Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery

Application to improve PERSIANN-CCS

Negin Hayatbini, Kuo lin Hsu, Soroosh Sorooshian, Yunji Zhang, Fuqing Zhang

Research output: Contribution to journalArticle

Abstract

The effective identification of clouds and monitoring of their evolution are important toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation algorithm is developed using image processing techniques. This method integrates morphological image gradient magnitudes to separate cloud systems and patches boundaries. A varying scale kernel is implemented to reduce the sensitivity of image segmentation to noise and to capture objects with various finenesses of the edges in remote sensing images. The proposed method is flexible and extendable from single to multispectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellite (GOES-16) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potentials comparing to the conventional segmentation technique used in PERSIANN-CCS to improve rain detection and estimation skills with an accuracy rate of up to 98% in identifying cloud regions.

Original languageEnglish (US)
Pages (from-to)901-913
Number of pages13
JournalJournal of Hydrometeorology
Volume20
Issue number5
DOIs
StatePublished - May 1 2019

Fingerprint

cloud classification
satellite imagery
artificial neural network
segmentation
GOES
image processing
radiance
imagery
detection
remote sensing
weather
rainfall
monitoring
prediction
method

All Science Journal Classification (ASJC) codes

  • Atmospheric Science

Cite this

Hayatbini, Negin ; Hsu, Kuo lin ; Sorooshian, Soroosh ; Zhang, Yunji ; Zhang, Fuqing. / Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery : Application to improve PERSIANN-CCS. In: Journal of Hydrometeorology. 2019 ; Vol. 20, No. 5. pp. 901-913.
@article{19219c59c08442c3af984269d9be1b46,
title = "Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery: Application to improve PERSIANN-CCS",
abstract = "The effective identification of clouds and monitoring of their evolution are important toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation algorithm is developed using image processing techniques. This method integrates morphological image gradient magnitudes to separate cloud systems and patches boundaries. A varying scale kernel is implemented to reduce the sensitivity of image segmentation to noise and to capture objects with various finenesses of the edges in remote sensing images. The proposed method is flexible and extendable from single to multispectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellite (GOES-16) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potentials comparing to the conventional segmentation technique used in PERSIANN-CCS to improve rain detection and estimation skills with an accuracy rate of up to 98{\%} in identifying cloud regions.",
author = "Negin Hayatbini and Hsu, {Kuo lin} and Soroosh Sorooshian and Yunji Zhang and Fuqing Zhang",
year = "2019",
month = "5",
day = "1",
doi = "10.1175/JHM-D-18-0197.1",
language = "English (US)",
volume = "20",
pages = "901--913",
journal = "Journal of Hydrometeorology",
issn = "1525-755X",
publisher = "American Meteorological Society",
number = "5",

}

Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery : Application to improve PERSIANN-CCS. / Hayatbini, Negin; Hsu, Kuo lin; Sorooshian, Soroosh; Zhang, Yunji; Zhang, Fuqing.

In: Journal of Hydrometeorology, Vol. 20, No. 5, 01.05.2019, p. 901-913.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Effective cloud detection and segmentation using a gradient-based algorithm for satellite imagery

T2 - Application to improve PERSIANN-CCS

AU - Hayatbini, Negin

AU - Hsu, Kuo lin

AU - Sorooshian, Soroosh

AU - Zhang, Yunji

AU - Zhang, Fuqing

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The effective identification of clouds and monitoring of their evolution are important toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation algorithm is developed using image processing techniques. This method integrates morphological image gradient magnitudes to separate cloud systems and patches boundaries. A varying scale kernel is implemented to reduce the sensitivity of image segmentation to noise and to capture objects with various finenesses of the edges in remote sensing images. The proposed method is flexible and extendable from single to multispectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellite (GOES-16) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potentials comparing to the conventional segmentation technique used in PERSIANN-CCS to improve rain detection and estimation skills with an accuracy rate of up to 98% in identifying cloud regions.

AB - The effective identification of clouds and monitoring of their evolution are important toward more accurate quantitative precipitation estimation and forecast. In this study, a new gradient-based cloud-image segmentation algorithm is developed using image processing techniques. This method integrates morphological image gradient magnitudes to separate cloud systems and patches boundaries. A varying scale kernel is implemented to reduce the sensitivity of image segmentation to noise and to capture objects with various finenesses of the edges in remote sensing images. The proposed method is flexible and extendable from single to multispectral imagery. Case studies were carried out to validate the algorithm by applying the proposed segmentation algorithm to synthetic radiances for channels of the Geostationary Operational Environmental Satellite (GOES-16) simulated by a high-resolution weather prediction model. The proposed method compares favorably with the existing cloud-patch-based segmentation technique implemented in the Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) rainfall retrieval algorithm. Evaluation of event-based images indicates that the proposed algorithm has potentials comparing to the conventional segmentation technique used in PERSIANN-CCS to improve rain detection and estimation skills with an accuracy rate of up to 98% in identifying cloud regions.

UR - http://www.scopus.com/inward/record.url?scp=85066289137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066289137&partnerID=8YFLogxK

U2 - 10.1175/JHM-D-18-0197.1

DO - 10.1175/JHM-D-18-0197.1

M3 - Article

VL - 20

SP - 901

EP - 913

JO - Journal of Hydrometeorology

JF - Journal of Hydrometeorology

SN - 1525-755X

IS - 5

ER -