Clustering of spatio-temporal precipitation patterns in the Legal Amazon using deep convolutional autoencoder
DOI:
https://doi.org/10.5902/2179460X85042Keywords:
Machine learning, Deep convolutional autoencoder, Clustering, Pattern recognition, Precipitation time seriesAbstract
Identifying patterns in precipitation time series in a given region is fundamental for its socioeconomic development. Many studies on this topic have been carried out in Brazil, mainly in the Amazon region. This research aimed at the development of a computational method for analyzing time series of precipitation using machine learning techniques, aiming at a method capable of extracting complex characteristics from the data, obtaining a map of attributes in low dimensionality for pattern recognition and discovery of homogeneous regions with respect to precipitation in the Legal Amazon. The proposed model is trained to learn the main and most complex characteristics of the original data and present them in low dimensionality in latent space. After training, the observations of the reconstructed data showed good performance as evaluated by the RMSE and NRMSE metric with resulting values equal to 0.06610 and 0.3355 respectively. The result of the low-dimensional representation of the data was analyzed by a clustering structure using hierarchical clustering with Ward's method. This methodology carried out consistent groupings characterizing homogeneous regions in relation to precipitation data. In this way, demonstrating that the representation in low dimensionality carried the main characteristics of the time series of the studied data.
Downloads
References
Amanaj´as, J. C. & Braga, C. C. (2012). Padr˜oes espac¸ o-temporal pluviom´etricos na amazˆonia oriental utilizando an´alise multivariada. Revista Brasileira de Meteorologia, 27:423–434. DOI: https://doi.org/10.1590/S0102-77862012000400006
Baia, A. F. & Castro, A. R. G. (2018). A Competitive Structure of Convolutional Autoencoder Networks for Electrocardiogram Signals Classification. In Anais do XV Encontro Nacional de Inteligˆencia Artificial e Computacional. (pp. 538-549). Porto Alegre: SBC. DOI: https://doi.org/10.5753/eniac.2018.4446
Bail˜ao, A. S. d. O. et al. (2020). Reconhecimento de padr˜oes por processos adaptativos de compress˜ao (Dissertação de Metsrado). Universidade Federal de Goi´as, Goiˆania, GO, Brasil.
Bhavsar, P., Safro, I., Bouaynaya, N., Polikar, R., & Dera, D. (2017). Machine learning in transportation data analytics. In Data analytics for intelligent transportation systems. (pp. 283-307). Elsevier. DOI: https://doi.org/10.1016/B978-0-12-809715-1.00012-2
Crispim, D. L., Fernandes, L. L., Ferreira Filho, D. F., & Lira, B. R. P. (2020). Comparação de m´etodos de agrupamentos hier´arquicos aglomerativos em indicadores de sustentabilidade em munic´ıpios do estado do par´a. Research, Society and Development, 9(2):e60922067–e60922067. DOI: https://doi.org/10.33448/rsd-v9i2.2067
Cruz, E. B. et al. (2016). Representac¸ ˜ao de s´eries temporais usando descritores de forma
aplicados a recurrence plots (Dissertação de Mestrado). Universidade Estadual de Campinas, Campinas, SP, Brasil.
Dourado, C. d. S., Oliveira, S. R. d. M., & Avila, A. M. H. d. (2013). An´alise de zonas homogˆeneas em s´eries temporais de precipitação no estado da bahia. Bragantia, 72(2):192–198. DOI: https://doi.org/10.1590/S0006-87052013000200012
Esling, P. & Agon, C. (2012). Time-series data mining. ACM Computing Surveys (CSUR), 45(1):1–34. DOI: https://doi.org/10.1145/2379776.2379788
Essien, A. & Giannetti, C. (2020). A deep learning model for smart manufacturing using convolutional lstm neural network autoencoders. IEEE Transactions on Industrial Informatics, 16(9):6069–6078. DOI: https://doi.org/10.1109/TII.2020.2967556
Gonc¸ alves, E. D., Pessoa, F. C. L., Neves, R. R., Rodrigues, R. S. S., & de Sousa, A. C. S. R. (2017). Identificação de regi˜oes homogˆeneas e an´alise de regress˜ao m´ultipla para regionalização de vaz˜ao na bacia hidrogr´afica do rio tapaj´os. Revista Brasileira deCartografia, 69(9). DOI: https://doi.org/10.14393/rbcv69n9-44082
Granzotti, R. A. (2020). Extrac¸ ˜ao de caracter´ısticas via autoencoders aplicada a interfaces c´erebro-computador baseadas em potenciais evocados visualmente em regime estacion´ario. (Tese de Doutorado). Faculdade de Engenharia El´etroca e de Computação, Universidade Estadual de Campinas, Campinas, SP, Brasil.
Guarienti, G. S. S. et al. (2015). Desenvolvimento de uma t´ecnica computacional de processamento espaço-temporal aplicada em s´eries de precipitac¸ção(Dissertação de Metrado). Universidade Federal de Mato Grosso, Cuiab´a, MS, Brasil˜ao.
Huang, H., Hu, X., Zhao, Y., Makkie, M., Dong, Q., Zhao, S., Guo, L., & Liu, T. (2017). Modeling task fmri data via deep convolutional autoencoder. IEEE transactions on medical imaging, 37(7):1551–1561. DOI: https://doi.org/10.1109/TMI.2017.2715285
Kingma, D. P. & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Lira, B. R. P., Crispim, D. L., Ferreira Filho, D. F., Fernandes, L. L., & Pessoa, F. C. L. (2020a). Agrupamento de Precipitac¸ ˜ao no estado do (Par´a), Brasil. Revista de Gest˜ao de ´Aguas da Am´erica Latina, 17(19). DOI: https://doi.org/10.21168/rega.v17e19
Lira, B. R. P. et al. (2019). Avaliação do comportamento e da tendˆencia pluviom´etrica na Amazˆonia Legal no Per´ıodo de 1986 a 2015 (Dissertac¸ ˜ao de Mestrado). Universidade Federal do Par´a, Bel´em, PA, Brasil.
Lira, B. R. P., Lopes, L. d. N. A., das Chaves, J. R., Santana, L. R., & Fernandes, L. L. (2020b). Identificação de Homogeneidade, Tendˆencia e Magnitude da Precipitação em Bel´em (Par´a) entre 1968 e 2018. Anu´ario do Instituto de Geociˆencias, 43(4), 426–439. DOI: https://doi.org/10.11137/2020_4_426_439
Maggioni & Silva, A. (2016). Classificac¸ ˜ao de s´eries temporais baseada em an´alise de recorrˆencia e extrac¸ ˜ao de caracter´ısticas (Dissertac¸ ˜ao de Mestrado). Universidade Federal de Mato Grosso do Sul, Campo Grande, MS, Brasil.
Masci, J., Meier, U., Cires¸ an, D., & Schmidhuber, J. (2018). Stacked convolutional auto-encoders for hierarchical feature extraction. In International conference on artificial neural networks. (pp. 52-59). Springer. DOI: https://doi.org/10.1007/978-3-642-21735-7_7
Menezes, F. P., Fernandes, L. L., & da Rocha, E. J. P. (2015). O uso da estat´ıstica para regionalização da precipitação no Estado do Par´a, Brasil. Revista Brasileira de Climatologia, 16. DOI: https://doi.org/10.5380/abclima.v16i0.40023
Neves, R. R., Gonc¸ alves, E. D., Pessoa, F. C. L., Fernandes, L. L., G´omez, Y. D., & dos Santos, J. I. N. (2017). Identificac¸ ˜ao de regi˜oes pluviometricamente homogˆeneas na sub bacia trombetas. Revista AIDIS de Ingenier´ıa y Ciencias Ambientales. Investigaci´on, desarrollo y pr´actica, 10(2):125–135.
S´a, J. E. F. C. S. d. (2023). Aplicação de T´ecnicas de Ciˆencia de Dados na Previs˜ao de Consumos Energ´eticos (Mestrado em Ciˆencia de Dados). Instituto Polit´ecnico de Leiria, Leiria, Portugal.
Santos, E. B., Lucio, P. S., & Silva, C. M. S. e. (2015). Precipitation regionalization of the brazilian amazon. Atmospheric Science Letters, 16(3):185–192. DOI: https://doi.org/10.1002/asl2.535
Severo, D. L., dos Santos Silva, H., & Tachini, M. (2019). Flutuações clim´aticas da precipitação no vale do itaja´ı (sc). Revista de Estudos Ambientais, 20(2):37–48. DOI: https://doi.org/10.7867/1983-1501.2018v20n2p37-48
Yin, C., Zhang, S., Wang, J., & Xiong, N. N. (2020). Anomaly detection based on convolutional recurrent autoencoder for iot time series. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 52(1), 112-122. DOI: https://doi.org/10.1109/TSMC.2020.2968516
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Ciência e Natura
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.
