AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecasting

Dimensions overall score 8.0

• AirDDE is the first neural delay differential equation framework for air quality forecasting that integrates delay modeling into continuous-time pollutant evolution under physical guidance.method 95%
• AirDDE achieves state-of-the-art forecasting performance with an average MAE reduction of 8.79% over the best baselines.result 92%
• Existing deep learning methods for air quality forecasting often overlook intrinsic delays in pollutant propagation by modeling pollutant dynamics as instantaneous processes.limitation 88%
• AirDDE introduces a memory-augmented attention module that retrieves globally and locally historical features to adaptively capture delay effects modulated by multifactor data.technical 90%
• AirDDE introduces a physics-guided delay evolving function grounded in the diffusion-advection equation that models diffusion, delayed advection, and source/sink terms.technical 90%
• The physics-guided delay evolving function can capture delay-aware pollutant accumulation patterns with physical plausibility.technical 85%
• Extensive experiments on three real-world datasets demonstrate AirDDE's effectiveness.result 88%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card