Abordagem Multivariada para Imputação de Temperatura Média na Região Amazônica baseada em Estações Meteorológicas e Dados de Reanálise ERA5-Land

• Jean Arthur Costa Dias UFPA https://orcid.org/0009-0005-7663-8072
• André Vinicius N. Alves UFPA https://orcid.org/0000-0001-8013-5869
• Waldemiro J. A. G. Negreiros UFPA https://orcid.org/0009-0007-2694-6274
• Rodrigo Gonçalves Novais PUC-Rio https://orcid.org/0000-0003-3481-5008
• Fernando Luiz Cyrino Oliveira PUC-Rio https://orcid.org/0000-0003-1870-9440
• Leonardo de O. Tamasauskas UFPA https://orcid.org/0009-0006-8049-8997
• Pedro H. do V. Guimarães UFPA https://orcid.org/0009-0006-2350-2451
• Karla Figueiredo UERJ https://orcid.org/0000-0001-8420-3937
• Gabriel B. Costa UFPA https://orcid.org/0000-0002-5254-489X
• Marivan S. Gomes UEA https://orcid.org/0009-0007-2022-9047
• Marcos César da Rocha Seruffo UFPA https://orcid.org/0000-0002-8106-0560

DOI: https://doi.org/10.5753/wcama.2026.20442

Resumo

This study investigates the imputation of missing values in mean air temperature time series in the state of Pará, Brazil, by integrating observational data from INMET and the ERA5-Land reanalysis. A multivariate non-linear approach based on the MissForest algorithm was developed and compared with models using only station data and with linear interpolation. The evaluation employed synthetic gaps together with the RMSE, MAE, and MAE in quantile 99 metrics. The results indicate that the inclusion of ERA5-Land reduced RMSE to 0.664–0.744 °C, MAE to 0.509–0.569 °C, and ∆P₉₉ to 0.909–1.013 °C, while increasing model stability and outperforming the other strategies, thus supporting the methodological consistency of the approach for tropical climate time series.

Referências

Abreu, J., Vidal, D., and Gonçalves, G. (2024). Serviço web para imputação de dados em séries temporais univariadas. In Anais do XV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 131–140, Porto Alegre, RS, Brasil. SBC.

Alejo-Sanchez, L. E., Márquez-Grajales, A., Salas-Martínez, F., Franco-Arcega, A., López-Morales, V., Acevedo-Sandoval, O. A., González-Ramírez, C. A., and Villegas-Vega, R. (2025). Missing data imputation of climate time series: A review.

Budiawan, I., Wicaksana, H. S., Ekawati, E., and Kurniadi, D. (2025). Quality assurance of field temperature data from weather stations: A case study of missforest imputation. In 2025 9th International Conference on Instrumentation, Control, and Automation (ICA), pages 157–162. IEEE.

den Braber, B., Oldekop, J. A., Devenish, K., Godar, J., Nolte, C., Schmoeller, M., and Evans, K. L. (2024). Socio-economic and environmental trade-offs in amazonian protected areas and indigenous territories revealed by assessing competing land uses. Nature Ecology & Evolution, 8(8):1482–1492.

Garrett, R., Ferreira, J., Abramovay, R., Brandão, J., Brondizio, E., Euler, A., Pinedo, D., Porro, R., Cabrera Rocha, E., Sampaio, O., et al. (2024). Transformative changes are needed to support socio-bioeconomies for people and ecosystems in the amazon. Nature Ecology & Evolution, 8(10):1815–1825.

Han, H., Liu, Z., Li, J., and Zeng, Z. (2024). Challenges in remote sensing based climate and crop monitoring: navigating the complexities using ai. Journal of cloud computing, 13(1):1–14.

Hoinaski, L., Will, R., and Ribeiro, C. B. (2024). Brazilian atmospheric inventories–brain: a comprehensive database of air quality in brazil. Earth System Science Data, 16(5):2385–2405.

Lalic, B., Stapleton, A., Vergauwen, T., Caluwaerts, S., Eichelmann, E., and Roantree, M. (2024). A comparative analysis of machine learning approaches to gap filling meteorological datasets. Environmental Earth Sciences, 83.

Lompar, M., Lalić, B., Dekić, L., and Petrić, M. (2019). Filling gaps in hourly air temperature data using debiased era5 data. Atmosphere 2019, Vol. 10,, 10.

Metcalfe, D. B., Anders, E., Axén, H., Petter Axelsson, E., Bermudez, A. E., Bartholomew, D. C., Butt, N., Cadillo-Quiroz, H., Chaudhary, N., Callebaut, T., et al. (2025). Gaps in tropical science from unrepresentative distribution of sampling and citation across natural terrestrial environments. Nature communications.

Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., et al. (2021). Era5-land: A state-of-the-art global reanalysis dataset for land applications. Earth system science data, 13(9):4349–4383.

Noor, N. M., Al Bakri Abdullah, M. M., Yahaya, A. S., and Ramli, N. A. (2015). Comparison of linear interpolation method and mean method to replace the missing values in environmental data set. In Materials science forum, volume 803, pages 278–281. Trans Tech Publ.

Qin, Y., Wang, D., Ziegler, A. D., Fu, B., and Zeng, Z. (2025). Impact of amazonian deforestation on precipitation reverses between seasons. Nature, 639(8053):102–108.

Rodrigues, D. T., Gonçalves, W. A., Silva, C. M. S. E., Spyrides, M. H. C., and Lúcio, P. S. (2023). Imputation of precipitation data in northeast brazil. Anais da Academia Brasileira de Ciencias, 95.

Tan, M. L., Armanuos, A. M., Ahmadianfar, I., Demir, V., Heddam, S., Al-Areeq, A. M., Abba, S. I., Halder, B., Kilinc, H. C., and Yaseen, Z. M. (2023). Evaluation of nasa power and era5-land for estimating tropical precipitation and temperature extremes. Journal of Hydrology, 624:129940.

Tatachar, A. V. (2021). Comparative assessment of regression models based on model evaluation metrics. International Research Journal of Engineering and Technology (IRJET), 8(09):2395–0056.

United Nations General Assembly (2015). Transforming our world: the 2030 agenda for sustainable development. A/RES/70/1. 21 October 2015. Available at: [link] [Accessed 15 February 2026].

Zhang, X. (2023). How to generate missing data for simulation studies. The Quantitative Methods for Psychology, 19:100–122.