Fusion of Orbital and Surface Data for Air Temperature Estimation in Belém Using Machine Learning
Resumo
This study evaluates fusion strategies between ERA5-Land orbital data and INMET surface observations to estimate daily air temperature in Belém, using data from 1994 to 2024. Different Random Forest models were compared, along with SARIMAX, LSTM, and stacking (SARIMAX and RF). The RF model with multivariate fusion achieved the best performance (RMSE = 0.5157 °C; R2 = 0.708; Skill = 6.19%), reducing bias relative to the orbital baseline, while chronological validation confirmed the temporal stability of RF-based models. The results indicate that, under low equatorial thermal variability, tree-based models are the most robust for satellite–surface fusion and thermal downscaling.
Referências
Alvares, C. A., Stape, J. L., Sentelhas, P. C., Gonçalves, J. d. M., Sparovek, G., et al. (2013). Köppen’s climate classification map for brazil. Meteorologische zeitschrift, 22(6):711–728.
Bergstra, J. and Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of machine learning research, 13(2).
Bhatti, M. A., Song, Z., Bhatti, U. A., et al. (2024). Aiot-driven multi-source sensor emission monitoring and forecasting using multi-source sensor integration with reduced noise series decomposition. Journal of Cloud Computing, 13:65.
Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Brousse, O., Simpson, C. H., Poorthuis, A., et al. (2024). Unequal distributions of crowd-sourced weather data in england and wales. Nature Communications, 15:4828.
Camps-Valls, G., Fernández-Torres, M. A., Cohrs, K. H., et al. (2025). Artificial intelligence for modeling and understanding extreme weather and climate events. Nature Communications, 16:1919.
Fick, S. E. and Hijmans, R. J. (2017). Worldclim 2: new 1-km spatial resolution climate surfaces for global land areas. International journal of climatology, 37(12):4302–4315.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., et al. (2020). The era5 global reanalysis. Quarterly journal of the royal meteorological society, 146(730):1999–2049.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Hubbard, K. and Lin, X. (2006). Reexamination of instrument change effects in the us historical climatology network. Geophysical research letters, 33(15).
Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
Ismaeel, A., Tai, A. P. K., Santos, E. G., et al. (2024). Patterns of tropical forest understory temperatures. Nature Communications, 15:549.
Khosravi, A., Nahavandi, S., Creighton, D., and Atiya, A. F. (2011). Comprehensive review of neural network-based prediction intervals and new advances. IEEE Transactions on neural networks, 22(9):1341–1356.
Kothiyal, S., Goel, S., Singh, R., Chilwal, A., and Ranjan, R. (2025). Sarima-based time series analysis of rainfall and temperature for the tarai region of uttarakhand. Journal of Agrometeorology, 27(1):73–76.
Lai, C.-Y., Hassanzadeh, P., Sheshadri, A., Sonnewald, M., Ferrari, R., and Balaji, V. (2025). Machine learning for climate physics and simulations. Annual Review of Condensed Matter Physics, 16:343–365.
Little, R. J. and Rubin, D. B. (2019). Statistical analysis with missing data. John Wiley & Sons.
Lopez-Gomez, I., Wan, Z. Y., Zepeda-Núñez, L., Schneider, T., Anderson, J., and Sha, F. (2025). Dynamical-generative downscaling of climate model ensembles. Proceedings of the National Academy of Sciences, 122(17):e2420288122.
McCulloch, M. T., Winter, A., Sherman, C. E., et al. (2024). 300 years of sclerosponge thermometry shows global warming has exceeded 1.5 °c. Nature Climate Change, 14:171–177.
Muñoz Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N. (2021). Era5-land: a state-of-the-art global reanalysis dataset for land applications. Earth System Science Data, 13(9):4349–4383.
Murphy, A. H. (1988). Skill scores based on the mean square error and their relationships to the correlation coefficient. Monthly weather review, 116(12):2417–2424.
Nash, J. E. and Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part i—a discussion of principles. Journal of hydrology, 10(3):282–290.
Nourani, V., Tosan, M., Huang, J. J., Gebremichael, M., Kantoush, S. A., and Dastourani, M. (2025). Advances in multi-source data fusion for precipitation estimation: remote sensing and machine learning perspectives. Earth-Science Reviews, page 105253.
Rains, D., Trigo, I., Dutra, E., Ermida, S., Ghent, D., Hulsman, P., Gómez-Dans, J., and Miralles, D. G. (2024). High-resolution (1 km) all-sky net radiation over europe enabled by the merging of land surface temperature retrievals from geostationary and polar-orbiting satellites. Earth System Science Data, 16:567–593.
Sagi, O. and Rokach, L. (2018). Ensemble learning: A survey. Wiley interdisciplinary reviews: data mining and knowledge discovery, 8(4):e1249.
Silván-Cárdenas, J. and Wang, L. (2010). Retrieval of subpixel tamarix canopy cover from landsat data along the forgotten river using linear and nonlinear spectral mixture models. Remote Sensing of Environment, 114(8):1777–1790.
Tamasauskas, L. d. O., Pereira, W. G., Negreiros, W. J., Guimaraes, P. H. d. V., Dias, J. A., Corrêa, A. B., Costa, G. B., and Seruffo, M. C. d. R. (2025). Comparison of lstm and sarima models for air temperature forecasting in belém, amazônia, pará. In Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais (WCAMA), pages 256–265. SBC.
van Tiggelen, M., Smeets, P. C. J. P., Reijmer, C. H., Kuipers Munneke, P., and van den Broeke, M. R. (2025). Imau antarctic automatic weather station data, including surface radiation balance (1995–2022). Earth System Science Data, 17:4933–4955.
Wei, S., Li, Q., Xu, Q., Li, Z., Zhang, H., and Lin, J. (2025). Updates to c-lsat 2.1 and the development of high-resolution land surface air temperature and diurnal temperature range datasets. Earth System Science Data, 17:4985–5005.
Wilks, D. S. (2011). Statistical methods in the atmospheric sciences, volume 100. Academic press.
Willmott, C. J. and Matsuura, K. (2005). Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate research, 30(1):79–82.
Wolpert, D. H. (1992). Stacked generalization. Neural networks, 5(2):241–259.
Wu, H. and Li, W. (2019). Downscaling land surface temperatures using a random forest regression model with multitype predictor variables. Ieee Access, 7:21904–21916.
Bergstra, J. and Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of machine learning research, 13(2).
Bhatti, M. A., Song, Z., Bhatti, U. A., et al. (2024). Aiot-driven multi-source sensor emission monitoring and forecasting using multi-source sensor integration with reduced noise series decomposition. Journal of Cloud Computing, 13:65.
Box, G. E., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.
Brousse, O., Simpson, C. H., Poorthuis, A., et al. (2024). Unequal distributions of crowd-sourced weather data in england and wales. Nature Communications, 15:4828.
Camps-Valls, G., Fernández-Torres, M. A., Cohrs, K. H., et al. (2025). Artificial intelligence for modeling and understanding extreme weather and climate events. Nature Communications, 16:1919.
Fick, S. E. and Hijmans, R. J. (2017). Worldclim 2: new 1-km spatial resolution climate surfaces for global land areas. International journal of climatology, 37(12):4302–4315.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., et al. (2020). The era5 global reanalysis. Quarterly journal of the royal meteorological society, 146(730):1999–2049.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Hubbard, K. and Lin, X. (2006). Reexamination of instrument change effects in the us historical climatology network. Geophysical research letters, 33(15).
Hyndman, R. J. and Athanasopoulos, G. (2018). Forecasting: principles and practice. OTexts.
Ismaeel, A., Tai, A. P. K., Santos, E. G., et al. (2024). Patterns of tropical forest understory temperatures. Nature Communications, 15:549.
Khosravi, A., Nahavandi, S., Creighton, D., and Atiya, A. F. (2011). Comprehensive review of neural network-based prediction intervals and new advances. IEEE Transactions on neural networks, 22(9):1341–1356.
Kothiyal, S., Goel, S., Singh, R., Chilwal, A., and Ranjan, R. (2025). Sarima-based time series analysis of rainfall and temperature for the tarai region of uttarakhand. Journal of Agrometeorology, 27(1):73–76.
Lai, C.-Y., Hassanzadeh, P., Sheshadri, A., Sonnewald, M., Ferrari, R., and Balaji, V. (2025). Machine learning for climate physics and simulations. Annual Review of Condensed Matter Physics, 16:343–365.
Little, R. J. and Rubin, D. B. (2019). Statistical analysis with missing data. John Wiley & Sons.
Lopez-Gomez, I., Wan, Z. Y., Zepeda-Núñez, L., Schneider, T., Anderson, J., and Sha, F. (2025). Dynamical-generative downscaling of climate model ensembles. Proceedings of the National Academy of Sciences, 122(17):e2420288122.
McCulloch, M. T., Winter, A., Sherman, C. E., et al. (2024). 300 years of sclerosponge thermometry shows global warming has exceeded 1.5 °c. Nature Climate Change, 14:171–177.
Muñoz Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N. (2021). Era5-land: a state-of-the-art global reanalysis dataset for land applications. Earth System Science Data, 13(9):4349–4383.
Murphy, A. H. (1988). Skill scores based on the mean square error and their relationships to the correlation coefficient. Monthly weather review, 116(12):2417–2424.
Nash, J. E. and Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part i—a discussion of principles. Journal of hydrology, 10(3):282–290.
Nourani, V., Tosan, M., Huang, J. J., Gebremichael, M., Kantoush, S. A., and Dastourani, M. (2025). Advances in multi-source data fusion for precipitation estimation: remote sensing and machine learning perspectives. Earth-Science Reviews, page 105253.
Rains, D., Trigo, I., Dutra, E., Ermida, S., Ghent, D., Hulsman, P., Gómez-Dans, J., and Miralles, D. G. (2024). High-resolution (1 km) all-sky net radiation over europe enabled by the merging of land surface temperature retrievals from geostationary and polar-orbiting satellites. Earth System Science Data, 16:567–593.
Sagi, O. and Rokach, L. (2018). Ensemble learning: A survey. Wiley interdisciplinary reviews: data mining and knowledge discovery, 8(4):e1249.
Silván-Cárdenas, J. and Wang, L. (2010). Retrieval of subpixel tamarix canopy cover from landsat data along the forgotten river using linear and nonlinear spectral mixture models. Remote Sensing of Environment, 114(8):1777–1790.
Tamasauskas, L. d. O., Pereira, W. G., Negreiros, W. J., Guimaraes, P. H. d. V., Dias, J. A., Corrêa, A. B., Costa, G. B., and Seruffo, M. C. d. R. (2025). Comparison of lstm and sarima models for air temperature forecasting in belém, amazônia, pará. In Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais (WCAMA), pages 256–265. SBC.
van Tiggelen, M., Smeets, P. C. J. P., Reijmer, C. H., Kuipers Munneke, P., and van den Broeke, M. R. (2025). Imau antarctic automatic weather station data, including surface radiation balance (1995–2022). Earth System Science Data, 17:4933–4955.
Wei, S., Li, Q., Xu, Q., Li, Z., Zhang, H., and Lin, J. (2025). Updates to c-lsat 2.1 and the development of high-resolution land surface air temperature and diurnal temperature range datasets. Earth System Science Data, 17:4985–5005.
Wilks, D. S. (2011). Statistical methods in the atmospheric sciences, volume 100. Academic press.
Willmott, C. J. and Matsuura, K. (2005). Advantages of the mean absolute error (mae) over the root mean square error (rmse) in assessing average model performance. Climate research, 30(1):79–82.
Wolpert, D. H. (1992). Stacked generalization. Neural networks, 5(2):241–259.
Wu, H. and Li, W. (2019). Downscaling land surface temperatures using a random forest regression model with multitype predictor variables. Ieee Access, 7:21904–21916.
Publicado
19/07/2026
Como Citar
TAMASAUSKAS, Leonardo de O.; NEGREIROS, Waldemiro J. A. G.; GUIMARÃES, Pedro H. do V.; PEREIRA, Williane G. S.; DIAS, Jean A. C.; COSTA, Gabriel B.; SERUFFO, Marcos C. da R..
Fusion of Orbital and Surface Data for Air Temperature Estimation in Belém Using Machine Learning. In: WORKSHOP DE COMPUTAÇÃO APLICADA À GESTÃO DO MEIO AMBIENTE E RECURSOS NATURAIS (WCAMA), 17. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 137-145.
ISSN 2595-6124.
DOI: https://doi.org/10.5753/wcama.2026.21200.
