Impact of VAEformer Compression Algorithm Precision Loss on the Tropospheric Delays for Microwave Remote Sensing

Junsheng Ding, Cancan Xu, Wu Chen, Junping Chen, Jungang Wang, Yize Zhang, Lei Bai, Tao Han, Yuhao Xiong

Abstract: Ray-tracing through numerical weather models (NWMs) is one of the most accurate methods for determining slant tropospheric delays (STDs) in microwave remote sensing. However, the massive data volumes of high-resolution NWMs create substantial I/O operations, limiting large-scale ray-tracing on general hardware. This constraint has historically necessitated parameterized tropospheric delay models, which are disseminated as standardized products (e.g., zenith delays with mapping functions and horizontal gradients). Recently, the AI-driven VAEformer algorithm revolutionized NWM compression, achieving >470:1 ratios by compressing 37 pressure level, 0.25° $\times$ 0.25° fifth-generation ECMWF atmospheric reanalysis (ERA5) data into files smaller than surface-only VMF3 products (1° $\times$ 1° resolution). This breakthrough challenges the conventional reliance on parameterized models as the sole practical solution. We quantified discrepancies in tropospheric delay parameters between original ERA5 and variational autoencoder transformer (VAEformer)-compressed extreme compression of ERA5 (CRA5) data across 2022, evaluating compression fidelity on global grids and against in situ zenith tropospheric delay (ZTD) estimates. Results show global average precision loss from compression is <2 mm (<5%) for ZTD, with RMSE differences <0.2 mm when validated against over 5000 global navigation satellite system (GNSS) stations. These errors are significantly smaller than interanalysis center (AC) variations (4–6 mm) and GNSS-NWM mismatches (>10 mm). Our findings demonstrate CRA5 as a reliable ERA5 substitute, with compression-induced inaccuracies being negligible for most microwave-based remote sensing applications. This work underscores that parameterized delay modeling is no longer the exclusive pathway, enabling efficient local computation of high-precision STDs without through mapping functions and gradients.

External IDs:doi:10.1109/tgrs.2025.3587944