Detecting Comma-Shaped Clouds for Severe Weather Forecasting Using Shape and Motion

Xinye Zheng, Jianbo Ye, Yukun Chen, Steve Wistar, Jia Li, Jose A. Piedra Fernández, Michael A. Steinberg, James Wang

Research output: Contribution to journalArticle

Abstract

Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Yet, because satellite image data are in increasingly higher resolution, both spatially and temporally, meteorologists cannot fully leverage the data in their forecasts. Automatic satellite image analysis methods that can find storm-related cloud patterns are thus in demand. We propose a machine learning and pattern recognition-based approach to detect 'comma-shaped' clouds in satellite images, which are specific cloud distribution patterns strongly associated with cyclone formulation. In order to detect regions with the targeted movement patterns, we use manually annotated cloud examples represented by both shape and motion-sensitive features to train the computer to analyze satellite images. Sliding windows in different scales ensure the capture of dense clouds, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud data set and cross match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.

Original languageEnglish (US)
Article number8606456
Pages (from-to)3788-3801
Number of pages14
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume57
Issue number6
DOIs
StatePublished - Jun 1 2019

Fingerprint

Weather forecasting
severe weather
weather forecasting
Satellites
sliding
Image analysis
Pattern recognition
Learning systems
pattern recognition
image analysis
cyclone
train
satellite image

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

Cite this

Zheng, Xinye ; Ye, Jianbo ; Chen, Yukun ; Wistar, Steve ; Li, Jia ; Piedra Fernández, Jose A. ; Steinberg, Michael A. ; Wang, James. / Detecting Comma-Shaped Clouds for Severe Weather Forecasting Using Shape and Motion. In: IEEE Transactions on Geoscience and Remote Sensing. 2019 ; Vol. 57, No. 6. pp. 3788-3801.
@article{765d9d28b02b4483b1bbeb5f1fe55081,
title = "Detecting Comma-Shaped Clouds for Severe Weather Forecasting Using Shape and Motion",
abstract = "Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Yet, because satellite image data are in increasingly higher resolution, both spatially and temporally, meteorologists cannot fully leverage the data in their forecasts. Automatic satellite image analysis methods that can find storm-related cloud patterns are thus in demand. We propose a machine learning and pattern recognition-based approach to detect 'comma-shaped' clouds in satellite images, which are specific cloud distribution patterns strongly associated with cyclone formulation. In order to detect regions with the targeted movement patterns, we use manually annotated cloud examples represented by both shape and motion-sensitive features to train the computer to analyze satellite images. Sliding windows in different scales ensure the capture of dense clouds, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud data set and cross match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.",
author = "Xinye Zheng and Jianbo Ye and Yukun Chen and Steve Wistar and Jia Li and {Piedra Fern{\'a}ndez}, {Jose A.} and Steinberg, {Michael A.} and James Wang",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/TGRS.2018.2887206",
language = "English (US)",
volume = "57",
pages = "3788--3801",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

Detecting Comma-Shaped Clouds for Severe Weather Forecasting Using Shape and Motion. / Zheng, Xinye; Ye, Jianbo; Chen, Yukun; Wistar, Steve; Li, Jia; Piedra Fernández, Jose A.; Steinberg, Michael A.; Wang, James.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 6, 8606456, 01.06.2019, p. 3788-3801.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Detecting Comma-Shaped Clouds for Severe Weather Forecasting Using Shape and Motion

AU - Zheng, Xinye

AU - Ye, Jianbo

AU - Chen, Yukun

AU - Wistar, Steve

AU - Li, Jia

AU - Piedra Fernández, Jose A.

AU - Steinberg, Michael A.

AU - Wang, James

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Yet, because satellite image data are in increasingly higher resolution, both spatially and temporally, meteorologists cannot fully leverage the data in their forecasts. Automatic satellite image analysis methods that can find storm-related cloud patterns are thus in demand. We propose a machine learning and pattern recognition-based approach to detect 'comma-shaped' clouds in satellite images, which are specific cloud distribution patterns strongly associated with cyclone formulation. In order to detect regions with the targeted movement patterns, we use manually annotated cloud examples represented by both shape and motion-sensitive features to train the computer to analyze satellite images. Sliding windows in different scales ensure the capture of dense clouds, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud data set and cross match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.

AB - Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Yet, because satellite image data are in increasingly higher resolution, both spatially and temporally, meteorologists cannot fully leverage the data in their forecasts. Automatic satellite image analysis methods that can find storm-related cloud patterns are thus in demand. We propose a machine learning and pattern recognition-based approach to detect 'comma-shaped' clouds in satellite images, which are specific cloud distribution patterns strongly associated with cyclone formulation. In order to detect regions with the targeted movement patterns, we use manually annotated cloud examples represented by both shape and motion-sensitive features to train the computer to analyze satellite images. Sliding windows in different scales ensure the capture of dense clouds, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud data set and cross match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.

UR - http://www.scopus.com/inward/record.url?scp=85066611927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066611927&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2018.2887206

DO - 10.1109/TGRS.2018.2887206

M3 - Article

AN - SCOPUS:85066611927

VL - 57

SP - 3788

EP - 3801

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 6

M1 - 8606456

ER -