Hybrid Quantum-Classical Processing Workflows in Modular Supercomputing Architectures for Data-Intensive Earth Observation Applications
Quantum Computing Category: Quantum Machine Learning
Scientific Domain: Earth Observation / Remote Sensing
This project explores hybrid quantum-classical processing workflows for large-scale Earth-observation applications within a modular supercomputing environment. Its work combines HPC resources with quantum annealing for machine-learning tasks and investigates how different processing stages can be assigned to the most suitable computing technology. Among the resulting methods is quantum-annealing support-vector regression for estimating biophysical variables from remote-sensing data, illustrating how quantum algorithms can be embedded into broader data-intensive scientific workflows.
Publication:
Pasetto, E., Delilbasic, A., Cavallaro, G., Willsch, M., Melgani, F., Riedel, M., Michielsen, K. Quantum Support Vector Regression for Biophysical Variable Estimation in Remote Sensing. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 2022, pp. 4903-4906. https://doi.org/10.1109/IGARSS46834.2022.9883963