A Precipitation forecasting in central ecotone region in Brazil using artificial neural networks and public climatic data
DOI:
https://doi.org/10.47236/2594-7036.2021.v5.i2.131-146pPalavras-chave:
Precipitation forecasting. Artificial neural network. Irrigated Agriculture. Water Resources Planning. Meteorology.Resumo
Precipitation forecasting may be of great value for farming, helping to reduce crop losses and irrigation costs, besides leveraging crop yield estimates. In Brazil, the state of Tocantins has a great part of its economy based on agriculture, where precipitation forecasting may help improve local production. Besides, rainfall forecasting can also contribute to urban planning through the management of water resources, among other applications Artificial Neural Networks (ANNs) have been used with relative success in precipitation forecasting for different locations and climates. With that, this work presents a method for weekly precipitation forecasting in six locations in the Brazilian state of Tocantins using ANNs and public climatic data. For that, MultiLayer Perceptron (MLP) networks were trained with data from local weather stations and El Niño Southern Oscillation (ENSO) related indices. First, input variables were selected using the forward selection algorithm. After that, ANN hyperparameters and input variables lag were optimized. The average Root Means Square Error (RMSE) of the final models was of 31.35 mm/week for the training dataset and 33.38 mm/week for the test dataset. Respectively, these values represent 9,83% and 10,46% of the maximum weekly precipitation found in the work dataset, which was of 319.1 mm. The results suggest that the created models are capable of reasonably good weekly precipitation forecasts, providing valuable information for farming, water resources management, urban planning and other related activies. Although there is possibly room for model improvement.Downloads
Métricas
Referências
ABBOT, J., MAROHASY, J. Input selection and optimization for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks. Atmospheric Research, USA, v.138, p.166-178, 2014.
ABBOT, J., MAROHASY, J. Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization. Atmospheric Research, USA, v. 197, p. 289-299, 2017.
AKRAMI, S.A., EL-SHAFIE, A., JAAFAR, O. Improving rainfall forecasting efficiency using modified adaptive neuro-fuzzy inference system (MANFIS). Water Resources Management, USA, v. 27, p. 3507-3523, 2013.
ANDERSON, W. et al. Life cycles of agriculturally relevant ENSO teleconnections in north and south America. International Journal of Climatology, USA, v. 37, p. 3297-3318, 2017.
ASSENG, S. et al. Is a 10-day rainfall forecast of value in dry-land wheat cropping? Agricultural and Forest Meteorology, USA, v. 216, p. 170-176, 2016.
BIER, A.A., FERRAZ, S.E.T. Comparação de metodologias de preenchimento de falhas em dados meteorológicos para estação no sul do Brasil. Revista Brasileira de Meteorologia, São Paulo, v. 32, n. 2, p. 215- 226, 2017.
CAO, J. et al. Irrigation scheduling of paddy rice using short-term weather forecast data. Agricultural Water Management, USA, v. 213, p. 714-723, 2019.
DUTTA, D. et al. An artificial neural network based approach for estimation of rain intensity from spectral moments of a doppler weather radar. Advances in Space Research, USA, v. 47, n. 11, p. 1949-1957, 2011.
ESTEVES, J.T., DE SOUZA ROLIM, G., FERRAUDO, A.S. Rainfall prediction methodology with binary multilayer perceptron neural networks. Climate Dynamics, USA, v. 52, p. 2319-2331, 2019.
INSTITUTO NACIONAL DE METEOROLOGIA, 2011. Nota Técnica No. 001/2011/SEGER/LAIME/CSC/INMET: Rede de Estações Meteorológicas Automáticas do INMET. Disponível em: http://www.inmet.gov.br/portal/css/content/topo_iframe/pdf/Nota_Tecnica-Rede_estacoes_INMET.pdf. Acesso em: jun. 2018.
LEE, J. et al. Application of artificial neural networks to rainfall forecasting in the geum river basin, Korea, Water, Switzerland, v. 10, n. 10, p. 1-14, 2018.
MAROHASY, J., ABBOT, J. Assessing the quality of eight different maximum temperature time series as inputs when using artificial neural networks to forecast monthly rainfall at cape Otway, Australia. Atmospheric Research, USA, v. 166, p. 141-149, 2015.
MAY, R., DANDY, G., MAIER, H. Review of input variable selection methods for artificial neural networks, In: SUZUKI, K. Artificial Neural Networks. 1. ed. IntechOpen, Croácia, 2011. p. 19-44.
DE OLIVEIRA, L.F.C. et al. Comparação de metodologias de preenchimento de falhas de séries históricas de precipitação pluvial anual. Revista Brasileira de Engenharia Agrícola e Ambiental, Paraíba, v.14, n.11, p.1186-1192, 2010.
CARDOSO, A. de O. et al. Extended time weather forecasts contribute to agricultural productivity estimates. Theoretical and Applied Climatology, USA, v. 102, p. 343-350, 2010.
SCAIFE, A. et al. What is the el niño-southern oscillation? Weather, USA, v. 74, n. 7, p. 250-251, 2019.
SECRETARIA DO PLANEJAMENTO E ORÇAMENTO DO ESTADO DO TOCANTINS, 2016. Perfil do Agronegócio Tocantinense. Disponível em: https://central3.to.gov.br/arquivo/354694/. Acesso em: jun. 2018.
TABONY, R.C. The estimation of missing climatological data. Journal of Climatology, USA, v. 3, n. 3, p. 297-314, 1983.
VELO, R., LÓPEZ, P., MASEDA, F. Wind speed estimation using multilayer perceptron. Energy Conversion and Management, USA, v. 81, p. 1-9, 2014.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2021 Revista Sítio Novo

Este trabalho está licenciado sob uma licença Creative Commons Attribution 4.0 International License.
Permite o compartilhamento, adaptação e uso para quaisquer fins, inclusive comerciais, desde que feita a devida atribuição aos autores e à Revista Sítio Novo.
Os autores declaram que o trabalho é original, não foi previamente publicado em parte ou no todo, exceto em servidores de preprints reconhecidos, desde que declarado, e que nenhum outro manuscrito similar de sua autoria está publicado ou em processo de avaliação por outro periódico, seja impresso ou eletrônico.
Declaram que não violaram nem infringiram nenhum tipo de direito de propriedade de outras pessoas, e que todas as citações no texto são fatos verdadeiros ou baseados em pesquisas de exatidão cientificamente considerável.
Os autores mantêm os direitos autorais dos manuscritos publicados nesta revista, permitindo o uso irrestrito de seu conteúdo, desde que citada a autoria original e a fonte da publicação.