Machine Learning Approaches to Extreme Weather Events Forecast in Urban Areas: Challenges and Initial Results

Authors

  • Fabio Porto National Laboratory of Scientific Computing, Petropolis, Brazil
  • Mariza Ferro National Laboratory of Scientific Computing, Petropolis, Brazil
  • Eduardo Ogasawara Federal Center for Technological Education, Rio de Janeiro, Brazil
  • Thiago Moeda National Observatory, Rio de Janeiro, Brazil
  • Claudio Daniel Tenorio de Barros National Laboratory of Scientific Computing, Petropolis, Brazil
  • Anderson Chaves Silva National Laboratory of Scientific Computing, Petropolis, Brazil
  • Rocio Zorrilla National Laboratory of Scientific Computing, Petropolis, Brazil
  • Rafael Silva Pereira National Laboratory of Scientific Computing, Petropolis, Brazil
  • Rafaela Nascimento Castro Federal Center for Technological Education, Rio de Janeiro, Brazil
  • João Victor Silva Federal Center for Technological Education, Rio de Janeiro, Brazil
  • Rebecca Salles Federal Center for Technological Education, Rio de Janeiro, Brazil
  • Augusto José Fonseca Federal Center for Technological Education, Rio de Janeiro, Brazil
  • Juliana Hermsdorff Sistema de Alerta Rio da Prefeitura do Rio de Janeiro, Rio de Janeiro, Brazil
  • Marcelo Magalhães Fundação Instituto de Geotécnica do Município do Rio de Janeiro, Rio de Janeiro, Brazil
  • Vitor Sá Centro de Operações Rio, Rio de Janeiro, Brazil
  • Antônio Adolfo Simões National Laboratory of Scientific Computing, Petropolis, Brazil
  • Carlos Cardoso National Laboratory of Scientific Computing, Petropolis, Brazil
  • Eduardo Bezerra Federal Center for Technological Education, Rio de Janeiro, Brazil

DOI:

https://doi.org/10.14529/jsfi220104

Keywords:

machine learning, rainfall forecast, extreme events

Abstract

Weather forecast services in urban areas face an increasingly hard task of alerting the population on extreme weather events. The hardness of the problem is due to the dynamics of the phenomenon, which challenges numerical weather prediction models and opens an opportunity for Machine Learning (ML) based models that may learn complex mappings between input-output from data. In this paper, we present an ongoing research project which aims at building ML predictive models for extreme precipitation forecast in urban areas, in particular in the Rio de Janeiro City. We present the techniques that we have been developing to improve rainfall prediction and extreme rainfall forecast, along with some initial experimental results. Finally, we discuss some challenges that remain to be tackled in this project.

References

https://www.cosmo-model.org/, accessed: 2021-09-20

https://www.mmm.ucar.edu/weather-research-and-forecasting-model, accessed: 2021-09-20

Agrawal, S., Barrington, L., Bromberg, C., et al.: Machine learning for precipitation nowcasting from radar images. CoRR abs/1912.12132 (2019), http://arxiv.org/abs/1912.12132

Ayzel, G., Scheffer, T., Heistermann, M.: Rainnet v1.0: a convolutional neural network for radar-based precipitation nowcasting. Geoscientific Model Development 13(6), 2631–2644 (2020). https://doi.org/10.5194/gmd-13-2631-2020

Bendre, N., Marn, H.T., Najafirad, P.: Learning from few samples: A survey (2020). https://doi.org/10.48550/ARXIV.2007.15484

Bonnet, S.M., Evsukoff, A., Morales Rodriguez, C.A.: Precipitation Nowcasting with Weather Radar Images and Deep Learning in São Paulo, Brasil. Atmosphere 11(11) (2020). https://doi.org/10.3390/atmos11111157

Castro, R., Souto, Y.M., Ogasawara, E., Porto, F., Bezerra, E.: STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for weather forecasting. Neurocomputing 426, 285–298 (2021). https://doi.org/10.1016/j.neucom.2020.09.060

Czibula, G., Mihai, A., Czibula, I.: RadRAR: A relational association rule mining approach for nowcasting based on predicting radar products values. Procedia Computer Science 176, 300–309 (2020). https://doi.org/10.1016/j.procs.2020.08.032

Czibula, G., Mihai, A., Mihuleţ, E., Teodorovici, D.: Using Self-Organizing Maps for Unsupervised Analysis of Radar Data for Nowcasting Purposes. Procedia Comput. Sci. 159(C), 48–57 (2019). https://doi.org/10.1016/j.procs.2019.09.159

daSilva, F.: Projeto pesquisa operacional (2019), internal Report, in PT

Ding, D., Zhang, M., Pan, X., et al.: Modeling extreme events in time series prediction. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. pp. 1114–1122. KDD ’19, ACM, New York, NY, USA (2019). https://doi.org/10.1145/3292500.3330896

Gates, B.: How to avoid a Climate Disaster: The Solutions We Have and the Breakthroughs We Need. Random House Large Print Publishing (2021)

Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation pp. 52–65 (1997)

Huffman, G., Bolvin, D., Braithwaite, D., et al.: NASA Global Precipitation Measurement (GPM) Integrated Multi-satellitE Retrievals for GPM (IMERG) v5.2. NASA (2014)

Imbalanced Learn: The imbalanced-learn (2021), https://imbalanced-learn.org/stable/

Jaye, A., Bruyère, C.L., Done, J.M.: Understanding future changes in tropical cyclogenesis using Self-Organizing Maps. Weather and climate extremes 26, 100235 (2019)

Karniadakis, G.E., Kevrekidis, I.G., Lu, L., et al.: Physics-informed machine learning. Nature Reviews Physics 3(6), 422–440 (2021). https://doi.org/10.1038/s42254-021-00314-5

Kim, S., Kim, H., Lee, J., et al.: Deep-Hurricane-Tracker: Tracking and Forecasting Extreme Climate Events. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). pp. 1761–1769 (2019). https://doi.org/10.1109/WACV.2019.00192

Kohonen, T.: The self-organizing map. Proceedings of the IEEE 78(9), 1464–1480 (1990). https://doi.org/10.1109/5.58325

Kohonen, T.: Essentials of the self-organizing map. Elsevier - Neural Networks 37, 52–65 (2013). https://doi.org/10.1016/j.neunet.2012.09.018

Liu, Z., Zhou, J.: Introduction to Graph Neural Networks. Morgan & Claypool (2020)

NCAR: NCEP Climate Forecast System Reanalysis (CFSR) 6-hourly Products, January 1979 to December 2010 (2010). https://doi.org/10.5065/D69K487

Pereira, R.: Strategies and techniques for deep learning on small data. Ph.D. thesis, National Laboratory of Scientific Computing (2020)

Pereira, R., Souto, Y., Chaves, A., et al.: DJEnsemble: A Cost-Based Selection and Allocation of a Disjoint Ensemble of Spatio-Temporal Models, pp. 226–231. ACM, New York, NY, USA (2021). https://doi.org/10.1145/3468791.3468806

Ravuri, S., Lenc, K., Willson, M., et al.: Skilful precipitation nowcasting using deep generative models of radar. Nature 597(7878), 672–677 (2021). https://doi.org/10.1038/s41586-021-03854-z

Rousseeuw, P.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics 20, 53–65 (1987), https://wis.kuleuven.be/stat/robust/papers/publications-1987/rousseeuw-silhouettes-jcam-sciencedirectopenarchiv.pdf

Sakoe, Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing 26(1), 43–46 (1978)

Scikit Learn: Scikit-learn: Machine Learning in Python (2011), https://scikit-learn.org/stable/index.html

Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press (2017)

Shi, X., Chen, Z., Wang, H., et al.: Convolutional lstm network: A machine learning approach for precipitation nowcasting. In: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1. pp. 802–810. NIPS’15, MIT Press, Cambridge, MA, USA (2015)

Skiena, S.S.: The Data Science Design Manual, vol. 1. Springer, New York (2017)

Sønderby, C.K., Espeholt, L., Heek, J., et al.: MetNet: A Neural Weather Model for Precipitation Forecasting. CoRR abs/2003.12140 (2020), https://arxiv.org/abs/2003.12140

Song, L., Schicker, I., Papazek, P., et al.: Machine Learning Approach to Summer Precipitation Nowcasting over the Eastern Alps. Meteorologische Zeitschrift 29(4), 289–305 (2020). https://doi.org/10.1127/metz/2019/0977

Souto, Y.M., Porto, F., Moura, A.M., Bezerra, E.: A Spatiotemporal Ensemble Approach to Rainfall Forecasting. In: Proceedings of the International Joint Conference on Neural Networks. pp. 574–581 (2018). https://doi.org/10.1109/IJCNN.2018.8489693

Wang, Y., Coning, E., Harou, A., et al.: Guidelines for Nowcasting Techniques (2017)

Wolpert, D., Macready, W.: No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation 1(1), 67–82 (1997). https://doi.org/10.1109/4235.585893

Xiang, Y., Ma, J., Wu, X.: A precipitation nowcasting mechanism for real-world data based on machine learning. Mathematical Problems in Engineering 2020, 1–11 (2020). https://doi.org/10.1155/2020/8408931

Downloads

Published

2022-05-25

How to Cite

Porto, F., Ferro, M., Ogasawara, E., Moeda, T. ., Tenorio de Barros, C. D., Chaves Silva, A., Zorrilla, R., Silva Pereira, R. ., Nascimento Castro, R. ., Silva, J. V., Salles, R., Fonseca, A. J., Hermsdorff, J., Magalhães, M., Sá, V., Simões, A. A., Cardoso, C., & Bezerra, E. . (2022). Machine Learning Approaches to Extreme Weather Events Forecast in Urban Areas: Challenges and Initial Results. Supercomputing Frontiers and Innovations, 9(1), 49–73. https://doi.org/10.14529/jsfi220104

Issue

Vol. 9 No. 1 (2022)

License

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-Non Commercial 3.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.