ABSTRACT
The Sentinel-1 and Sentinel-2 images should be downloaded and ready to use. This chapter proceeds to the creation of a dataset that can be used to train the model and also to evaluates its performance in terms of root mean squared error. The Sentinel-1 image has 16 bits signed encoding and the Sentinel-2 images have 16 bits unsigned encoding, i.e. integer numbers. Radar is an active sensor, meaning that it emits a radio wave “illuminating” the target and the echo is received and recorded. Synthetic Aperture Radar (SAR) is a kind of radar that generates images using the motion of the sensor to simulate a larger antenna, enabling a higher-resolution image. The first step to prepare the SAR images is the calibration. The calibration ensures that the intensity value actually represents the sigma zero value of the reflectivity, i.e., the radar cross section normalized to area.
