Association of Pediatric Influenza with Weather: Analysis and Prediction in Tianjin, China

Children are highly vulnerable to influenza with severe complications. Weather conditions can substantially modulate patterns of influenza transmission. This study collated historical (2018–2024) cases of daily pediatric influenza-like illness (ILI) and weekly ILI percentage (ILI%) in Tianjin, a megacity near Beijing (China), together with data of concurrent meteorological variables. Meteorological signals associated with increased cases of pediatric influenza were identified by distinguishing non-epidemic and epidemic seasons. A machine learning Informer–Long Short-Term Memory (LSTM) hybrid framework was developed for meteorological risk prediction of pediatric influenza, with validation conducted during the 2024–2025 seasonal influenza epidemic. During non-epidemic periods, lower temperature (4-day mean T_max < 20°C, T_min < 12°C) and larger diurnal temperature range (DTR; 4-day mean DTR > 10°C) triggered pediatric ILI fluctuations, with differential impacts across age groups. The onset of the seasonal influenza epidemic was strongly predictable using thresholds of T_min < 0°C and specific humidity (q_ave) < 3 g kg⁻¹, which could enable two-week advance warnings. The supervised rolling LSTM model integrating meteorological variables (mean atmospheric pressure (P_ave), T_min, DTR, relative humidity (RH), or q_ave), holiday patterns (Holiday and School day), and future ILI% prediction by Informer achieved precise forecasts of the onset, surge, peak duration, and decline of ILI cases during the seasonal influenza epidemic of 2024–2025, demonstrating superior temporal resolution and accuracy. By calculating meteorological risk factors from predicted daily pediatric ILI cases, we are able to provide actionable risk alerts for optimized medical resource allocation and targeted prevention strategies in schools and households. Through integration of weather forecasts and epidemiological surveillance, the method proposed in this study could be used to advance location-specific influenza preparedness and better cope with health concerns associated with climate change.