Stable hydrogen isoscape in precipitation generated using data fusion for East China

The stable hydrogen isotope in precipitation is an effective environmental tracer for climatic and hydrologic studies. However, accurate and high-precision precipitation hydrogen isoscapes are currently unavailable in China. In this study, a data fusion method based on Convolutional Neural Networks (CNN) is used to fuse the hydrogen isotopic composition (δ²H_p) of observations and isotope-equipped general circulation model (iGCM) simulations. A precipitation hydrogen isoscape with a temporal resolution of monthly and a spatial resolution of 50–60 km is established for East China for the 1969–2017 period. Prior to building the isoscape, the performance of three data fusion methods (DFMs) and two bias correction methods (BCMs) is compared. The results indicate that the CNN fusion method performs the best with a correlation coefficient larger than 0.90 and root mean square error smaller than 10.5‰when using observation as a benchmark. The fusion methods based on back propagation and long short-term memory neural network perform similarly, while slightly outperforming the bias correction methods. Thus, the CNN method is used to generate the hydrogen isoscape, and the temporal and spatial distribution characteristics of the hydrogen isotope in precipitation are analyzed based on this dataset. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ²H_p is consistent with the temperature effect in northern China, and consistent with the precipitation amount effect in southern China. The trend of the δ²H_p time series is consistent with that of observed precipitation and temperature. Overall, the generated isoscape effectively reproduces the observations, and has the characteristics of time continuity and relative spatial regularity, which can provide valuable data support for tracking atmospheric and hydrological processes.