Abstract
In this article, a nowcasting technique for meteorological radar images based on a generative neural network is presented. This technique’s performance is compared with state-of-the-art optical flow procedures. Both methods have been validated using a public domain data set of radar images, covering an area of about 104 km2 over Japan, and a period of five years with a sampling frequency of five minutes. The performance of the neural network, trained with three of the five years of data, forecasts with a time horizon of up to one hour, evaluated over one year of the data, proved to be significantly better than those obtained with the techniques currently in use.
Highlights
Forecasting precipitation at very high resolutions in space and time, with the aim of providing the boundary conditions for hydrological models and estimating the associated risk, is one of the most difficult challenges in meteorology [1]
The results obtained in [23] show that in case of real video sequence the best results are achieved with the minimization of e0 only, i.e., the mean absolute error (MAE) between the calculated and the actual image
The performance of NN, ST, SP, DR, LK nowcasting techniques described in the Sections 2 and 3, were assessed for 2017
Summary
Forecasting precipitation at very high resolutions in space and time, with the aim of providing the boundary conditions for hydrological models and estimating the associated risk, is one of the most difficult challenges in meteorology [1]. There are several nowcasting procedures for radar images and related by-products based on OF, operational in meteorological centers, that are able to provide predictions with appreciable skills with a time horizon of up to three hours [11,12], when used with additional information from numerical model’s data, and real-time precipitation measurements. For this reason, the topic, widely investigated, is still of interest for research [13].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
