Machine learning for improvement of upper-tropospheric relative humidity in ERA5 weather model data

Wang, Ziming; Bugliaro, Luca; Gierens, Klaus; Hegglin, Michaela I.; Rohs, Susanne; Petzold, Andreas; Kaufmann, Stefan; Voigt, Christiane

doi:https://doi.org/10.5194/acp-25-2845-2025

Articles | Volume 25, issue 5

https://doi.org/10.5194/acp-25-2845-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/acp-25-2845-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 25, issue 5

Research article

|

07 Mar 2025

Research article |

| 07 Mar 2025

Machine learning for improvement of upper-tropospheric relative humidity in ERA5 weather model data

Ziming Wang, Luca Bugliaro, Klaus Gierens, Michaela I. Hegglin, Susanne Rohs, Andreas Petzold, Stefan Kaufmann, and Christiane Voigt

Supplement

https://doi.org/10.5194/acp-25-2845-2025-supplement

Data sets

IAGOS Data Portal D. Boulanger et al. https://doi.org/10.25326/20

Copernicus Climate Change Service (C3S) Climate Data Store (CDS) H. Hersbach et al. https://doi.org/10.24381/cds.bd0915c6

Tensorflow: Large-scale machine learning on heterogeneous distributed systems M. Abadi et al. https://arxiv.org/abs/1603.04467

Model code and software

pycontrails: Python library for modeling aviation climate impacts M. Shapiro et al. https://doi.org/10.5281/zenodo.7776686

Download

Article (3947 KB)
Full-text XML

Short summary

Upper-tropospheric relative humidity bias in the ERA5 weather model is corrected by 10 % by an artificial neural network using aircraft in-service humidity data and thermodynamic and dynamical variables. The improved skills of the weather model will advance cirrus research, weather forecasts, and measures for contrail reduction.