Improvement of CMIP6 water vapor accuracy by the digital twin innovation based on GNSS

The accelerating pace of global warming poses unprecedented challenges to climate prediction and environmental sustainability. The ensuing development of the sixth phase of the Coupled Model Intercomparison Project (CMIP6) has empowered climate research into a new era, enabling simulation and projection of the global atmosphere. However, the Global Climate Models (GCMs) database is built upon physical models, inevitably with limitations of deficient observational restraints, insufficient regional simulation capacities and low spatio-temporal resolution. In contrast, the Global Navigation Satellite System (GNSS) is characterized by high precision, high temporal resolution and all-weather availability. Therefore, we propose a GNSS-integrated approach that leverages the high-precision feature of GNSS observations to enhance CMIP6 water vapor accuracy and demonstrate the improved performances of the digital twin of atmospheric Precipitable Water Vapor (PWV) over the Turkey with comprehensive validations. The results show that the Root Mean Square Errors (RMSEs) of CMIP6 water vapor improved from CNN, XGBoost and LSTM algorithm digital twins are 4.57 mm, 4.04 mm and 4.93 mm against GNSS-PWV and 5.40 mm, 5.66 mm and 5.41 mm against ERA5-PWV, which are improved by 22.27 %, 18.51 % and 22.12 %, respectively. Spatio-temporal analysis reveals the pronounced improvements during winter and in mid-altitude regions. Notably, low RMSEs were recorded in the eastern and central inland areas (improved by 50 % upon XGBoost). Across all digital twin implementations, this study pioneers GNSS into CMIP6 water vapor correction, improving the accuracy of future water vapor projections from GCMs obviously. These breakthroughs promote the contribution of GNSS in meteorology and geodesy for climate research.