Exploring SAR interferometry (InSAR) for surface monitoring
Exploring SAR interferometry (InSAR) for surface monitoring
Requirements
- M.Sc. in Machine Learning, Data Science, Computer Science, Mathematics, Telecommunications, or similar
- Knowledge of Python
- Software development skills
- Basic concepts of signals processing
- Basic concepts of data science, concerning data analysis, processing and machine learning
Description
Natural disasters are extreme and sudden events caused by environmental factors that injure people and damage property. As research foundation, we are interested in studying tools and applications for fast respond in case of natural disasters. After a disaster, for example, is extremely important rapidly address the rescue to the more damaged areas. As LINKS Foundation we are working on different technologies, among which the satellite images coming from the Copernicus project. We are extending our studies on Sentinel-1 which is not cloud dependant, has a very short revisit times and includes SAR instrument. The Interferometric SAR (InSAR) exploits the phase difference between two complex radar SAR observations of the same area, taken from slightly different sensor positions, and extracts distance information about the Earth’s terrain. The aim of the thesis is to retrieve, analyze Sentinel-1 data, and develop a pipeline for computing the interferometry and persistent scatterer interferometry in order to extract multiple timeseries that represent the displacement of the ground surface. The thesis includes the following activities: (i) Data identification and acquisition (ii) state of the art analysis (iii) data analysis and preprocessing (iv) inSAR computation (v) PSI computation (vi) design a machine learning model to detect the critical areas in a pilot case.