A hybrid model for influenza forecasting in Xinjiang: adapting to complex seasonality and post-COVID-19 structural breaks

Key Points

• The research aims to develop a robust model for influenza forecasting that adapts to local complexities in Xinjiang.
• Developed the LSTM-GBR hybrid model for influenza forecasting.
• Validated the model against general-purpose forecasting methods.
• Focused on local dynamics and structural breaks in the data.
• Achieved high accuracy in influenza forecasting for Xinjiang.
• Successfully captured complex local seasonal patterns.
• Highlighted the importance of localized forecasting tools in public health.