Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction
ACM Transactions on Internet of Things · 28.02.2025 · 6 (1) · 1-24
DOI: 10.1145/3702243 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Internet of Things, online erschienen am 08.01.2025. Verfasst von Jinxiao Fan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 61 Literaturangaben. Gefördert von: NSFC, Beijing Major Science and Technology Project, A3 Foresight Program of NSFC.
Abstract (Originalsprache)
Predicting air quality using multimodal data is crucial to comprehensively capture the diverse factors influencing atmospheric conditions. Therefore, this study introduces a multimodal learning framework that integrates outdoor images with traditional ground-based observations to improve the accuracy and reliability of air quality predictions. However, aligning and fusing these heterogeneous data sources poses a formidable challenge, further exacerbated by pervasive data incompleteness issues in practice. In this article, we propose a novel incomplete multimodal learning approach (iMMAir) to recovery missing data for robust air quality prediction. Specifically, we first design a shallow feature extractor to capture modal-specific features within the latent representation space. Then we develop a conditional diffusion-driven recovery module to mitigate the distribution gap between the recovered and true data. This module further incorporates two conditional constraints of temporal correlation and semantic consistency for effective modal completion. Finally, we reconstruct incomplete modalities and fuse available data using a multimodal transformer network to predict the air quality. To alleviate the modality imbalance problem, we employ an adaptive gradient modulation strategy to adjust the optimization of each modality. Experimental results demonstrate that iMMAir significantly reduces prediction errors, outperforming baseline models by an average of 5.6% and 2.5% in air quality regression and classification tasks. Our source code and data are available at https://github.com/pestasu/IMMAir .
Förderung
- NSFC
- Beijing Major Science and Technology Project
- A3 Foresight Program of NSFC
- Beijing Natural Science Foundation
Zitieren
APA
Fan, J., Qi, M., Liu, L., & Ma, H. (2025). Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction. ACM Transactions on Internet of Things, 6(1), 1-24. https://doi.org/10.1145/3702243
Vancouver
Fan J, Qi M, Liu L, Ma H. Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction. ACM Transactions on Internet of Things. 2025;6(1):1-24. doi:10.1145/3702243
BibTeX
@article{Fan2025,
author = {Fan, Jinxiao and Qi, Mengshi and Liu, Liang and Ma, Huadong},
title = {Diffusion-driven Incomplete Multimodal Learning for Air Quality Prediction},
journal = {ACM Transactions on Internet of Things},
year = {2025},
volume = {6},
number = {1},
pages = {1--24},
doi = {10.1145/3702243}
}
EUVIMED