Deep learning methodologies for change detection in SAR image time series

• Grant number: 24/20120-5
• Support Opportunities: Scholarships in Brazil - Doctorate (Direct)
• Start date: March 01, 2025
• End date: August 31, 2028
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Aluísio de Souza Pinheiro
• Grantee: Lucas Perondi Kist
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 23/02538-0 - Time series, wavelets, high dimensional data and applications, AP.TEM

Abstract

There is a growing need for procedures and algorithms to help environmental remote sensing on the challenging tasks which arise every day. This project explores the employment and development of novel methodologies based on statistical deep learning. The aim is to detect changes in Earth`s surface using time series of remote sensing images. The rigorous adaptation of deep learning methodologies will provide the data analyst with powerful tools for processing the aforementioned time series, and generating spatial-temporal change maps. (AU)