FaXNet: a frequency-adaptive, explainable, and uncertainty-aware network for influenza forecasting
Frontiers in Public Health · 2026
DOI: 10.3389/fpubh.2026.1746529 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Public Health, 2026. Verfasst von Wei He und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Innovation Engineering, Macau University of Science and Technology, Macao, Macao SAR, China. Hauptthemen laut MEDLINE: Influenza, Human, Deep Learning. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Accurate and interpretable influenza forecasting is critical for public health preparedness, yet many models struggle to capture multi-scale temporal dynamics and to provide reliable uncertainty estimates. These challenges are particularly pronounced in China, where influenza seasonality differs between northern temperate and southern subtropical regions.
Methods
We propose FaXNet, a frequency-adaptive, explainable, and uncertainty-aware deep learning framework that integrates data-driven spectral representation with interpretable component selection and probabilistic forecasting. We compiled weekly influenza positivity rates from the Chinese National Influenza Center and aligned them with ERA5-Land meteorological variables (temperature, dew point, and precipitation) for northern and southern China from 2011 to 2023. FaXNet was evaluated against representative statistical, machine learning, deep learning, and decomposition-based baselines for 1–4-week-ahead forecasting using standard accuracy and calibration metrics.
Results
FaXNet achieved consistently superior performance in both regions, with 1-week-ahead R 2 of 0.9319 (north) and 0.8665 (south), and 4-week-ahead R 2 of 0.4493 (north) and 0.4960 (south). The proposed method maintained a statistically significant performance advantage against all benchmarks across varying horizons, validating the effectiveness of frequency-adaptive modeling in mitigating error accumulation. Model explanations highlighted precipitation as the dominant meteorological driver in the north and temperature as the primary factor in the south.
Conclusion
FaXNet provides accurate, interpretable forecasts with calibrated prediction intervals across 1–4-week horizons, offering actionable lead time for region-specific risk assessment and resource planning. Performance may depend on surveillance data completeness and the limited set of exogenous covariates considered, motivating future extensions with additional drivers (e.g., mobility or vaccination) and broader external validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Innovation Engineering, Macau University of Science and Technology, Macao, Macao SAR, China.
- Institute of Systems Engineering, Macau University of Science and Technology, Macao, Macao SAR, China.
- Faculty of Social Sciences, The University of Hong Kong, Hong Kong, Hong Kong SAR, China.
- National Clinical Research Center for Respiratory Disease, State Key Laboratory of Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affliated Hospital of Guangzhou Medical University, Guangzhou,…
Zitieren
APA
He, W., Li, X., Liang, X., Liu, Z., Zeng, Z., Yang, Z., & Hon, C. (2026). FaXNet: a frequency-adaptive, explainable, and uncertainty-aware network for influenza forecasting. Frontiers in Public Health. https://doi.org/10.3389/fpubh.2026.1746529
Vancouver
He W, Li X, Liang X, Liu Z, Zeng Z, Yang Z, et al. FaXNet: a frequency-adaptive, explainable, and uncertainty-aware network for influenza forecasting. Frontiers in Public Health. 2026. doi:10.3389/fpubh.2026.1746529
BibTeX
@article{He2026,
author = {He, Wei and Li, Xuanfeng and Liang, Xiaolin and Liu, Zige and Zeng, Zhiqi and Yang, Zifeng and Hon, Chitin},
title = {FaXNet: a frequency-adaptive, explainable, and uncertainty-aware network for influenza forecasting},
journal = {Frontiers in Public Health},
year = {2026},
doi = {10.3389/fpubh.2026.1746529}
}
EUVIMED