An improved global remote-sensing-based surface soil moisture (RSSSM) dataset covering 2003–2018

Abstract

Abstract. Soil moisture is an important variable linking the atmosphere and terrestrial ecosystems. However, long-term satellite monitoring of surface soil moisture at the global scale needs improvement. In this study, we conducted data calibration and data fusion of 11 well-acknowledged microwave remote-sensing soil moisture products since 2003 through a neural network approach, with Soil Moisture Active Passive (SMAP) soil moisture data applied as the primary training target. The training efficiency was high (R2=0.95) due to the selection of nine quality impact factors of microwave soil moisture products and the complicated organizational structure of multiple neural networks (five rounds of iterative simulations, eight substeps, 67 independent neural networks, and more than 1 million localized subnetworks). Then, we developed the global remote-sensing-based surface soil moisture dataset (RSSSM) covering 2003–2018 at 0.1∘ resolution. The temporal resolution is approximately 10 d, meaning that three data records are obtained within a month, for days 1–10, 11–20, and from the 21st to the last day of that month. RSSSM is proven comparable to the in situ surface soil moisture measurements of the International Soil Moisture Network sites (overall R2 and RMSE values of 0.42 and 0.087 m3 m−3), while the overall R2 and RMSE values for the existing popular similar products are usually within the ranges of 0.31–0.41 and 0.095–0.142 m3 m−3), respectively. RSSSM generally presents advantages over other products in arid and relatively cold areas, which is probably because of the difficulty in simulating the impacts of thawing and transient precipitation on soil moisture, and during the growing seasons. Moreover, the persistent high quality during 2003–2018 as well as the complete spatial coverage ensure the applicability of RSSSM to studies on both the spatial and temporal patterns (e.g. long-term trend). RSSSM data suggest an increase in the global mean surface soil moisture. Moreover, without considering the deserts and rainforests, the surface soil moisture loss on consecutive rainless days is highest in summer over the low latitudes (30∘ S–30∘ N) but mostly in winter over the mid-latitudes (30–60∘ N, 30–60∘ S). Notably, the error propagation is well controlled with the extension of the simulation period to the past, indicating that the data fusion algorithm proposed here will be more meaningful in the future when more advanced microwave sensors become operational. RSSSM data can be accessed at https://doi.org/10.1594/PANGAEA.912597 (Chen, 2020).

Generating seamless global daily AMSR2 soil moisture (SGD-SM) long-term products for the years 2013–2019

“…Nevertheless, the acquired daily soil moisture products are always incomplete in global land (see Fig. 1a, about 30 %-80 % missing ratio in AMSR2), because of the satellite orbit coverage and the limitations of soil moisture retrieval algorithms (Cho et al, 2017;Long et al, 2019). The invalid land regions refer to areas with a gap or missing information.…”

Daily soil moisture mapping at 1 km resolution based on SMAP data for areas affected by desertification in Northern China

“…MLR and SVR have been widely used as regression methods in the past (Yu et al, 2012;Achieng, 2019;Wang et al, 2019). ANN is currently one of the most popular machine learning methods and is used in many fields, including remote sensing of soil moisture inversion (Del Frate et al, 2003;Elshorbagy and Parasuraman, 2008;Yao et al, 2017;Chen et al, 2021).…”

“…Machine learning methods can be applied to show the nonlinear relationships between SM and surface variables. Random forest (RF) and artificial neural network (ANN) have been widely used in previous studies due to their high generalization ability and robustness (Yao et al, 2017;Liu et al, 2020;Demarchi et al, 2020;Chen et al, 2021). Chen et al (2021) developed the global surface SM dataset covering 2003-2018 at 0.1° resolution with neural networks and some related variables.…”

“…Random forest (RF) and artificial neural network (ANN) have been widely used in previous studies due to their high generalization ability and robustness (Yao et al, 2017;Liu et al, 2020;Demarchi et al, 2020;Chen et al, 2021). Chen et al (2021) developed the global surface SM dataset covering 2003-2018 at 0.1° resolution with neural networks and some related variables. Im et al (2016) used machine learning approaches (RF, boosted regression trees, and Cubist) to downscale AMSR-E SM data in South Korea and Australia and found RF to be superior to the other downscaling methods.…”

InterComparison and Evaluation of MultiSource Soil Moisture Products in China

“…With the rapid development of remote sensing technology and the continuous improvement of relevant models, various SM estimation products (such as reanalysis, Land Data Assimilation Systems [LDAS], and satellite retrieval) are more widely used in the existing research because of their good spatiotemporal continuity. But due to the differences in data source, algorithms, coverage, and spatiotemporal resolution, all these products are subject to great uncertainties (Chen & Yuan, 2020; Chen et al., 2020, 2021). On the other hand, many different products (e.g., ERA‐Interim and ERA5) are constantly being iterated and updated.…”