Comparison of LSTM and SARIMA Models for Air Temperature Forecasting in Belém, Amazônia, Pará
Abstract
This study investigates air temperature forecasting in the city of Belém-PA, comparing the performance of the SARIMA and LSTM models. To this end, daily data from the ERA5-Land database was used and statistical metrics such as mean absolute error (MAE), mean squared error (MSE) and coefficient of determination (R²) were evaluated, supported by ANOVA, Shapiro-Wilk, Levene and Tukey tests. The results indicate that the LSTM model was more accurate, capturing complex patterns better than SARIMA. The findings reinforce the potential of recurrent neural networks in climate modeling and suggest new approaches for improving weather forecasting.References
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X. (2015). Tensor-Flow: Large-scale machine learning on heterogeneous systems. Software available from [link].
Abdi, H. and Williams, L. J. (2010). Newman-keuls test and tukey test. Encyclopedia of research design, 2:897–902.
Akbar, A. A., Darmawan, Y., Wibowo, A., and Rahmat, H. K. (2024). Accuracy assessment of monthly rainfall predictions using seasonal arima and long short-term memory (lstm). Journal of Computer Science and Engineering (JCSE), 5(2):100–115.
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631.
Arsad, F. S., Hod, R., Ahmad, N., Ismail, R., Mohamed, N., Baharom, M., Osman, Y., Radi, M. F. M., and Tangang, F. (2022). The impact of heatwaves on mortality and morbidity and the associated vulnerability factors: a systematic review. International Journal of Environmental Research and Public Health, 19(23):16356.
Ayad, S. (2022). Modeling and forecasting air temperature in tetouan (morocco) using sarima model. J. Earth Sci. Geotech. Eng, 12:1–13.
Balasooriya, S., Nguyen, C., Kavalchuk, I., and Yasakethu, L. (2022). Forecasting model comparison for soil moisture to obtain optimal plant growth. In 2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), pages 1–7. IEEE.
Bergstra, J., Bardenet, R., Bengio, Y., and Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in neural information processing systems, 24.
Brasil, I. (2023). Censo demográfico 2022. Dados nacionais. Fundação Instituto Brasileiro de Geografia e Estatística. Brasil.
Costa, H., Santana, T., Silva, R., Gomes, N., Gonçalves, G., Guiselini, C., Almeida, G., and Medeiros, V. (2022). Estudo da viabilidade técnica do emprego de detectores térmicos de baixa resolução na suinocultura 4.0. In Anais do XIII Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 21–30, Porto Alegre, RS, Brasil. SBC.
Cuevas, A., Febrero, M., and Fraiman, R. (2004). An anova test for functional data. Computational statistics & data analysis, 47(1):111–122.
Du, Q., Zhang, M., Wang, S., Che, C., Ma, R., and Ma, Z. (2019). Changes in air temperature over china in response to the recent global warming hiatus. Journal of Geographical Sciences, 29:496–516.
Fan, C., Zou, B., Li, J., Wang, M., Liao, Y., and Zhou, X. (2024). Exploring the relationship between air temperature and urban morphology factors using machine learning under local climate zones. Case Studies in Thermal Engineering, 55:104151.
Gastwirth, J. L., Gel, Y. R., and Miao, W. (2009). The impact of levene’s test of equality of variances on statistical theory and practice.
Gill, K., Bhatt, K., Kaur, B., and Sandhu, S. S. (2023). Arima approach for temperature and rainfall time series prediction in punjab. Journal of Agrometeorology, 25(4):571–576.
Hanusz, Z., Tarasinska, J., and Zielinski, W. (2016). Shapiro–wilk test with known mean. REVSTAT-statistical Journal, 14(1):89–100.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Karunaratne, S., Athukorala, D., Murayama, Y., and Morimoto, T. (2022). Assessing surface urban heat island related to land use/land cover composition and pattern in the temperate mountain valley city of kathmandu, nepal. Remote Sensing, 14(16).
Khalil, U., Azam, U., Aslam, B., Ullah, I., Tariq, A., Li, Q., and Lu, L. (2022). Developing a spatiotemporal model to forecast land surface temperature: A way forward for better town planning. Sustainability, 14(19).
Necula, S.-C., Hauer, I., Fotache, D., and Hurbean, L. (2025). Advanced hybrid models for air pollution forecasting: Combining sarima and bilstm architectures. Electronics (2079-9292), 14(3).
Nogueira, S. M. C. and Moreira, M. A. (2015). Avaliação das previsões de temperatura do modelo eta para o estado do paraná. In Anais do XVII Simpósio Brasileiro de Sensoriamento Remoto (SBSR), pages 2071–2078, São José dos Campos. Instituto Nacional de Pesquisas Espaciais (INPE). Acesso em: 3 mar. 2025.
Park, I., Kim, H. S., Lee, J., Kim, J. H., Song, C. H., and Kim, H. K. (2019). Temperature prediction using the missing data refinement model based on a long short-term memory neural network. Atmosphere, 10(11):718.
Paspaltzis, V. and Calheiros, A. (2023). Uma abordagem usando redes neurais artificiais para a previsão de curto prazo de altura de ondas marítimas em região portuária. In Anais do XIV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 141–150, Porto Alegre, RS, Brasil. SBC.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Scheffer, D., Souza, A. M., Zanini, R. R., et al. (2014). Utilização de modelos arima para previsão da arrecadação de icms do estado do rio grande do sul. Simpósio de Pesquisa Operacional e Logística da Marinha, 17.
Seabold, S. and Perktold, J. (2010). statsmodels: Econometric and statistical modeling with python. In 9th Python in Science Conference.
Silveira, A., Mattos, V., Nakamura, L., Amaral, M., Konrath, A., and Bornia, A. (2022). Análise do valor-p determinado pela estatística τ na aplicação do teste de dickey-fuller aumentado. Trends in Computational and Applied Mathematics, 23(2):283–298.
Smith, T. G. et al. (2017–). pmdarima: Arima estimators for Python. [Online; accessed ¡today¿].
Stone Jr, B., Mallen, E., Rajput, M., Gronlund, C. J., Broadbent, A. M., Krayenhoff, E. S., Augenbroe, G., O’Neill, M. S., and Georgescu, M. (2021). Compound climate and infrastructure events: how electrical grid failure alters heat wave risk. Environmental Science & Technology, 55(10):6957–6964.
UNDRR (2025). Making Cities Resilient 2030. Avaliable in: [link].
Yadav, N., Rajendra, K., Awasthi, A., Singh, C., and Bhushan, B. (2023). Systematic exploration of heat wave impact on mortality and urban heat island: A review from 2000 to 2022. Urban Climate, 51:101622.
Zhang, C., Yin, Y., Chen, G., Deng, H., Ma, D., and Wu, S. (2022). Water use efficiency-based assessment of risk to terrestrial ecosystems in china under global warming targets of 1.5° c and 2.0° c. Ecological Indicators, 143:109349.
Abdi, H. and Williams, L. J. (2010). Newman-keuls test and tukey test. Encyclopedia of research design, 2:897–902.
Akbar, A. A., Darmawan, Y., Wibowo, A., and Rahmat, H. K. (2024). Accuracy assessment of monthly rainfall predictions using seasonal arima and long short-term memory (lstm). Journal of Computer Science and Engineering (JCSE), 5(2):100–115.
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 2623–2631.
Arsad, F. S., Hod, R., Ahmad, N., Ismail, R., Mohamed, N., Baharom, M., Osman, Y., Radi, M. F. M., and Tangang, F. (2022). The impact of heatwaves on mortality and morbidity and the associated vulnerability factors: a systematic review. International Journal of Environmental Research and Public Health, 19(23):16356.
Ayad, S. (2022). Modeling and forecasting air temperature in tetouan (morocco) using sarima model. J. Earth Sci. Geotech. Eng, 12:1–13.
Balasooriya, S., Nguyen, C., Kavalchuk, I., and Yasakethu, L. (2022). Forecasting model comparison for soil moisture to obtain optimal plant growth. In 2022 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), pages 1–7. IEEE.
Bergstra, J., Bardenet, R., Bengio, Y., and Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in neural information processing systems, 24.
Brasil, I. (2023). Censo demográfico 2022. Dados nacionais. Fundação Instituto Brasileiro de Geografia e Estatística. Brasil.
Costa, H., Santana, T., Silva, R., Gomes, N., Gonçalves, G., Guiselini, C., Almeida, G., and Medeiros, V. (2022). Estudo da viabilidade técnica do emprego de detectores térmicos de baixa resolução na suinocultura 4.0. In Anais do XIII Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 21–30, Porto Alegre, RS, Brasil. SBC.
Cuevas, A., Febrero, M., and Fraiman, R. (2004). An anova test for functional data. Computational statistics & data analysis, 47(1):111–122.
Du, Q., Zhang, M., Wang, S., Che, C., Ma, R., and Ma, Z. (2019). Changes in air temperature over china in response to the recent global warming hiatus. Journal of Geographical Sciences, 29:496–516.
Fan, C., Zou, B., Li, J., Wang, M., Liao, Y., and Zhou, X. (2024). Exploring the relationship between air temperature and urban morphology factors using machine learning under local climate zones. Case Studies in Thermal Engineering, 55:104151.
Gastwirth, J. L., Gel, Y. R., and Miao, W. (2009). The impact of levene’s test of equality of variances on statistical theory and practice.
Gill, K., Bhatt, K., Kaur, B., and Sandhu, S. S. (2023). Arima approach for temperature and rainfall time series prediction in punjab. Journal of Agrometeorology, 25(4):571–576.
Hanusz, Z., Tarasinska, J., and Zielinski, W. (2016). Shapiro–wilk test with known mean. REVSTAT-statistical Journal, 14(1):89–100.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8):1735–1780.
Karunaratne, S., Athukorala, D., Murayama, Y., and Morimoto, T. (2022). Assessing surface urban heat island related to land use/land cover composition and pattern in the temperate mountain valley city of kathmandu, nepal. Remote Sensing, 14(16).
Khalil, U., Azam, U., Aslam, B., Ullah, I., Tariq, A., Li, Q., and Lu, L. (2022). Developing a spatiotemporal model to forecast land surface temperature: A way forward for better town planning. Sustainability, 14(19).
Necula, S.-C., Hauer, I., Fotache, D., and Hurbean, L. (2025). Advanced hybrid models for air pollution forecasting: Combining sarima and bilstm architectures. Electronics (2079-9292), 14(3).
Nogueira, S. M. C. and Moreira, M. A. (2015). Avaliação das previsões de temperatura do modelo eta para o estado do paraná. In Anais do XVII Simpósio Brasileiro de Sensoriamento Remoto (SBSR), pages 2071–2078, São José dos Campos. Instituto Nacional de Pesquisas Espaciais (INPE). Acesso em: 3 mar. 2025.
Park, I., Kim, H. S., Lee, J., Kim, J. H., Song, C. H., and Kim, H. K. (2019). Temperature prediction using the missing data refinement model based on a long short-term memory neural network. Atmosphere, 10(11):718.
Paspaltzis, V. and Calheiros, A. (2023). Uma abordagem usando redes neurais artificiais para a previsão de curto prazo de altura de ondas marítimas em região portuária. In Anais do XIV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 141–150, Porto Alegre, RS, Brasil. SBC.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Scheffer, D., Souza, A. M., Zanini, R. R., et al. (2014). Utilização de modelos arima para previsão da arrecadação de icms do estado do rio grande do sul. Simpósio de Pesquisa Operacional e Logística da Marinha, 17.
Seabold, S. and Perktold, J. (2010). statsmodels: Econometric and statistical modeling with python. In 9th Python in Science Conference.
Silveira, A., Mattos, V., Nakamura, L., Amaral, M., Konrath, A., and Bornia, A. (2022). Análise do valor-p determinado pela estatística τ na aplicação do teste de dickey-fuller aumentado. Trends in Computational and Applied Mathematics, 23(2):283–298.
Smith, T. G. et al. (2017–). pmdarima: Arima estimators for Python. [Online; accessed ¡today¿].
Stone Jr, B., Mallen, E., Rajput, M., Gronlund, C. J., Broadbent, A. M., Krayenhoff, E. S., Augenbroe, G., O’Neill, M. S., and Georgescu, M. (2021). Compound climate and infrastructure events: how electrical grid failure alters heat wave risk. Environmental Science & Technology, 55(10):6957–6964.
UNDRR (2025). Making Cities Resilient 2030. Avaliable in: [link].
Yadav, N., Rajendra, K., Awasthi, A., Singh, C., and Bhushan, B. (2023). Systematic exploration of heat wave impact on mortality and urban heat island: A review from 2000 to 2022. Urban Climate, 51:101622.
Zhang, C., Yin, Y., Chen, G., Deng, H., Ma, D., and Wu, S. (2022). Water use efficiency-based assessment of risk to terrestrial ecosystems in china under global warming targets of 1.5° c and 2.0° c. Ecological Indicators, 143:109349.
Published
2025-07-20
How to Cite
TAMASAUSKAS, Leonardo de O.; PEREIRA, Williane G. S.; NEGREIROS, Waldemiro J. A. G.; GUIMARÃES, Pedro H. do V.; DIAS, Jean A. C.; CORRÊA, Alan B. S.; COSTA, Gabriel B.; SERUFFO, Marcos C. da R..
Comparison of LSTM and SARIMA Models for Air Temperature Forecasting in Belém, Amazônia, Pará. In: WORKSHOP ON COMPUTING APPLIED TO THE MANAGEMENT OF THE ENVIRONMENT AND NATURAL RESOURCES (WCAMA), 16. , 2025, Maceió/AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 256-265.
ISSN 2595-6124.
DOI: https://doi.org/10.5753/wcama.2025.9107.
