Generation of global 1 km daily soil moisture product from 2000 to 2020 using ensemble learning

Abstract

<p>Motivated by the lack of long-term global soil moisture products with both high spatial and temporal resolutions, a global 1 km daily spatiotemporally continuous soil moisture product (GLASS SM) was generated from 2000 to 2020 using an ensemble learning model (eXtreme Gradient Boosting – XGBoost). The model was developed by integrating multiple datasets, including albedo, land surface temperature, and leaf area index products from the Global Land Surface Satellite (GLASS) product suite, as well as the European reanalysis (ERA5-Land) soil moisture product, in situ soil moisture dataset from the International Soil Moisture Network (ISMN), and auxiliary datasets (Multi-Error-Removed Improved-Terrain (MERIT) DEM and Global gridded soil information (SoilGrids)). Given the relatively large-scale differences between point-scale in situ measurements and other datasets, the triple collocation (TC) method was adopted to select the representative soil moisture stations and their measurements for creating the training samples. To fully evaluate the model performance, three validation strategies were explored: random, site independent, and year independent. Results showed that although the XGBoost model achieved the highest accuracy on the random test samples, it was clearly a result of model overfitting. Meanwhile, training the model with representative stations selected by the TC method could considerably improve its performance for site- or year-independent test samples. The overall validation accuracy of the model trained using representative stations on the site-independent test samples, which was least likely to be overfitted, was a correlation coefficient (<em>R</em>) of 0.715 and root mean square error (RMSE) of 0.079 m³ m⁻³. Moreover, compared to the model developed without station filtering, the validation accuracies of the model trained with representative stations improved significantly for most stations, with the median <em>R</em> and unbiased RMSE (ubRMSE) of the model for each station increasing from 0.64 to 0.74 and decreasing from 0.055 to 0.052 m³ m⁻³, respectively. Further validation of the GLASS SM product across four independent soil moisture networks revealed its ability to capture the temporal dynamics of measured soil moisture (<em>R</em>=0.69–0.89; ubRMSE = 0.033–0.048 m³ m⁻³). Lastly, the intercomparison between the GLASS SM product and two global microwave soil moisture datasets – the 1 km Soil Moisture Active Passive/Sentinel-1 L2 Radiometer/Radar soil moisture product and the European Space Agency Climate Change Initiative combined soil moisture product at 0.25^∘ – indicated that the derived product maintained a more complete spatial coverage and exhibited high spatiotemporal consistency with those two soil moisture products. The annual average GLASS SM dataset from 2000 to 2020 can be freely downloaded from <a href="https://doi.org/10.5281/zenodo.7172664">https://doi.org/10.5281/zenodo.7172664</a> (Zhang et al., 2022a), and the complete product at daily scale is available at <a href="http://glass.umd.edu/soil_moisture/">http://glass.umd.edu/soil_moisture/</a> (last access: 12 May 2023).</p>