Influpaint uses diffusion models to forecast influenza incidence by encoding disease dynamics as spatiotemporal images

Influpaint adapts denoising diffusion probabilistic models (AI systems that learn to generate data by reversing noise) to epidemic forecasting, encoding influenza seasons as spatiotemporal images where pixel intensity represents incidence.

In real-time evaluation during the 2023–2025 U.S. CDC FluSight challenges, performance improved substantially across seasons, with highly accurate but somewhat overconfident projections in 2024–2025. Best performance was achieved with a training dataset containing 30% surveillance and 70% simulated trajectories.

Influpaint generates realistic, diverse epidemic trajectories and achieves forecast accuracy that is competitive with leading ensemble methods in retrospective evaluation, demonstrating that diffusion models can capture spatiotemporal structure in influenza dynamics.