Next Article in Journal
Satellite-Based Estimation of Daily Ground-Level PM2.5 Concentrations over Urban Agglomeration of Chengdu Plain
Previous Article in Journal
Emission Factors Derived from 13 Euro 6b Light-Duty Vehicles Based on Laboratory and On-Road Measurements
Article Menu

Export Article

Open AccessArticle

Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks

1,2,† and 1,2,*,†
1
Department of Big Data Science, University of Science and Technology (UST), Daejeon 34113, Korea
2
Research Data Sharing Center, Division of National Science and Technology Data, Korea Institute of Science and Technology Information (KISTI), Daejeon 34141, Korea
*
Author to whom correspondence should be addressed.
Current address of affiliation 2: (34141) 245 Daehak-ro, Yuseong-gu, Daejeon, Korea.
Atmosphere 2019, 10(5), 244; https://doi.org/10.3390/atmos10050244
Received: 22 April 2019 / Revised: 26 April 2019 / Accepted: 26 April 2019 / Published: 2 May 2019
(This article belongs to the Section Climatology and Meteorology)
  |  
PDF [1089 KB, uploaded 2 May 2019]
  |  

Abstract

This paper presents a viewpoint from computer vision to the radar echo extrapolation task in the precipitation nowcasting domain. Inspired by the success of some convolutional recurrent neural network models in this domain, including convolutional LSTM, convolutional GRU and trajectory GRU, we designed a new sequence-to-sequence neural network structure to leverage these models in a realistic data context. In this design, we decreased the numbers of channels in high abstract recurrent layers rather than increasing them. We formulated the task as a problem of encoding five radar images and predicting 10 steps ahead at the pixel level, and found that using only the common mean squared error can misguide the training and mislead the testing. Especially, the image quality of last predictions usually degraded rapidly. As a solution, we employed some visual image quality assessment techniques including Structural Similarity (SSIM) and multi-scale SSIM to train our models. Experimental results show that our structure was more tolerant to increasing uncertainty in the data, and the use of image quality metrics can significantly reduce the blurry image issue. Moreover, we found that using SSIM was very effective and a combination of SSIM with mean squared error and mean absolute error yielded the best prediction quality. View Full-Text
Keywords: convolutional LSTM; convolutional GRU; trajectory GRU; precipitation nowcasting; radar echo extrapolation; image quality assessment convolutional LSTM; convolutional GRU; trajectory GRU; precipitation nowcasting; radar echo extrapolation; image quality assessment
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Tran, Q.-K.; Song, S.-K. Computer Vision in Precipitation Nowcasting: Applying Image Quality Assessment Metrics for Training Deep Neural Networks. Atmosphere 2019, 10, 244.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Atmosphere EISSN 2073-4433 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top