No abstract

No abstract

The use of hydrogen and oxygen stable isotopes in estimating soil water evaporation loss under continuous evaporation conditions is crucial for gaining insight into soil water movement processes under different conditions. In this study, via highfrequency meteorological monitoring and continuous soil water measurements, we investigated the variation of hydrogen and oxygen stable isotopes and soil water fluxes with soil depth and time for soil water at different depths under continuous evaporation conditions. The precipitation isotope δ rain and soil water flux changes were determined using the Craig-Gordon model. It was shown that the isotopic fractionation of soil water in the surface layer 0-30 cm was dominated by a gaseousdominated transport process, and that both the δ 18 O and δD values and evaporative intensity decreased with increasing soil depth. In terms of time dynamics, the evaporation loss of soil water varies continuously with seasons and is the highest during summer. The use of δ 18 O to quantify the soil water evaporation loss provides greater accuracy than that provided by δD. The relative errors in the evaporation loss calculated based on δ 18 O and δD were 13% and 34%, respectively. A sensitivity analysis of each parameter indicated that the relative error calculated by the model is primarily determined by temperature and relative humidity uncertainty. The sensitivity analysis reveals the critical evaporation intensity of soil water at various depths from unsteady to steady state evaporation. When the relative humidity changes by 1%, the evaporation loss fraction changes from 0.001 to 0.034. The results of this study are important for quantifying the soil water resources in arid and semi-arid areas without precipitation using stable isotopes of hydrogen and oxygen.

No abstract

The combined utilization of spatiotemporal clustering and deep learning neural network models were designed to evaluate the applicability of the multi-year and multi-sites precipitation δ18O forecasting method based on the precipitation isotope data of 10 stations in Germany from 1988 to 2012. In the overall forecasting, the performance of single-site multi-year forecasting is in the order of the Bi-directional Long Short-Term Memory (Bi-LSTM), CNN-Bi-LSTM, and the Convolutional Neural Network (CNN), with CNN-Bi-LSTM being the optimal model for multi-site multi-year forecasts. The seasonal forecasting does not demonstrate a significant improvement compared to the overall forecasting. For forecasting based on spatiotemporal clustering, cluster 1 improved accuracy, and cluster 2 improved error reduction and variance consistency. Nevertheless, the accuracy of forecasts depends solely on the amount of input data when the proportion of forecasting increases to a certain level. Overall, the seasonal forecasting is more appropriate for improving forecasting within a specific season, while spatiotemporal clustering can improve forecasting accuracy to some degree. In addition, optimal solutions exist for the type and number of model clusters. In terms of model types, CNN-Bi-LSTM generally has better forecasting performance than CNN and Bi-LSTM.