Spatiotemporal Imputation of Traffic Emissions With Self-Supervised Diffusion Model

The comprehensive regulatory oversight of traffic emissions frequently encounters the missing not-at-random (MNAR) pattern, characterized by the long-term block missing in adjacent road segments, arising from insufficient monitoring points and nonuniform spatiotemporal distribution. The spatiotemporal block missing simultaneously disrupts the spatiotemporal correlation, introducing significant biases in spatiotemporal modeling for incomplete data. The emerging diffusion model recovers the information of the missing regions in a self-supervised manner and focuses on the generation process of the missing regions to address biases. However, the dynamics and spatiotemporal heterogeneity of traffic emissions limit its applicability in unknown spatiotemporal missing. To address this issue, this article proposes a novel progressive
D
iffusion
M
odel-based framework for
S
patio
T
emporal
I
mputation of traffic emissions (STI-dm). Specifically, a self-supervised masked training strategy is first devised to construct the nonlocal similarity prior of traffic emission data, explicitly introducing the MNAR missing mechanism for the diffusion process. Furthermore, an enhanced approach of noise injection and supervised denoising is adopted to rectify misconceptions of nonlocal alignment, decreasing modeling biases associated with incomplete data in the generation process. The imputation and prior modeling processes are progressively performed until obtaining stable results, and each of the preceding modeling processes benefits from the gradual improvement results in the other. Experimental evidence indicates that STI-dm surpasses the current state-of-the-art algorithms in scenarios with intricate spatiotemporal patterns and varying rates of missing data.