A STUDY OF THE STANDARDIZED PRECIPITATION INDEX (SPI) AND MACHINE LEARNING TECHNIQUES FOR DROUGHT PREDICTION IN THE STATE OF PARAÍBA, BRAZIL
DOI:
https://doi.org/10.47820/recima21.v5i10.5736Keywords:
SPI, Drought, Machine LearnigAbstract
This study aimed to identify and analyze droughts in Paraíba, using the Standardized Precipitation Index (SPI) and machine learning algorithms for predicting SPI for the subsequent years (2020-2021) at six rainfall stations distributed across the mesoregions of Paraíba. The Precipitation data were downloaded from the Global Precipitation Climatology Centre (GPCC) and the National Oceanic and Atmospheric Administration (NOAA) database, covering the period from 1991 to 2019. Three machine learning algorithms were selected based on their ability to fit historical SPI data: Extra Trees Regressor, Gradient Boosting Regressor, and Random Forest Regressor. The applied machine learning models yielded satisfactory results, with the Extra Trees Regressor consistently producing the highest R² value across all stations, indicating high data explainability. The predictions were analyzed to determine their accuracy and reliability, providing valuable insights into precipitation variability and drought occurrence in different mesoregions of Paraíba. In conclusion, this study contributed to understanding climate variability and its implications in Paraíba, offering valuable insights into drought occurrence and the importance of adaptive approaches to mitigate adverse impacts. The application of SPI and machine learning techniques proved effective in analyzing and predicting precipitation, providing an objective approach to characterizing drought and rainfall intensity in specific regions.
Downloads
References
ALFIAN, G.; SYAFRUDIN, M.; FAHRURROZI, I.; FITRIYANI, N. L.; ATMAJI, F. T. D.; WIDODO, T.; BAHIYAH, N.; BENES, F.; RHEE, J. Predicting Breast Cancer from Risk Factors Using SVM and Extra-Trees-Based Feature Selection Method. Computers, v. 11, p. 136, 2022. Disponível em: https://doi.org/10.3390/computers11090136. Acesso em: 28 set. 2023. DOI: https://doi.org/10.3390/computers11090136
BREIMAN, L. Random Forests. Machine Learning, v. 45, p. 5-32, 2001. DOI: https://doi.org/10.1023/A:1010933404324
CUTLER, A.; CUTLER, D. R.; STEVENS, J. R. Random Forests. In: ZHANG, C.; MA, Y. (Ed.). Ensemble Machine Learning: Methods and Applications. [S. l.]: Springer, 2011. cap. 5, p. 157-176. DOI: 10.1007/978-1-4419-9326-7_5. DOI: https://doi.org/10.1007/978-1-4419-9326-7_5
DA SILVA, A. S. A.; MENEZES, R. S. C.; STOSIC, T. Análise multifractal do índice de precipitação padronizado. Research, Society and Development, v. 10, n. 7, p.e24710716535-e24710716535, 2021. DOI: https://doi.org/10.33448/rsd-v10i7.16535
DE FARIAS, A. A.; SOUZA, J. T. A.; De Sousa, F. D. A. S. IDENTIFICAÇÃO E ANÁLISE DE SECAS SEVERAS E EXTREMAS NO MUNICÍPIO DE TAPEROÁ-PB. Revista Brasileira de Geografia Física, v. 07, n. 05, especial- VIWMCRHPE, p. 818-826, 2014. DOI: https://doi.org/10.26848/rbgf.v7.5.p818-826
DE SOUZA GUEDES, R. V.; MACEDO, M. J. H.; DE SOUZA, F. D. A. S. Análise espacial de eventos de secas com base no índice padronizado de precipitação e análise de agrupamento. Brazilian Journal of Environmental Sciences (Online), v. 23, p. 55-65, 2012.
DIDÁTICA TECH. Como funciona o algoritmo ExtraTrees. [S. l.]: Didativa Tech, s. d. Disponível em: https://didatica.tech/como-funciona-o-algoritmo-extratrees/. Acesso em: 28 set. 2023.
FILHO, M. MAE (Erro Médio Absoluto) Em Machine Learning. [S. l.: s. n.], s. d. Disponível em: https://mariofilho.com/mae-erro-medio-absoluto-em-machine-learning/. Acesso em: 28 set. 2023.
FRIEDMAN, Jerome H. “Greedy Function Approximation: A Gradient Boosting Machine.” The Annals of Statistics, v. 29, n. 5, p. 1189–1232, 2001. http://www.jstor.org/stable/2699986. DOI: https://doi.org/10.1214/aos/1013203451
HASAN, H.; RADI, N. A.; KASSIM, S. Modeling of extreme temperature using generalized extreme value (GEV) distribution: A case study of Penang. In: Proceedings of the world congress on engineering, v. 1, p. 181-186, july 2012.
ICMC JÚNIOR. Random Forest. [S. L.]: ICMC Junior, s. d. Disponível em: https://icmcjunior.com.br/random-forest/. Acesso em: Acesso em: 28 set. 2023.
MACEDO, M. J. H.; DE SOUZA GUEDES, R. V.; DE ASSIS SALVIANO, F. D. A. Monitoramento e intensidade das secas e chuvas na cidade de Campina Grande/PB. Revista Brasileira de Climatologia, v. 8, 2011. DOI: https://doi.org/10.5380/abclima.v8i0.25797
MACEDO, M. J. H.; DE SOUZA GUEDES, R. V.; DE SOUZA, F. D. A. S.; DA CUNHA DANTAS, F. R. Análise do índice padronizado de precipitação para o estado da Paraíba, Brasil. Ambiente & Água - An Interdisciplinary Journal of Applied Science, v. 5, n. 1, p. 204-214, 2010.
MASUI, T. All You Need to Know about Gradient Boosting Algorithm − Part 1. Regression. Towards Data Science, [S. l.], 20 jan. 2022. Disponível em: https://towardsdatascience.com/all-you-need-to-know-about-gradient-boosting-algorithm-part-1-regression-2520a34a502. Acesso em: 28 set. 2023.
MATHBOUT, S.; LOPEZ-BUSTINS, J. A.; MARTIN-VIDE, J.; BECH, J.; RODRIGO, F. S. Spatial and temporal analysis of drought variability at several time scales in Syria during 1961–2012. Atmospheric Research, v. 200, p. 153-168, 2018. DOI: https://doi.org/10.1016/j.atmosres.2017.09.016
MATPLOTLIB. Documentação estável. [S. l.]: MATPLOTLIB, s. d. Disponível em: https://matplotlib.org/stable/index.html. Acesso em: 20 ago. 2023.
MCKEE, T. B.; DOESKEN, N. J.; KLEIST, J. The relationship of drought frequency and duration to time scales. In: Proceedings of the 8th Conference on Applied Climatology, v. 17, n. 22, p. 179-183, 1993, jan. 1993.
OTCHERE, D. A.; GANAT, T. O. A.; OJERO, J. O.; TACKIE-OTOO, B. N.; TAKI, M. Y. Application of gradient boosting regression model for the evaluation of feature selection techniques in improving reservoir characterisation predictions. Journal of Petroleum Science and Engineering, v. 208, Part E, p. 109244, 2022. ISSN 0920-4105. Disponível em: https://doi.org/10.1016/j.petrol.2021.109244. Acesso em: 28 set. 2023. DOI: https://doi.org/10.1016/j.petrol.2021.109244
PANDAS. Documentação. [S. l.]: Pandas, s. d. Disponível em: https://pandas.pydata.org/docs/. Acesso em: 20 ago. 2023
PARAÍBA TOTAL. Geografia. [S. l.]: Paraíba Total, 2021. Disponível em: https://www.paraibatotal.com.br/a-paraiba/geografia/. Acesso em: 20 ago. 2023.
PYTHON SOFTWARE FOUNDATION. Documentação Python 3.x (Português do Brasil). [S. l.]: Python Software Foundation, s. d. Disponível em: https://docs.python.org/pt-br/3/. Acesso em: 20 ago. 2023.
R DEVELOPMENT CORE TEAM. R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing, 2013. ISBN 3-900051-07-0, 2014.
SANTOS, C. A. G.; BRASIL NETO, R. M.; DA SILVA, R. M.; DOS SANTOS, D. C. Innovative approach for geospatial drought severity classification: a case study of Paraíba state, Brazil. Stochastic Environmental Research and Risk Assessment, v. 33, n. 2, p. 545-562, 2019. DOI: https://doi.org/10.1007/s00477-018-1619-9
SEABORN. Introdução ao tutorial. [S. l.]: SEABORN, s. d. Disponível em: https://seaborn.pydata.org/tutorial/introduction.html. Acesso em: 20 ago. 2023.
SODRÉ, G. D. A. 2040: o aquecimento global gerando impacto econômico na produção de cana no Estado de São Paulo. 2010. Tese (Doutorado) – Fundação Getulio Vargas, São Paulo, 2010.
SVOBODA, M.; HAYES, M.; WOOD, D. Standardized precipitation index: user guide. [S. l.: s. n.], 2012.
THOM, H. C. A note on the gamma distribution. Monthly weather review, v. 86, n. 4, p. 117-122, 1958. DOI: https://doi.org/10.1175/1520-0493(1958)086<0117:ANOTGD>2.0.CO;2
WANG, K. Y.; LI, Q. F.; YANG, Y.; ZENG, M.; Li, P. C.; ZHANG, J. X. Analysis of spatio-temporal evolution of droughts in Luanhe River Basin using different drought indices. Water Science and Engineering, v. 8, n. 4, p. 282-290, 2015. DOI: https://doi.org/10.1016/j.wse.2015.11.004
XARRAY. Documentação estável. [S. l.]: Xarray, s. d. Disponível em: https://docs.xarray.dev/en/stable/. Acesso em: 20 ago. 2023.
Downloads
Published
License
Copyright (c) 2024 RECIMA21 - Revista Científica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
