Quantum Annealer for Network Flow Minimization in InSAR Images

Abstract

Quantum Machine Learning is a young field of resarch, and it promises to provide the computational advantage over a conventional method for a family of problems in a practical domain. For practical problems in Earth observation (EO), the deluge of remotely-sensed images counting hundreds of Terabytes per day needs to be converted into meaningful information, largely impacting the socio-economic-environmental triangle. The particularity of EO images as “instrument” measurements extends the challenge of information extraction beyond the spatial information, as EO sensors gather physical parameters of a scene. Hence, our objectives are to enlarge the current methodologies and achievements made in emergent Quantum Machine Learning using a D-Wave quantum annealer as well as a gate-based quantum computer. As an exploratory work, we present the result obtained from the practical optimization problem in EO when appying a D-Wave quantum annealer.