EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Comparative evaluation of machine learning strategies for short-term dengue forecasting in Brazilian capital municipalities

Darllan Collins da Cunha E Silva, Liliane Moreira Nery, Nícholas de Paula Nicomedes, Pedro Cesar Madureira de Godoy Camargo, Leopoldo André Dutra Lusquino Filho, Raphael de Vicq Ferreira da Costa, Teresa Maria Fernandes Valente

International Journal of Biometeorology · 2026

DOI: 10.1007/s00484-026-03300-7 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift International Journal of Biometeorology, 2026. Verfasst von Darllan Collins da Cunha E Silva und 6 weiteren Autor:innen. Beteiligte Einrichtung: São Paulo State University (UNESP), Institute of Science and Technology, Sorocaba, Brazil. Hauptthemen laut MEDLINE: Dengue, Machine Learning. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade Estadual Paulista Júlio De Mesquita Filho.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dengue is an arboviral disease of high public health relevance, characterized by pronounced temporal variability, nonlinearity, and recurrent outbreaks, which pose challenges to epidemiological surveillance and decision-making. This study evaluated the performance of machine learning methods for short-term forecasting of the weekly dengue morbidity rate in the 27 Brazilian capital cities, comprising the 26 state capitals and Brasília, Federal District, with horizons up to 4 weeks. Epidemiological, climatic, and socioeconomic data were compiled for these capital cities and used to compare a Gated Recurrent Unit (GRU) neural network, formulated as a Multi-Input Multi-Output (MIMO) model, and a Gradient Boosting model (CatBoost), implemented using a Direct forecasting strategy with horizon-specific models. Validation was conducted using a walk-forward approach, with evaluation based on absolute error metrics and the coefficient of determination. The results indicated that the GRU architecture presented recurring limitations, including underfitting, temporal lag, and low capacity to anticipate epidemic peaks. In contrast, the CatBoost model demonstrated greater robustness and better adaptation to the variability of epidemiological time series, showing superior performance in most of the analyzed capitals. The findings reinforce that greater architectural complexity does not necessarily imply better operational performance and highlight the potential of ensemble-based methods for short-term epidemiological surveillance applications. These findings contribute to dengue forecasting by showing that, under a common validation framework, ensemble-based strategies may provide greater operational robustness than recurrent MIMO architectures for short-term prediction in heterogeneous epidemiological settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DengueMachine LearningBrazilForecastingHumansCitiesBoosting Machine Learning AlgorithmsPredictive Learning ModelsPrediction AlgorithmsRecurrent Neural Networks

Stichwörter der Autor:innen

Epidemiological surveillanceMulti-horizon forecastingPredictive modelingPublic healthTime series

Autor:innen und Institutionen

  • São Paulo State University (UNESP), Institute of Science and Technology, Sorocaba, Brazil.
  • University of Minho, Institute of Earth Sciences (ICT), Braga, Portugal.
  • São Paulo State University (UNESP), Institute of Science and Technology, Sorocaba, Brazil. nicholas.nicomedes@unesp.br.

Förderung

  • Universidade Estadual Paulista Júlio De Mesquita Filho

Zitieren

APA

Silva, D. C. D. C. E., Nery, L. M., Nicomedes, N. P., Camargo, P. C. M. G., Lusquino Filho, L. A. D., Costa, R. V. F. D., & Valente, T. M. F. (2026). Comparative evaluation of machine learning strategies for short-term dengue forecasting in Brazilian capital municipalities. International Journal of Biometeorology. https://doi.org/10.1007/s00484-026-03300-7

Vancouver

Silva DCDCE, Nery LM, Nicomedes NP, Camargo PCMG, Lusquino Filho LAD, Costa RVFD, et al. Comparative evaluation of machine learning strategies for short-term dengue forecasting in Brazilian capital municipalities. International Journal of Biometeorology. 2026. doi:10.1007/s00484-026-03300-7

BibTeX
@article{Silva2026,
  author = {Silva, Darllan Collins da Cunha E and Nery, Liliane Moreira and Nicomedes, Nícholas de Paula and Camargo, Pedro Cesar Madureira de Godoy and Lusquino Filho, Leopoldo André Dutra and Costa, Raphael de Vicq Ferreira da and Valente, Teresa Maria Fernandes},
  title = {Comparative evaluation of machine learning strategies for short-term dengue forecasting in Brazilian capital municipalities},
  journal = {International Journal of Biometeorology},
  year = {2026},
  doi = {10.1007/s00484-026-03300-7}
}
Kostenlos starten →