Machine Learning Techniques for Downscaling SMOS Satellite Soil Moisture Using MODIS Land Surface Temperature for Hydrological Application

2013 ◽  
Vol 27 (8) ◽  
pp. 3127-3144 ◽  
Author(s):  
Prashant K. Srivastava ◽  
Dawei Han ◽  
Miguel Rico Ramirez ◽  
Tanvir Islam
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Machine Learning Techniques ◽  
Modis Land Surface Temperature ◽  
Learning Techniques ◽  
Smos Satellite

scholarly journals Improving Predictions of Water and Heat Fluxes by Assimilating MODIS Land Surface Temperature Products into the Common Land Model

2011 ◽  
Vol 12 (2) ◽  
pp. 227-244 ◽  
Author(s):  
Tongren Xu ◽  
Shaomin Liu ◽  
Shunlin Liang ◽  
Jun Qin
Keyword(s):  
Soil Moisture ◽  
Data Assimilation ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Heat Fluxes ◽  
Model Parameters ◽  
Modis Land Surface Temperature ◽  
Common Land Model ◽  
The Common

Abstract Four data assimilation scheme combinations derived from two strategies and two optimization algorithms [the ensemble Kalman filter (EnKF) and the shuffled complex evolution method developed at The University of Arizona (SCE-UA)] are developed based on the Common Land Model (CLM) to improve predictions of water and heat fluxes. The first strategy is constructed through adjusting the soil temperature, while the second strategy adjusts the soil moisture. Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST) products are compared with ground-measured surface temperature, and assimilated into the CLM. The relationship equation between the MODIS LST products and CLM surface temperature is taken as the observation operator and the root-mean-square error (RMSE) is applied as the observation error. The assimilation results are validated by measurements from six observation sites located in Germany, the United States, and China. Results indicate that the developed data assimilation schemes can improve estimates of water and heat fluxes. Overall, strategy 2 is superior to strategy 1 when using the same optimization algorithm. The EnKF algorithm performs slightly better than the SCE-UA algorithm when using the same strategy. Strategy 2 combined with the EnKF algorithm performs best for water and heat fluxes, and the reductions in the RMSE are found to be 24.0 and 15.2 W m−2 for sensible and latent heat fluxes, respectively. The joint assimilation of the MODIS LST and soil moisture observations can produce better results for strategy 2 with the SCE-UA. Since preprocessing model parameters are used in this study, the uncertainties in the model parameters may have resulted in suboptimal assimilation results. Therefore, model calibrations should be conducted in the future.

scholarly journals Spatial Downscaling of SMAP Soil Moisture Using MODIS Land Surface Temperature and NDVI During SMAPVEX15

2017 ◽  
Vol 14 (11) ◽  
pp. 2107-2111 ◽  
Author(s):  
Andreas Colliander ◽  
Joshua B. Fisher ◽  
Gregory Halverson ◽  
Olivier Merlin ◽  
Sidharth Misra ◽  
...  
Keyword(s):  
Soil Moisture ◽  
Surface Temperature ◽  
Land Surface Temperature ◽  
Land Surface ◽  
Modis Land Surface Temperature ◽  
Spatial Downscaling
Sign in / Sign up

Export Citation Format

Share Document