Recurrent Neural Networks applied to short-term weather forecasting using radar images from the city of Chapecó, SC, Brazil

Authors

DOI:

https://doi.org/10.5902/2179460X87262

Keywords:

Recurrent neural networks, Nowcasting, Radar, Meteorology

Abstract

This work proposes a new computational approach that makes use of Recurrent Convolutional Neural Networks, in which weather radar images a r e used to predict the spread and intensity of storms up to 3 hours in advance, known as nowcasting. To this end, we used images from the meteorological radar located in the city of Chapecó - SC. This data is public and available on the website of the Institute for Space Research (INPE). To this end, we propose to evaluate the use of a recurrent convolutional neural network with spatiotemporal learning called PredRNN++. The results were validated through case studies of storms that occurred in the region covered by the radar used. To evaluate the performance of the neural network, in addition to a visual analysis of the results, the MSE and SSIM metrics were used. The results show that PredRNN++ was able to simulate the shape and location of the weather system.

Downloads

Download data is not yet available.

Author Biographies

Felipe Copceski Rossatto, Universidade Federal de Pelotas

Holds a bachelor's degree in Mathematics from the Regional Integrated University of Alto Uruguai and Missions (2019) and a master's degree in Mathematical Modeling from the Federal University of Pelotas (2023). He has experience in the area of Mathematics, with an emphasis on Mathematics.

Fabrício Pereira Härter, Universidade Federal de Pelotas

He holds a bachelor's degree in Meteorology from the Federal University of Pelotas (1995), a master's degree in Meteorology from the National Institute for Space Research (1999) and a PhD in Applied Computing from the National Institute for Space Research (2004) with a postdoctoral degree from the University of Waterloo (2006). He worked with weather forecasting for the media and agriculture, was a research assistant in a project on satellite precipitation estimates, participated in the Brazilian Antarctic Program and consulted for the World Meteorological Organization, together with the National Institute of Meteorology. Its priority line of research is the assimilation of meteorological data (neural networks, Kalman filtering and variational methods) and the initialization of numerical models.  He is currently an Associate Professor at the Federal University of Pelotas (UFPel), a permanent member of the Graduate Program in Mathematical Modeling, a member of the Structuring Teaching Nucleus of the collegiate of the Undergraduate Course in Meteorology, of the Departmental Council of the Faculty of Meteorology.

Elcio Hideiti Shiguemori, Instituto de Estudios Avanzados

He is a Researcher at the Institute for Advanced Studies (IEAv) of the Department of Aerospace Science and Technology (DCTA). PhD in applied computing from the National Institute for Space Research (INPE) (2007). He holds a Master's degree in Applied Computing from INPE (2002), a degree in Computer Engineering (1998) and a degree in Computer Science from UBC (1999). He is a professor in the Graduate Program in Applied Computing at INPE and a professor in the PG-CTE Graduate Program at ITA. He is a professor at Universidade Paulista (UNIP) and coordinator of the Computer Engineering course. He has experience in the area of Computing, working mainly on the following topics: Artificial Intelligence, Machine Learning, Data Science, Autonomous Air Navigation, Image Processing and Computer Vision.

Leonardo Calvetti, Universidade Federal de Pelotas

Holds a degree in Meteorology from the Federal University of Pelotas (1998), a master's degree (2002) and a PhD (2011) in Meteorology from the University of São Paulo. He worked as a research meteorologist at Simepar until January 2016. He is currently a professor at the Faculty of Meteorology at UFPel working in the areas of meteorological radar, nowcasting, mesoscale, hydrometeorology and numerical weather forecasting.

References

Browning, K. A. (1989). Nowcasting of precipitation systems. Reviews of Geophysics, 27, 345-370. doi: 10.1029/RG027i003p00345.

Camporeale, E. (2019). The challenge of machine learning in space weather: Nowcasting and forecasting. Space Wheater, 11, 1166-1207. doi: 10.48550/arXiv.1903.05192.

Hyndman, R. J., Koehler, A. B. (2006). Another look at measures of forecast accuracy. International journal of forecasting, 22, 679-688. doi: 10.1016/j.ijforecast.2006.03.001.

Wang, Y., Gao, Z., Long, M., Wang, J., Philip, S. Y. (2018). Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. Internacional Conference on Machine Learning, 5123-5132. doi: 10.48550/arXiv.1804.06300.

Wang, Z., Bovic, A. C., Sheikh, H. R., Simoncelli, E. P. (2004). Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. doi: 10.1109/TIP.2003.819861.

Downloads

Published

2024-11-04

How to Cite

Rossatto, F. C., Härter, F. P., Shiguemori, E. H., & Calvetti, L. (2024). Recurrent Neural Networks applied to short-term weather forecasting using radar images from the city of Chapecó, SC, Brazil. Ciência E Natura, 46(esp. 1), e87262. https://doi.org/10.5902/2179460X87262

Issue

Vol. 46 No. esp. 1 (2024): ERMAC e ENMC

Section

Special Edition 1

License

Copyright (c) 2024 Ciência e Natura

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

To access the DECLARATION AND TRANSFER OF COPYRIGHT AUTHOR’S DECLARATION AND COPYRIGHT LICENSE click here.

 

Ethical Guidelines for Journal Publication

The Ciência e Natura journal is committed to ensuring ethics in publication and quality of articles. 

Conformance to standards of ethical behavior is therefore expected of all parties involved: Authors, Editors, Reviewers, and the Publisher.

In particular, 

Authors: Authors should present an objective discussion of the significance of research work as well as sufficient detail and references to permit others to replicate the experiments. Fraudulent or knowingly inaccurate statements constitute unethical behavior and are unacceptable. Review Articles should also be objective, comprehensive, and accurate accounts of the state of the art. The Authors should ensure that their work is entirely original works, and if the work and/or words of others have been used, this has been appropriately acknowledged. Plagiarism in all its forms constitutes unethical publishing behavior and is unacceptable. Submitting the same manuscript to more than one journal concurrently constitutes unethical publishing behavior and is unacceptable. Authors should not submit articles describing essentially the same research to more than one journal. The corresponding Author should ensure that there is a full consensus of all Co-authors in approving the final version of the paper and its submission for publication.

Editors: Editors should evaluate manuscripts exclusively on the basis of their academic merit. An Editor must not use unpublished information in the editor's own research without the express written consent of the Author. Editors should take reasonable responsive measures when ethical complaints have been presented concerning a submitted manuscript or published paper.

Reviewers: Any manuscripts received for review must be treated as confidential documents. Privileged information or ideas obtained through peer review must be kept confidential and not used for personal advantage. Reviewers should be conducted objectively, and observations should be formulated clearly with supporting arguments, so that Authors can use them for improving the paper. Any selected Reviewer who feels unqualified to review the research reported in a manuscript or knows that its prompt review will be impossible should notify the Editor and excuse himself from the review process. Reviewers should not consider manuscripts in which they have conflicts of interest resulting from competitive, collaborative, or other relationships or connections with any of the authors, companies, or institutions connected to the papers.

Most read articles by the same author(s)