A reduced latency regional gap-filling method for SMAP using random forest regression

Xiaoyi Wang; Haishen Lü; Wade T Crow; Gerald Corzo; Yonghua Zhu; Jianbin Su; Jingyao Zheng; Qiqi Gou

doi:10.1016/j.isci.2022.105853

A reduced latency regional gap-filling method for SMAP using random forest regression

iScience. 2022 Dec 22;26(1):105853. doi: 10.1016/j.isci.2022.105853. eCollection 2023 Jan 20.

Authors

Xiaoyi Wang^{1

2}, Haishen Lü^{1

2}, Wade T Crow³, Gerald Corzo⁴, Yonghua Zhu^{1

2}, Jianbin Su⁵, Jingyao Zheng^{1

2}, Qiqi Gou^{1

2}

Affiliations

¹ State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China.
² Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China.
³ USDA-ARS Hydrology and Remote Sensing Laboratory, Beltsville, MD 20705-2350, USA.
⁴ Hydroinformatics Chair Group, IHE Delft Institute for Water Education, 2611AX Delft, the Netherlands.
⁵ National Tibetan Plateau Data Center, Key Laboratory of Tibetan Environmental Changes and Land Surface Processes, Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing 100101, China.

Abstract

The soil moisture active/passive (SMAP) mission represents a significant advance in measuring soil moisture from satellites. However, its large spatial-temporal data gaps limit the use of its values in near-real-time (NRT) applications. Considering this, the study uses NRT operational metadata (precipitation and skin temperature), together with some surface parameterization information, to feed into a random forest model to retrieve the missing values of the SMAP L3 soil moisture product. This practice was tested in filling the missing points for both SMAP descending (6:00 AM) and ascending orbits (6:00 PM) in a crop-dominated area from 2015 to 2019. The trained models with optimized hyper-parameters show the goodness of fit (R² ≥ 0.86), and their resulting gap-filled estimates were compared against a range of competing products with in situ and triple collocation validation. This gap-filling scheme driven by low-latency data sources is first attempted to enhance NRT spatiotemporal support for SMAP L3 soil moisture.

Keywords: Earth sciences; Remote sensing; Soil science.