Soil moisture estimation using an artificial neural network: a feasibility study

An artificial neural network (ANN) based algorithm is implemented and tested for soil moisture estimation. The ANN model is calibrated (trained) and validated (tested) with data including National Centers for Environmental Protection (NCEP) daily precipitation; normalized difference vegetation index (NDVI) data processed by the US Geological Survey Earth Resources Observations Systems (USGS EROS) data center; Geostationary Operational Environmental Satellite (GOES) based, cloud-masked infrared (IR) skin temperature produced by the University of Maryland; and soil moisture profiles measured over the Oklahoma (OK) Mesonet. The performance of the ANN model is evaluated by direct comparison between the soil moisture estimated by the ANN model and the Mesonet measurements and by examining the correlation between them. Strong correlation is demonstrated between the ANN estimates and Mesonet measurements for spatially averaged data. This work suggests that the ANN model is a promising alternative to soil moisture estimation. The advantage of the ANN approach to soil moisture estimation is that it can provide estimates having resolution commenmmensurate with remotely sensed IR data and has the potential for worldwide coverage.

[1]  Jerome D. Fast,et al.  The Effect of Heterogeneous Soil Moisture on a Summer Baroclinic Circulation in the Central United States , 1991 .

[2]  William L. Crosson,et al.  Toward a Dynamic-Thermodynamic Assimilation of Satellite Surface Temperature in Numerical Atmospheric Models , 1994 .

[3]  E. Engman,et al.  Estimating Soil Moisture From Satellite Microwave Observations: Past and Ongoing Projects, and Relevance to GCIP. , 1999 .

[4]  Robert H. Woodward,et al.  Soil moisture estimation using GOES-VISSR infrared data - A case study with a simple statistical method , 1987 .

[5]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[6]  J. C. Price,et al.  Land surface temperature measurements from the split window channels of the NOAA 7 Advanced Very High Resolution Radiometer , 1984 .

[7]  Kuolin Hsu,et al.  Estimation of physical variables from multichannel remotely sensed imagery using a neural network: Application to rainfall estimation , 1999 .

[8]  Robert Hecht-Nielsen,et al.  Applications of counterpropagation networks , 1988, Neural Networks.

[9]  Robert H. Woodward,et al.  Determining Soil Moisture from Geosynchronous Satellite Infrared Data: A Feasibility Study , 1984 .

[10]  Thomas J. Schmugge,et al.  Estimation of Soil Moisture with Api Algorithms and Microwave Emission , 1981 .

[11]  P. Wetzel,et al.  Effects of Spatial Variations of Soil Moisture and Vegetation on the Evolution of a Prestorm Environment: A Numerical Case Study , 1991 .

[12]  L. Simmonds,et al.  Measurement of Evaporation from Bare Soil and its Estimation Using Surface Resistance , 1996 .

[13]  A. Robock,et al.  Satellite remote sensing of soil moisture in Illinois, United States , 1999 .

[14]  Andrew S. Jones,et al.  Data Assimilation of Satellite-Derived Heating Rates as Proxy Surface Wetness Data into a Regional Atmospheric Mesoscale Model. Part II: A Case Study , 1998 .

[15]  S. Sorooshian,et al.  Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks , 1997 .

[16]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[17]  Bhaskar J. Choudhury,et al.  Simulating Soil Water Recession Coefficients for Agricultural Watersheds , 1983 .

[18]  Moti Segal,et al.  Sensitivity of forecast rainfall in a Texas convective system to soil moisture and convective parameterization , 2000 .

[19]  Craig A. Clark,et al.  Numerical Simulations of the Effect of Soil Moisture and Vegetation Cover on the Development of Deep Convection , 1995 .

[20]  T. Carlson,et al.  Thermal remote sensing of surface soil water content with partial vegetation cover for incorporation into climate models , 1995 .

[21]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[22]  R. Pielke.  Mesoscale Meteorological Modeling , 1984 .

[23]  P. Doraiswamy,et al.  Relationship between satellite microwave radiometric data, antecedent precipitation index, and regional soil moisture , 1993 .

[24]  J. D. Tarpley,et al.  The multi‐institution North American Land Data Assimilation System (NLDAS): Utilizing multiple GCIP products and partners in a continental distributed hydrological modeling system , 2004 .

[25]  S. Barnes,et al.  Mesoscale objective map analysis using weighted time-series observations , 1973 .

[26]  W. Cotton,et al.  A large-eddy simulation study of cumulus clouds over land and sensitivity to soil moisture , 2001 .

[27]  S. Sorooshian,et al.  Evaluation of PERSIANN system satellite-based estimates of tropical rainfall , 2000 .