Day 4

Detailed paper information

Back to list

Paper title Advancing of Earth Observation Methodologies by using a Quantum Computer
  1. Soronzonbold Otgonbaatar German Aerospace Center (DLR), Remote Sensing Technology Institute Speaker
  2. Mihai Datcu DLR - German Aerospace Center
Form of presentation Poster
  • C2. Digital Twins
    • C2.01 Towards a Digital Twin of the Earth - advances and challenges ahead
Abstract text Recent breakthroughs in building a quantum computer with very few quantum bits (qubits) and in applying Machine Learning (ML) techniques to any annotated datasets, led to quantum Machine Learning (qML) and practical Quantum Algorithms (QA) being considered as a promising disruptive technique for a particular class of supervised learning methods and optimization problems. There is growing interest to apply a qML network and QAs to classical data/problems. However, the QML network and QAs are posing several new challenges, for instance, how to map classical data to qubits (quantum data) due to the limited number of qubits of quantum computers, or how to use the specificity of the “qubits” to obtain advantages over non-quantum computing techniques, while ubiquitous data/problems in practical domains has a classical nature.

Furthermore, quantum computers emerge as a paradigm shift to tackle practical (intractable) Earth observation problems from a new viewpoint with the promise to speed up a number of algorithms for some practical problems. In recent years, there is growing interest to employ quantum computers for assisting machine learning (ML) techniques as well as a conventional computer for supporting quantum computers. Moreover, researchers both in academy and industry are still investigating QML approaches and QAs for discovering patterns or speeding up some ML techniques for finding highly-informative patterns in big data.

Remotely-sensed images are used for Earth observation both from aircraft or satellite platforms. The images acquired by satellites are available in digital format and contain information on the number of spectral bands, radiometric resolution, spatial resolution, etc. We performed the first exploratory studies for applying QML and QAs to remotely-sensed images and problems by using a D-Wave quantum annealer and a gate-based quantum computer (an IBM and Google quantum computer). Such quantum computers solve optimization problems and run ML methods by exploiting different mechanisms and techniques of quantum physics. Therefore, we present the differences for solving problems on a D-Wave quantum annealer and a gate-based quantum computer, and how to program these two quantum computers to advance Earth observation methodologies according to our gained experiences, as well as the challenges being encountered.


[1] S. Otgonbaatar and M. Datcu, "Classification of Remote Sensing Images With Parameterized Quantum Gates," in IEEE Geoscience and Remote Sensing Letters, doi: 10.1109/LGRS.2021.3108014.
[2] S. Otgonbaatar and M. Datcu, "Natural Embedding of the Stokes Parameters of Polarimetric Synthetic Aperture Radar Images in a Gate-Based Quantum Computer," in IEEE Transactions on Geoscience and Remote Sensing, doi: 10.1109/TGRS.2021.3110056.
[3] S. Otgonbaatar and M. Datcu, "Quantum annealer for network flow minimization in InSAR images," EUSAR 2021; 13th European Conference on Synthetic Aperture Radar, 2021, pp. 1-4.
[4] S. Otgonbaatar and M. Datcu, "A Quantum Annealer for Subset Feature Selection and the Classification of Hyperspectral Images," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 7057-7065, 2021, doi: 10.1109/JSTARS.2021.3095377.