An adaptive weight ensemble approach to forecast influenza activity in the context of irregular seasonality

Forecasting of influenza activity in tropical and subtropical regions such as Hong Kong is challenging due to irregular seasonality with high variability in the onset of influenza epidemics, and potential summer activity. To overcome this challenge, we develop a diverse set of statistical, machine learning and deep learning approaches to forecast influenza activity in Hong Kong 0-to 8- week ahead, leveraging a unique multi-year surveillance record spanning 34 winter and summer epidemics from 1998-2019. We develop a simple average ensemble (SAE), which is the average of individual forecasts from the top three individual models. We also consider an adaptive weight blending ensemble (AWBE) that allows for dynamic updates of each model contribution based on LASSO regression and uses decaying weights in historical data to capture rapid change in influenza activity. Overall, across all 9 weeks of horizon, all models outperform the baseline constant incidence model, reducing the root mean square error (RMSE) by 23%-29% and weighted interval score (WIS) by 25%-31%. The SAE ensemble only slightly better than individual models, reducing RMSE and WIS by 29%. The AWBE ensemble reduce RMSE by 45% and WIS by 46%, and outperform individual models for forecasts of epidemic trends (growing, flat, descending), and during both winter and summer seasons. Using the post-COVID surveillance data in 2023-2024 as another test period, the AWBE ensemble still reduces RMSE by 32% and WIS by 36%. Our framework contributes to the ensemble forecasting of infectious diseases with irregular seasonality. Significance statement In subtropical and tropical regions, irregular influenza seasonality makes accurate forecasting challenging. We test ensemble approaches using diverse statistical, machine learning, and deep learning models based on a unique multi-year surveillance record in Hong Kong. Performance of individual models varies by season and epidemic trend, but simple averaging ensemble cannot improve accuracy. Here we develop an adaptive weight ensemble approach, which updated individual model contributions dynamically. This approach halves the RMSE, outperforms all individual models in different settings and reducing RMSE by one-third even in post-COVID periods. Our method contributes to comparison and benchmarking of models in ensemble forecasts, enhancing the evidence base for synthesizing multiple models in disease forecasting in geographies with irregular influenza seasonality. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This project was supported by the Theme-based Research Scheme (Project No. T11-712/19-N) of the Research Grants Council of the Hong Kong SAR Government, and the Health and Medical Research Fund, Food and Health Bureau, Government of the Hong Kong Special Administrative Region (grant no. 21200292). BJC is supported by the AIR@innoHK program of the Innovation and Technology Commission of the Hong Kong SAR Government. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: https://www.chp.gov.hk/en/statistics/data/10/26/44/292/7010.html; https://www.chp.gov.hk/en/static/24012.html I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors