DeepLab Network for Meteorological Trough Line Recognition
Authors: 
Yali Cai, Qian LiAuthors Info & Claims
Pages 36 - 41
Abstract
A meteorological trough line recognition method is proposed in this paper, in which a DeepLab network that adopts an encoder-decoder architecture is utilized to classify each point in the meteorological grid data into two categories: trough point or not, and then the trough area with the strongest horizontal convergence in the low-pressure area will be identified. The meteorological elements data related to the formation of trough includes the air pressure, the wind velocity and the temperature on 500hp, while the labels are marked with trough lines manually, they are used to train the network model. The proposed method first uses the Deeplab model to recognize the trough area from the meteorological elements data and then extracts the trough line from the trough area by skeleton line extraction algorithm. To evaluate our proposed method, the quantitative experiments were conducted and the results show us that the precission rate of proposed method performances better than the traditional method.
References
[1]
Allen G L, Cowan C R M, Power H, “Acquiring information from simple weather maps: Influences of domain-specific knowledge and general visual–spatial abilities,” Learning and Individual Differences, vol. 16, no. 4, pp. 337-349, 2006
[2]
D Mechem, An Introduction to Dynamic Meteorology (Fifth Edition), 2013.
[3]
ALLACE, John M, Atmospheric science: an introductory survey, Elsevier, 2006.
[4]
Peiyuan Z, “The characters of mesoscale structures near the trough line——analysis of Doppler wind measurements,” Meteorological Monthly, 1991.
[5]
Long J, Shelhamer E, Darrell T, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 4, pp. 640-651, 2015.
[6]
Chen L C, Papandreou G, Schroff F, & Adam, H, “Rethinking Atrous Convolution for Semantic Image Segmentation,” 2017.
[7]
Meiying Y, Nanping X, Zhendong Y, “A Test of Recognition of Centres of High and Low Pressure and Trough-Line,” METEOROLOGICAL MONTHLY, 1994.
[8]
Yuan M, Xu N, Yu Z, “A Test of Recognition of Centres of High and Low Pressure and Trough-Line,” METEOROLOGICAL MONTHLY, 1994.
[9]
Peter Knippertz, “A Simple Identification Scheme for Upper-Level Troughs and Its Application to Winter Precipitation Variability in Northwest Africa,” Journal of Climate, vol. 17, no. 6, pp. 1411–1418, 2010.
[10]
Qian L, Yan H, Yin F, “Automatic Analysis of Trough Lines Based on Curvature Tracing,” Atmosphere, vol. 9, no. 3, pp. 88, 2018.
[11]
Yoo H J, “Deep Convolution Neural Networks in Computer Vision: a Review,” Ieie Transactions on Smart Processing & Computing, vol. 4, no. 1, pp. 35-43, 2015.
[12]
Au O K C, Tai C L, Chu H K, “Skeleton extraction by mesh contraction,” ACM transactions on graphics (TOG), vol. 27, no. 3, pp. 1-10, 2008.
[13]
Chen L C, Papandreou G, Schroff F, “Rethinking Atrous Convolution for Semantic Image Segmentation,” 2017.
[14]
Chen L C, Zhu Y, Papandreou G, “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,” European Conference on Computer Vision, 2018.
[15]
Chollet F, “Xception: Deep Learning with Depthwise Separable Convolutions,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
[16]
Zhang Z, Sabuncu M R, “Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels,” 2018.
[17]
Gong Y, Li J, “The quantified verification method of synoptic meteorology and the application to AREM,” Scientia Meteorologica Sinica, vol. 30, no. 6, pp.763-772, 2010.
[18]
Changjian Y, Wendong H, Chunmei Z, “Auto-analysis of Trough System at 500 hPa Based on Gradient Algorithm,” Journal of Applied Meteorological ence, 2016.
Recommendations
A neural network-based local rainfall prediction system using meteorological data on the Internet
Display Omitted Local rainfall prediction system based on neural networks (NNs) using meteorological data obtained from the Internet is developed, and local rainfall prediction in Japan using data from the website of Japan Meteorological Agency (JMA) is ...
Supercomputer-based visualization systems used for analyzing output data of a numerical weather prediction model
ICS '90: Proceedings of the 4th international conference on SupercomputingComparison of two supercomputer-based visualization systems developed over a half-year period show that the visualization/animation efficiency is largely dependent upon the efficiencies of individual computers, networking, and memory management.
Using a ...
A customisable downscaling approach for local-scale meteorological and air pollution forecasting: Performance evaluation for a year of urban meteorological forecasts
In this paper we develop a customisable downscaling approach for local-scale air quality and meteorological forecasting applications, using The Air Pollution Model (TAPM) with the Conformal Cubic Atmospheric Model (CCAM). The CCAM-TAPM system allows ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2021
81 pages
ISBN:9781450385725
DOI:10.1145/3502814
Copyright © 2021 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 11 April 2022
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- the National Natural Science Foundation of China
- Hunan Province Natural Science Fund
- the National Key Research and Development Program of China
- the China Postdoctoral Science Foundation
Conference
SSIP 2021
SSIP 2021: 2021 4th International Conference on Sensors, Signal and Image Processing
October 15 - 17, 2021
Nanjing, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 24Total Downloads
- Downloads (Last 12 months)9
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format