clouds,more »
- Authors:
-
- Univ. of California, Irvine, CA (United States). Dept. of Civil and Environmental Engineering. The Henry Samueli School of Engineering. Center for Hydrometeorology and Remote Sensing (CHRS)
- Syracuse Univ., NY (United States). Sept. of Electrical Engineering and Computer Science
- Univ. of California, Irvine, CA (United States). Dept. of Civil and Environmental Engineering. The Henry Samueli School of Engineering. Center for Hydrometeorology and Remote Sensing (CHRS); Univ. of California, Irvine, CA (United States). Dept. of Earth System Science
- NASA Ames Research Center (ARC), Moffett Field, Mountain View, CA (United States)
- Publication Date:
- Research Org.:
- Univ. of California, Oakland, CA (United States)
- Sponsoring Org.:
- USDOE Office of International Affairs (IA)
- OSTI Identifier:
- 1801041
- Grant/Contract Number:
- IA0000018
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Remote Sensing
- Additional Journal Information:
- Journal Volume: 12; Journal Issue: 2; Journal ID: ISSN 2072-4292
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES; 47 OTHER INSTRUMENTATION; Environmental Sciences & Ecology; Geology; Remote Sensing; Imaging Science & Photographic Technology; geostationary satellites; CloudSat; cloud types; near real-time monitoring; deep learning; precipitation
Citation Formats
Afzali Gorooh, Vesta, Kalia, Subodh, Nguyen, Phu, Hsu, Kuo-lin, Sorooshian, Soroosh, Ganguly, Sangram, and Nemani, Ramakrishna. Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS. United States: N. p., 2020.
Web. doi:10.3390/rs12020316.
Afzali Gorooh, Vesta, Kalia, Subodh, Nguyen, Phu, Hsu, Kuo-lin, Sorooshian, Soroosh, Ganguly, Sangram, & Nemani, Ramakrishna. Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS. United States. https://doi.org/10.3390/rs12020316
Afzali Gorooh, Vesta, Kalia, Subodh, Nguyen, Phu, Hsu, Kuo-lin, Sorooshian, Soroosh, Ganguly, Sangram, and Nemani, Ramakrishna. Sat .
"Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS". United States. https://doi.org/10.3390/rs12020316. https://www.osti.gov/servlets/purl/1801041.
@article{osti_1801041,
title = {Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS},
author = {Afzali Gorooh, Vesta and Kalia, Subodh and Nguyen, Phu and Hsu, Kuo-lin and Sorooshian, Soroosh and Ganguly, Sangram and Nemani, Ramakrishna},
abstractNote = {Satellite remote sensing plays a pivotal role in characterizing hydrometeorological components including cloud types and their associated precipitation. The Cloud Profiling Radar (CPR) on the Polar Orbiting CloudSat satellite has provided a unique dataset to characterize cloud types. However, data from this nadir-looking radar offers limited capability for estimating precipitation because of the narrow satellite swath coverage and low temporal frequency. We use these high-quality observations to build a Deep Neural Network Cloud-Type Classification (DeepCTC) model to estimate cloud types from multispectral data from the Advanced Baseline Imager (ABI) onboard the GOES-16 platform. The DeepCTC model is trained and tested using coincident data from both CloudSat and ABI over the CONUS region. Evaluations of DeepCTC indicate that the model performs well for a variety of cloud types including Altostratus, Altocumulus, Cumulus, Nimbostratus, Deep Convective and High clouds. However, capturing low-level clouds remains a challenge for the model. Results from simulated GOES-16 ABI imageries of the Hurricane Harvey event show a large-scale perspective of the rapid and consistent cloud-type monitoring is possible using the DeepCTC model. Additionally, assessments using half-hourly Multi-Radar/Multi-Sensor (MRMS) precipitation rate data (for Hurricane Harvey as a case study) show the ability of DeepCTC in identifying rainy clouds, including Deep Convective and Nimbostratus and their precipitation potential. We also use DeepCTC to evaluate the performance of the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) product over different cloud types with respect to MRMS referenced at a half-hourly time scale for July 2018. Our analysis suggests that DeepCTC provides supplementary insights into the variability of cloud types to diagnose the weakness and strength of near real-time GEO-based precipitation retrievals. With additional training and testing, we believe DeepCTC has the potential to augment the widely used PERSIANN-CCS algorithm for estimating precipitation.},
doi = {10.3390/rs12020316},
journal = {Remote Sensing},
number = 2,
volume = 12,
place = {United States},
year = {Sat Jan 18 00:00:00 EST 2020},
month = {Sat Jan 18 00:00:00 EST 2020}
}
Works referenced in this record:
Evaluation of PERSIANN System Satellite–Based Estimates of Tropical Rainfall
journal, September 2000
- Sorooshian, Soroosh; Hsu, Kuo-Lin; Gao, Xiaogang
- Bulletin of the American Meteorological Society, Vol. 81, Issue 9
Global Cloud Climatologies: A Historical Review
journal, May 1984
- Hughes, N. A.
- Journal of Climate and Applied Meteorology, Vol. 23, Issue 5
Using naive Bayes classifier for classification of convective rainfall intensities based on spectral characteristics retrieved from SEVIRI
journal, July 2016
- Hameg, Slimane; Lazri, Mourad; Ameur, Soltane
- Journal of Earth System Science, Vol. 125, Issue 5
Advances in Understanding Clouds from ISCCP
journal, November 1999
- Rossow, William B.; Schiffer, Robert A.
- Bulletin of the American Meteorological Society, Vol. 80, Issue 11
Measuring Cloud Properties from Space: A Review
journal, March 1989
- Rossow, William B.
- Journal of Climate, Vol. 2, Issue 3
A Closer Look at the ABI on the GOES-R Series
journal, April 2017
- Schmit, Timothy J.; Griffith, Paul; Gunshor, Mathew M.
- Bulletin of the American Meteorological Society, Vol. 98, Issue 4
Conditional Generative Adversarial Networks (cGANs) for Near Real-Time Precipitation Estimation from Multispectral GOES-16 Satellite Imageries—PERSIANN-cGAN
journal, September 2019
- Hayatbini, Negin; Kong, Bailey; Hsu, Kuo-lin
- Remote Sensing, Vol. 11, Issue 19
The area coverage of geophysical fields as a function of sensor field-of-view
journal, June 1994
- Key, Jeffrey R.
- Remote Sensing of Environment, Vol. 48, Issue 3
Classification of precipitating clouds using satellite infrared observations and its implications for rainfall estimation
journal, July 2018
- So, Damwon; Shin, Dong‐Bin
- Quarterly Journal of the Royal Meteorological Society, Vol. 144, Issue S1
A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
text, January 2017
- Ball, John E.; Anderson, Derek T.; Chan, Chee Seng
- arXiv
Pattern recognition techniques for the identification of cloud and cloud systems
journal, September 1995
- Pankiewicz, G. S.
- Meteorological Applications, Vol. 2, Issue 3
A systematic analysis of performance measures for classification tasks
journal, July 2009
- Sokolova, Marina; Lapalme, Guy
- Information Processing & Management, Vol. 45, Issue 4
High-Spatial-Resolution Surface and Cloud-Type Classification from MODIS Multispectral Band Measurements
journal, February 2003
- Li, Jun; Menzel, W. Paul; Yang, Zhongdong
- Journal of Applied Meteorology, Vol. 42, Issue 2
Cloud Classification of AVHRR Imagery in Maritime Regions Using a Probabilistic Neural Network
journal, August 1994
- Bankert, Richard L.
- Journal of Applied Meteorology, Vol. 33, Issue 8
On the determination of cloud cover from satellite sensors: The effect of sensor spatial resolution
journal, January 1992
- Wielicki, Bruce A.; Parker, Lindsay
- Journal of Geophysical Research, Vol. 97, Issue D12
Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community
journal, September 2017
- Ball, John E.; Anderson, Derek T.; Chan, Chee Seng
- Journal of Applied Remote Sensing, Vol. 11, Issue 04
Validation of the CloudSat precipitation occurrence algorithm using the Canadian C band radar network
journal, January 2008
- Hudak, David; Rodriguez, Peter; Donaldson, Norman
- Journal of Geophysical Research, Vol. 113
Kalman Filter–Based CMORPH
journal, December 2011
- Joyce, Robert J.; Xie, Pingping
- Journal of Hydrometeorology, Vol. 12, Issue 6
THE CLOUDSAT MISSION AND THE A-TRAIN: A New Dimension of Space-Based Observations of Clouds and Precipitation
journal, December 2002
- Stephens, Graeme L.; Vane, Deborah G.; Boain, Ronald J.
- Bulletin of the American Meteorological Society, Vol. 83, Issue 12
HER2 Molecular Marker Scoring Using Transfer Learning and Decision Level Fusion
journal, March 2021
- Tewary, Suman; Mukhopadhyay, Sudipta
- Journal of Digital Imaging, Vol. 34, Issue 3
Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning Methods
journal, January 2014
- Camps-Valls, Gustavo; Tuia, Devis; Bruzzone, Lorenzo
- IEEE Signal Processing Magazine, Vol. 31, Issue 1
Application of neural networks to AVHRR cloud segmentation
journal, May 1995
- Yhann, S. R.; Simpson, J. J.
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 33, Issue 3
Studying Altocumulus with Ice Virga Using Ground-Based Active and Passive Remote Sensors
journal, April 2004
- Wang, Zhien; Sassen, Kenneth; Whiteman, David N.
- Journal of Applied Meteorology, Vol. 43, Issue 3
Daytime Precipitation Estimation Using Bispectral Cloud Classification System
journal, May 2010
- Behrangi, Ali; Hsu, Koulin; Imam, Bisher
- Journal of Applied Meteorology and Climatology, Vol. 49, Issue 5
Attribution of extreme rainfall from Hurricane Harvey, August 2017
journal, December 2017
- van Oldenborgh, Geert Jan; van der Wiel, Karin; Sebastian, Antonia
- Environmental Research Letters, Vol. 12, Issue 12
Cloud Type and Macrophysical Property Retrieval Using Multiple Remote Sensors
journal, October 2001
- Wang, Zhien; Sassen, Kenneth
- Journal of Applied Meteorology, Vol. 40, Issue 10
An Automated Neural Network Cloud Classifier for Use over Land and Ocean Surfaces
journal, October 1997
- Miller, Shawn W.; Emery, William J.
- Journal of Applied Meteorology, Vol. 36, Issue 10
An optimal image transform for threshold-based cloud detection using heteroscedastic discriminant analysis
journal, March 2011
- Marais, Izak Van Zyl; Du Preez, Johan Adam; Steyn, Willem Herman
- International Journal of Remote Sensing, Vol. 32, Issue 6
Cloud Detection with MODIS. Part II: Validation
journal, July 2008
- Ackerman, S. A.; Holz, R. E.; Frey, R.
- Journal of Atmospheric and Oceanic Technology, Vol. 25, Issue 7
Classifying clouds around the globe with the CloudSat radar: 1-year of results
journal, January 2008
- Sassen, Kenneth; Wang, Zhien
- Geophysical Research Letters, Vol. 35, Issue 4
Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis: SOLO, AN ANN MODEL SUITABLE FOR HYDROLOGIC MODELING
journal, December 2002
- Hsu, Kuo-lin; Gupta, Hoshin V.; Gao, Xiaogang
- Water Resources Research, Vol. 38, Issue 12
Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks
journal, September 1997
- Hsu, Kou-lin; Gao, Xiaogang; Sorooshian, Soroosh
- Journal of Applied Meteorology, Vol. 36, Issue 9
NWCSAF AVHRR Cloud Detection and Analysis Using Dynamic Thresholds and Radiative Transfer Modeling. Part I: Algorithm Description
journal, January 2005
- Dybbroe, Adam; Karlsson, Karl-Göran; Thoss, Anke
- Journal of Applied Meteorology, Vol. 44, Issue 1
Combination of support vector machine, artificial neural network and random forest for improving the classification of convective and stratiform rain using spectral features of SEVIRI data
journal, May 2018
- Lazri, Mourad; Ameur, Soltane
- Atmospheric Research, Vol. 203
Precipitation Identification with Bispectral Satellite Information Using Deep Learning Approaches
journal, May 2017
- Tao, Yumeng; Gao, Xiaogang; Ihler, Alexander
- Journal of Hydrometeorology, Vol. 18, Issue 5
Climatology of cloud water content associated with different cloud types observed by A-Train satellites: Climatology of Cloud Water Content
journal, May 2015
- Huang, Lei; Jiang, Jonathan H.; Wang, Zhien
- Journal of Geophysical Research: Atmospheres, Vol. 120, Issue 9
Extended contingency table: Performance metrics for satellite observations and climate model simulations: TECHNICAL NOTE
journal, October 2013
- AghaKouchak, A.; Mehran, A.
- Water Resources Research, Vol. 49, Issue 10
CloudNet: Ground‐Based Cloud Classification With Deep Convolutional Neural Network
journal, August 2018
- Zhang, Jinglin; Liu, Pu; Zhang, Feng
- Geophysical Research Letters, Vol. 45, Issue 16
A neural network approach to cloud classification
journal, January 1990
- Lee, J.; Weger, R. C.; Sengupta, S. K.
- IEEE Transactions on Geoscience and Remote Sensing, Vol. 28, Issue 5
Artificial intelligence systems for rainy areas detection and convective cells' delineation for the south shore of Mediterranean Sea during day and nighttime using MSG satellite images
journal, September 2016
- Tebbi, Mohsene Abdelfettah; Haddad, Boualem
- Atmospheric Research, Vol. 178-179
A Survey on Transfer Learning
journal, October 2010
- Pan, Sinno Jialin; Yang, Qiang
- IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10
Comparison of Cloud Type Classification with Split Window Algorithm Based on Different Infrared Band Combinations of Himawari-8 Satellite
journal, January 2018
- Purbantoro, Babag; Aminuddin, Jamrud; Manago, Naohiro
- Advances in Remote Sensing, Vol. 07, Issue 03
Cloud Detection Using Satellite Measurements of Infrared and Visible Radiances for ISCCP
journal, December 1993
- Rossow, William B.; Garder, Leonid C.
- Journal of Climate, Vol. 6, Issue 12
CloudSat and CALIPSO within the A-Train: Ten Years of Actively Observing the Earth System
journal, March 2018
- Stephens, Graeme; Winker, David; Pelon, Jacques
- Bulletin of the American Meteorological Society, Vol. 99, Issue 3
Cloud detection and analysis: A review of recent progress
journal, May 1988
- Goodman, A. H.; Henderson-Sellers, A.
- Atmospheric Research, Vol. 21, Issue 3-4
Multi-Radar Multi-Sensor (MRMS) Quantitative Precipitation Estimation: Initial Operating Capabilities
journal, April 2016
- Zhang, Jian; Howard, Kenneth; Langston, Carrie
- Bulletin of the American Meteorological Society, Vol. 97, Issue 4