A generative ozone concentration imputation and forecasting method based on a novel conditional diffusion model

doi:10.1016/j.jhazmat.2025.139075

A generative ozone concentration imputation and forecasting method based on a novel conditional diffusion model

2025-07-01

0

PRE

AI

DOI：10.1016/j.jhazmat.2025.139075

Original

Original request for help

Save

Abstract

En 中文

• The generative method ensures integrity and prediction quality of ozone sequence. • Joint noise prediction network in diffusion model combines Transformer and SSSD. • Capturing the uncertainty of noise promotes clean ozone sequence generation. • Imputation and forecasting are achieved with high quality simultaneously. • The method outperformed other models including the standard Transformer and SSSD.

A generative ozone concentration imputation and forecasting method based on a novel conditional diffusion model

Abstract

Journal

Organization