Sensor data simulations using Monte-Carlo and neural network methods
Richard K. Kiang · 2005
Parametric and non-parametric Monte-Carlo methods and a neural network method are used for data simulation. A Landsat-4 Thematic Mapper dataset and its ground truth are utilized for training and testing. The abilities and deficiencies of the three methods are compared. It is shown that the neural network method provides an attractive alternative for data simulation.