Main > Laser & Optoelectronics Progress >  Volume 57 >  Issue 20 >  Page 201011 > Article
  • Abstract
  • Abstract
  • View Summary
  • Figures (8)
  • Tables (2)
  • Equations (0)
  • References (24)
  • Get PDF(in Chinese)
  • Paper Information
  • Received: Dec. 24, 2019

    Accepted: Feb. 25, 2020

    Posted: Oct. 1, 2020

    Published Online: Oct. 17, 2020

    The Author Email: Lin Zhiwei (cwlin@fafu.edu.cn), Liu Jinfu (fjljf@126.com)

    DOI: 10.3788/LOP57.201011

  • Get Citation
  • Copy Citation Text

    Suhui Yang, Zhiwei Lin, Shaojun Lai, Jinfu Liu. Precipitation Nowcasting Based on Dual-Flow 3D Convolution and Monitoring Images[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201011

    Download Citation

  • Category
  • Image Processing
  • Share
Laser & Optoelectronics Progress, Vol. 57, Issue 20, 201011 (2020)

Precipitation Nowcasting Based on Dual-Flow 3D Convolution and Monitoring Images

Yang Suhui1, Lin Zhiwei1,3,4,*, Lai Shaojun2, and Liu Jinfu1,5,6,**

Author Affiliations

  • 1College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China
  • 2Fuzhou Meteorological Bureau, Fuzhou, Fujian 350014, China
  • 3College of Forestry, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China
  • 4Forestry Post-Doctoral Station, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China
  • 5Cross-Strait Nature Reserve Research Center, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350002, China
  • 6Key Laboratory of Fujian Universities for Ecology and Resource Statistics, Fuzhou, Fujian 350002, China

Abstract

At present, most of the precipitation nowcasting production is unable to consider the problems of high coverage, high accuracy, and low cost. Therefore, we herein propose a method based on outdoor monitoring images and deep neural network to forecast the rainfall intensity in the next 1 h. We design a dual-flow 3D convolutional neural network to extract high-dimensional features of rainfall information in images. The local information is adaptively generated at a low computational cost, and the temporal and spatial characteristics of rainfall information are extracted by the proposed network which integrates the whole network and the local network using a double loss function. The experimental results show that the neural network based on the dual loss function is better than that based on the single loss function in precipitation intensity forecasting. Percent of doom, false alarm rat, critical success index, and the accuracy of the proposed network are better than those of other models in most cases. In terms of visualization of the model effect, the proposed network can effectively extract the feature information of the precipitation images. Therefore, the proposed precipitation nowcasting method is capable of fine and low-cost precipitation prediction.

keywords

Please Enter Your Email: