Extended Abstract (2.8M)3.7
Disaggregation of microwave remote sensing data for estimating near-surface soil moisture using a Neural Network
William L. Crosson, National Space Science and Technology Center, Huntsville, AL; and C. A. Laymon, M. P. Schamschula, and A. Steward
Estimation of soil moisture using microwave remote sensors holds great promise for many applications, including numerical weather prediction and agriculture. However, a scale disparity exists between the resolutions of future satellite-borne microwave remote sensing data (30-60 km) and the much finer scales at which soil moisture estimates are desired. Hydrology models may be useful for bridging this gap, as the factors controlling soil moisture variability (precipitation, soil and vegetation properties, topography) are known with reasonable accuracy at fine spatial scales and are used in models to estimate the spatial distribution of soil moisture at the desired spatial scale. Therefore, it is important to explore ways to disaggregate low-resolution passive microwave remote sensing data to the higher resolution of a hydrologic model.
A Neural Network-based disaggregation model, called DisaggNet, has been developed to address the feasibility of disaggregating low-resolution microwave remote sensing data to estimate soil moisture and to estimate associated errors as a function of the data resolution. DisaggNet was tested using microwave brightness temperature (TB) data from the Electronically Steered Thinned Array Radiometer (ESTAR), an aircraft-based instrument operating a 1.4 GHz that was flown on a near-daily basis over the experimental domain of the Southern Great Plains 1997 Hydrology Experiment. The method has been tested by first degrading the resolution of the ESTAR TB data from the original 800 m to lower resolutions by simple arithmetic averaging. DisaggNet combines the degraded TB data with higher-resolution precipitation, soil, vegetation, and topographic properties to estimate the spatial distribution of soil moisture at 800 m resolution. Through separate training procedures, the DisaggNet has been trained to estimate either ESTAR- or model-derived near-surface soil moisture. Performance of DisaggNet was evaluated by comparing these estimates with soil moisture estimates derived from the hydrology model or from the full-resolution ESTAR TB data. Testing was performed at five degraded resolutions (1.6, 3.2, 6.4, 12.8, 25.6 km) under a variety of soil moisture conditions. Experiments have provided insight into the contributions of various input data to the performance and design of the neural network.
Supplementary URL: http://www.caos.aamu.edu/HSCaRS/LinDANet/
Session 3, remote sensing of hydrologic processes
Thursday, 17 January 2002, 8:30 AM-2:15 PM
Previous paper Next paper