ABSTRACT:

Monthly and weekly soil moisture predictions in 2010 at 1-km spatial resolution using two different modeling methods integrated in the modular SOil Moisture SPatial Inference Engine (SOMOSPIE- Rorabaugh et al. 2019) (kernel-weighted k-nearest neighbors <KKNN>, Random Forests <RF>). Data were acquired from the European Space Agency Climate Change Initiative (ESA CCI) soil moisture product version 6.1, 0.25-degrees spatial resolution. Modeled soil moisture layers are delivered for two regions in the conterminous United States. Each region encompasses a polygon of 7.5° x 3.75° (n = 450 pixels with 30 columns and 15 rows in the native resolution of the ESA CCI Soil moisture product). Region 1 <so called West Region> consists of an area of 275,516 km2. Region 2 <so called Midwest region> consists of an area of 283,499 km2. Predicted soil moisture values were validated by means of two approaches, cross-validation using the ESA CCI estimates and independent ground-truth records from the North American Soil Moisture Database (currently known as the National Soil Moisture Network). Detailed methods and results of this dataset are described in: Llamas, R.M; Valera, Leobardo; Olaya, Paula; Taufer, Michela; Vargas, Rodrigo "Downscaling Satellite Soil Moisture based on a modular SOil Moisture SPatial Inference Engine (SOMOSPIE)", Remote Sensing (submitted).

ABSTRACT:

Monthly and weekly soil moisture predictions in 2010 at 1-km spatial resolution using two different modeling methods integrated in the modular SOil Moisture SPatial Inference Engine (SOMOSPIE- Rorabaugh et al. 2019) (kernel-weighted k-nearest neighbors <KKNN>, Random Forests <RF>). Data were acquired from the European Space Agency Climate Change Initiative (ESA CCI) soil moisture product version 6.1, 0.25-degrees spatial resolution. Modeled soil moisture layers are delivered for two regions in the conterminous United States. Each region encompasses a polygon of 7.5° x 3.75° (n = 450 pixels with 30 columns and 15 rows in the native resolution of the ESA CCI Soil moisture product). Region 1 <so called West Region> consists of an area of 275,516 km2. Region 2 <so called Midwest region> consists of an area of 283,499 km2. Predicted soil moisture values were validated by means of two approaches, cross-validation using the ESA CCI estimates and independent ground-truth records from the North American Soil Moisture Database (currently known as the National Soil Moisture Network). Detailed methods and results of this dataset are described in: Llamas, R.M; Valera, Leobardo; Olaya, Paula; Taufer, Michela; Vargas, Rodrigo "Downscaling Satellite Soil Moisture based on a modular SOil Moisture SPatial Inference Engine (SOMOSPIE)", Remote Sensing (submitted).

ABSTRACT:

Monthly and weekly soil moisture predictions in 2010 at 1-km spatial resolution using four different Machine Learning Methods integrated in the Satellite Soil Moisture based on a modular SOil Moisture SPatial Inference Engine (SOMOSPIE- Rorabaugh et al. 2019) (kernel-weighted k-nearest neighbors <KKNN>, Random Forests <RF>, Surrogate-Based Model <SBM> and a Hybrid Piecewise Polynomial Modeling Technique <HYPPO>). Data were acquired from the European Space Agency Climate Change Initiative (ESA CCI) soil moisture product version 6.1, 0.25-degrees spatial resolution. Modeled soil moisture layers are delivered for two regions in the conterminous United States. Each region encompasses a polygon of 7.5° x 3.75° (n = 450 pixels with 30 columns and 15 rows in the native resolution of the ESA CCI Soil moisture product). Region 1 <so called West Region> comprises an area of 275,516 km2. Region 2 <so called Midwest region> comprises an area of 283,499 km2. Predicted soil moisture values were validated by means two approaches, cross-validation using the ESA CCI estimates and independent ground-truth records from the North American Soil Moisture Database (currently known as the National Soil Moisture Network). Detailed methods and results of this dataset are described in: Llamas, R.M; Valera, Leobardo; Olaya, Paula; Taufer, Michela; Vargas, Rodrigo “Downscaling Satellite Soil Moisture based on a modular SOil Moisture SPatial Inference Engine (SOMOSPIE)”, Remote Sensing (submitted).

ABSTRACT:

Monthly soil moisture predictions over a region of interest centered on Oklahoma and surrounded areas from January 2000 to September 2012. Data were acquired from the European Space Agency Climate Change Initiative soil moisture product version 4.5, 0.25-degrees spatial resolution. The modeled product aims to fill soil moisture spatial gaps from the original product over the region of Interest. Soil moisture values were calculated based on three methods, e.g. Ordinary Kriging, Regression Kriging and Generalized Linear Model. Reference monthly soil moisture layers were generated based on daily soil moisture estimates over each 0.25-degrees pixel in the region of interest. Three different sampling approaches were considered to model soil moisture estimates, using 100% of available data from the original satellite data, 75% and 50% of available soil moisture estimates respectively. Data were randomly removed to simulate different scenarios of gap presence in the original ESA CCI product. Soil Moisture values were validated by means of 10-fold cross validation and ground-truth validation with records from the North American Soil Moisture Data Base. Detailed methods and code cab be found in: Llamas, R.M; Guevara, Mario; Rorabaugh, Danny; Taufer, Michela; Vargas, Rodrigo. "Spatial Gap-Filling of ESA CCI Satellite-Derived Soil Moisture based on Geostatistical Techniques and Multiple Regression", Remote Sensing (accepted)