Filling Satellite Microwave Observation Gaps via Generative Synthesis
Remote Sensing · 07.07.2026 · 18 (13) · 2256
DOI: 10.3390/rs18132256 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 07.07.2026. Verfasst von Han Du und 14 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, China Meteorological Administration Tornado Key Laboratory.
Abstract (Originalsprache)
Polar-orbiting microwave radiometers provide indispensable all-weather measurements of the atmospheric state, yet revisit intervals of many hours leave critical gaps during rapidly evolving weather events. To address this limitation, we developed MIDAS (Microwave Inference via Diffusion Across Satellites), a probabilistic framework that estimates microwave brightness temperature (BT) fields across the geostationary full-disk domain from infrared observations at 10 min intervals. This study focuses on the five Microwave Humidity Sounder-2 (MWHS-2) humidity-sounding channels near 183 GHz, which provide vertically resolved water vapor information. MIDAS achieves relative errors below 0.5% for the majority of cases, with a channel-averaged mean absolute error of 1.15 K, outperforming a deterministic U-Net baseline (1.43 K). Beyond per-sample evaluation, MIDAS reproduces large-scale climatological patterns across the full-disk domain over a three-month summer period, consistent with Radiative Transfer for TOVS–Scattering (RTTOV-SCATT) simulations. In deep convective scenes where reconstruction is most difficult, the ensemble spread naturally tracks reconstruction difficulty, providing a built-in indicator of prediction confidence. Notably, MIDAS incorporates real-time polar-orbiting observations as physical constraints via a merge-sampling mechanism, reducing ensemble RMSE by over 20% and improving probabilistic calibration by more than 30%. Proof-of-concept assimilation experiments for two high-impact weather cases show that MIDAS-generated fields yield forecast improvements comparable to those from real satellite observations, reducing tropical cyclone track errors from approximately 110 km to 40 km and improving heavy precipitation forecasts at extreme rainfall thresholds where direct infrared assimilation shows no benefit. Overall, our framework demonstrates the potential of generative models to supplement sparse observational coverage and provide physically plausible microwave humidity fields for downstream applications.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- China Meteorological Administration Tornado Key Laboratory
- Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications
Zitieren
APA
Du, H., Pan, B., Ping, F., Xu, J., Nai, C., Sun, S., Chao, J., Wang, J., Yang, S., Chen, X., Li, J., Mao, J., Yin, L., Li, Y., & Xiao, Z. (2026). Filling Satellite Microwave Observation Gaps via Generative Synthesis. Remote Sensing, 18(13), 2256. https://doi.org/10.3390/rs18132256
Vancouver
Du H, Pan B, Ping F, Xu J, Nai C, Sun S, et al. Filling Satellite Microwave Observation Gaps via Generative Synthesis. Remote Sensing. 2026;18(13):2256. doi:10.3390/rs18132256
BibTeX
@article{Du2026,
author = {Du, Han and Pan, Baoxiang and Ping, Fan and Xu, Jin and Nai, Congyi and Sun, Sencan and Chao, Jie and Wang, Jingnan and Yang, Shangshang and Chen, Xi and Li, Jingyuan and Mao, Jiahua and Yin, Lei and Li, Yupeng and Xiao, Ziniu},
title = {Filling Satellite Microwave Observation Gaps via Generative Synthesis},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {13},
pages = {2256},
doi = {10.3390/rs18132256}
}
EUVIMED