Using machine learning to produce near surface soil moisture estimates from deeper in situ records at U.S. Climate Reference Network (USCRN) locations: Analysis and applications to AMSR-E satellite validation |
| |
| Institution: | 1. USDA-ARS-Hydrology and Remote Sensing Laboratory, Beltsville, MD, USA;2. Cooperative Institute for Climate and Satellites - NC, Asheville, NC, USA;3. NOAA-National Centers for Environmental Information, Asheville, NC, USA;4. Southeast Climate Science Center, N.C.State University. Raleigh, NC, USA;1. Department of Civil and Architectural Engineering, KTH Royal Institute of Technology, Brinellvägen 23, 10044, Stockholm, Sweden;2. Policy Wing, Ministry of Petroleum and Natural Resources, Government of Pakistan, Pakistan;3. Hydrogeology Group, Department of Geotechnical Engineering and Geosciences, Universitat Politècnica de Catalunya, UPC-BarcelonaTech, 08034 Barcelona, Spain;4. School of Mechanical, Aerospace and Civil Engineering, University of Manchester, United Kingdom;1. Department of Mathematics, and College of Earth, Ocean, and Atmospheric Sciences, Oregon State University, Corvallis, OR 97331, USA;2. Department of Mathematics and Program in Applied Mathematics, University of Arizona, Tucson AZ 85721, USA;1. Department of Soil System Science, Helmholtz Centre for Environmental Research – UFZ, Halle (Saale), Germany;2. Department of Geosciences/Soil Physics Division, University of Bayreuth, Bayreuth, Germany;3. Departamento de Recursos Hídricos y Ciencias Ambientales, Facultad de Ciencias Agropecuarias, Universidad de Cuenca, Cuenca, Ecuador |
| |
| Abstract: | Surface soil moisture is a critical parameter for understanding the energy flux at the land atmosphere boundary. Weather modeling, climate prediction, and remote sensing validation are some of the applications for surface soil moisture information. The most common in situ measurement for these purposes are sensors that are installed at depths of approximately 5 cm. There are however, sensor technologies and network designs that do not provide an estimate at this depth. If soil moisture estimates at deeper depths could be extrapolated to the near surface, in situ networks providing estimates at other depths would see their values enhanced. Soil moisture sensors from the U.S. Climate Reference Network (USCRN) were used to generate models of 5 cm soil moisture, with 10 cm soil moisture measurements and antecedent precipitation as inputs, via machine learning techniques. Validation was conducted with the available, in situ, 5 cm resources. It was shown that a 5 cm estimate, which was extrapolated from a 10 cm sensor and antecedent local precipitation, produced a root-mean-squared-error (RMSE) of 0.0215 m3/m3. Next, these machine-learning-generated 5 cm estimates were also compared to AMSR-E estimates at these locations. These results were then compared with the performance of the actual in situ readings against the AMSR-E data. The machine learning estimates at 5 cm produced an RMSE of approximately 0.03 m3/m3 when an optimized gain and offset were applied. This is necessary considering the performance of AMSR-E in locations characterized by high vegetation water contents, which are present across North Carolina. Lastly, the application of this extrapolation technique is applied to the ECONet in North Carolina, which provides a 10 cm depth measurement as its shallowest soil moisture estimate. A raw RMSE of 0.028 m3/m3 was achieved, and with a linear gain and offset applied at each ECONet site, an RMSE of 0.013 m3/m3 was possible. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
