Triple Collocation-Based Model Error Estimation of VIC-Simulated Soil Moisture at Spatial and Temporal Scales in the Continental United States in 2010–2020

The model error is a direct reflection of the accuracy of the model simulation. However, it is challenging to estimate the model error due to the presence of numerous uncertainties inherent to the atmospheric and soil data, as well as the structure and parameters of the model itself. This paper addresses the fundamental issue of error estimation in the simulation of soil moisture by the Variable Infiltration Capacity (VIC) model, with a particular focus on the continental United States from 2010 to 2020. The paper develops a model error estimation method based on the Triple Collocation (TC) error estimation and in situ data validation of the VIC model at different temporal and spatial scales. Furthermore, it addresses the issue of failing to consider the variability of temporal and spatial scales in model error estimations. Furthermore, it generates the standard product data on soil moisture simulation errors for the VIC model in the continental United States. The mean of the simulation error variance of the VIC model, estimated using the TC method for spatially scaled soil moisture in the continental United States, is found to be 0.0045 (m³/m³)², with a median value of 0.0042 (m³/m³)². The mean time-scale error variance of the VIC model, validated using ground station data, is 0.0096 (m³/m³)², with a median value of 0.0078 (m³/m³)². Concurrently, the paper employs Köppen climate classification and land cover data as supplementary data, conducting a comprehensive investigation and analysis of the characteristics and alterations of the VIC model error in the study area from both temporal and spatial perspectives. The findings indicate a proclivity for reduced error rates during the summer months and elevated rates during the winter, with lower rates observed in the western region and higher rates in the eastern region. The objective of this study is twofold: firstly, to conduct a quantitative assessment and analysis of the VIC model’s simulation capabilities; secondly, to validate the accuracy and quality of the soil moisture products simulated by the model. The accurate estimation of model errors is a fundamental prerequisite for the numerical simulation and data assimilation of models, which has a vast range of applications in numerical meteorological and hydrological forecasting, natural environment monitoring, and other fields.