Title :
Spatial characterization of remotely sensed soil moisture data using self organizing feature maps
Author :
Kothari, Ravi ; Islam, Shafiqul
Author_Institution :
Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA
fDate :
3/1/1999 12:00:00 AM
Abstract :
Compact characterization of soil moisture at a given scale using self-organizing feature maps is presented. The authors find that as few as 49 neurons capture the spatial structure of remotely sensed soil moisture images from the southern Great Plains. Average latent heat flux computed from the original image of 21204 pixels and from 49 neurons are comparable
Keywords :
geophysical signal processing; geophysics computing; hydrological techniques; hydrology; moisture measurement; remote sensing; self-organising feature maps; soil; Great Plains; USA; United States; data compression; hydrology; image processing; measurement technique; neural net; neural network; remote sensing; self organizing feature map; soil moisture; spatial characterization; spatial structure; Distributed computing; Geoscience; Land surface; Large-scale systems; Neurons; Pixel; Remote sensing; Self organizing feature maps; Soil moisture; Spatial resolution;
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
