2026-08-05T02:57:24Zhttp://doidb.wdc-terra.org/oaip/oai

oai:doidb.wdc-terra.org:80242026-06-10T10:28:31ZDOIDBDOIDB.GFZ

false4DOIDB.GFZ 10.5880/GFZ.1.1.2024.001 Yuan, Peng Peng Yuan 0000-0002-1717-8425 GFZ German Research Centre for Geosciences, Potsdam, Germany Balidakis, Kyriakos Kyriakos Balidakis 0000-0002-3370-1300 GFZ German Research Centre for Geosciences, Potsdam, Germany Wang, Jungang Jungang Wang 0000-0002-7060-5342 GFZ German Research Centre for Geosciences, Potsdam, Germany Technische Universität Berlin, Berlin, Germany Xia, Pengfei Pengfei Xia 0000-0001-5499-0212 Wuhan University Wang, Jian Jian Wang 0000-0001-6512-4803 Wuhan University Zhang, Mingyuan Mingyuan Zhang 0009-0002-5040-2385 Wuhan University Jiang, Weiping Weiping Jiang 0000-0002-3267-9682 Wuhan University Schuh, Harald Harald Schuh 0000-0001-5443-0370 GFZ German Research Centre for Geosciences, Potsdam, Germany Technische Universität Berlin, Berlin, Germany Wickert, Jens Jens Wickert 0000-0002-7379-5276 GFZ German Research Centre for Geosciences, Potsdam, Germany Technische Universität Berlin, Berlin, Germany Deng, Zhiguo Zhiguo Deng 0000-0002-0452-9185 GFZ German Research Centre for Geosciences GFZ Data Services 2024 neural network troposphere model EARTH SCIENCE > ATMOSPHERE > ALTITUDE EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC PRESSURE EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC WATER VAPOR Yuan, Peng Peng Yuan 0000-0002-1717-8425 GFZ German Research Centre for Geosciences, Potsdam, Germany Deng, Zhiguo Zhiguo Deng 0000-0002-0452-9185 GFZ German Research Centre for Geosciences Yuan, Peng GFZ German Research Centre for Geosciences, Potsdam, Germany 2019-01-01/2021-12-31T18:00:00 Model 10.1029/2024GL111404 10.1002/qj.3803 CC BY 4.0 With the growing use of airborne platforms in Earth observation, accurate tropospheric delay corrections across various altitudes have become essential. Most existing tropospheric delay models are referenced to the Earth’s surface and rely on analytical closed-form vertical adjustments to approximate delays at user heights. However, these analytical models often fail to capture the complex vertical variations in atmospheric conditions.

To address this limitation, we developed a novel approach leveraging deep neural networks (DNN) to reconstruct global three-dimensional zenith hydrostatic delay (ZHD) and zenith wet delay (ZWD) derived from numerical weather models (NWM). Using the ERA5 pressure-level product (Hersbach et al., 2020) for model training, the DNN refines predictions by correcting the residuals of an analytical third-order exponential model (EXP3). This hybrid method takes advantage of the non-linear fitting capabilities of DNN, significantly enhancing the accuracy of vertical tropospheric delay corrections up to 14 km above the Earth’s surface. The model achieves an average precision of 0.4 mm for ZHD and 0.8 mm for ZWD, reducing root-mean-square (RMS) errors by 63% and 36%, respectively, compared to EXP3.

This dataset includes the EXP3 model, structured on a 1° × 1° global grid at four synoptic times daily (00:00, 06:00, 12:00, and 18:00 UTC) for the period 2019–2022. Additionally, it provides the corresponding DNN model to correct errors in the EXP3 predictions. It is important to note that the model is designed for altitudes ranging from the Earth’s surface up to 14 km.
Global coverage at synoptic hours in 2019-2021 -180 180 90 -90 Bundesministerium für Umwelt, Naturschutz, nukleare Sicherheit und Verbraucherschutz http://dx.doi.org/10.13039/501100013549 67KI32002C EKAPEx Deutsche Forschungsgemeinschaft http://dx.doi.org/10.13039/501100001659 SFB 1464, No. 434617780 TerraQ Deutsche Forschungsgemeinschaft http://dx.doi.org/10.13039/501100001659 FOR 5456, No. 490990195 COCAT State Key Laboratory of Geo-Information Engineering http://dx.doi.org/10.13039/501100011354 SKLGIE2024-M-1-1