QUANTUM MACHINE LEARNING FOR REMOTE SENSING - EXPLORING POTENTIAL AND CHALLENGES

Aug 4, 2026

Quantum technologies are expanding rapidly, creating new opportunities in scientific domains, with Quantum Machine Learning (QML) standing out for its promise to transform data processing and analysis. This work examines how QML can support remote sensing by enabling analysis of space-based data. The paper reviews common claims about quantum advantage in remote sensing and identifies open challenges. A focused study addresses kernel value concentration, which affects quantum runtime; results show it reduces performance but does not eliminate the possibility of quantum advantage.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages4

Reading Time10 min

AccessFree to download

Introduction

Quantum Machine Learning

Potential advantages of QML

Challenges for Quantum Advantage

Kernel value concentration study

Conclusion

arXiv :2311 .07626v1 [ quant-ph] 13 Nov 2023 QUANTUM MACHINE LEARNING FOR REMOTE SENSING: EXPLORING POTENTIAL AND CHALLENGES Artur Miroszewski 1, Jakub Nalepa2 ,3, Bertrand Le Saux4, Jakub Mielczarek 1 1Institute of Theoretical Physics, Jagiellonian University, Łojasiewicza 11, 30-348 Cracow, Poland 2 KP Labs, Bojkowska 37J, 44-100 Gliwice, Poland 3 Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland 4European Space Agency Φ-lab, Largo Galileo Galilei 1, 00044 Frascati, Italy ABSTRACT The industry of quantum technologies is rapidly expanding, offering promising opportunities for various scientific domains. Among these emerging technologies, Quantum Machine Learning (QML) has attracted considerable attention due to its potential to revolutionize data processing and analysis. In this paper, we investigate the application of QML in the field of remote sensing. It is believed that QML can provide valuable insights for analysis of data from space. We delve into the common beliefs surrounding the quantum advantage in QML for remote sensing and highlight the open challenges that need to be addressed. To shed light on the challenges, we conduct a study focused on the problem of kernel value concentration, a phenomenon that adversely affects the runtime of quantum computers. Our findings indicate that while this issue negatively impacts quantum computer performance, it does not entirely negate the potential quantum advantage in QML for remote sensing. Index Terms— Quantum Machine Learning, Remote Sensing, Quantum Computation 1. INTRODUCTION Quantum computing technologies attract attention from academia, business entities and general public. With the constant development of both technology and theory behind quantum computation, the claims for its potential use grow significantly. At the same time, as those claims get validated, we are becoming more and more aware of the limitations of quantum computing. We review recent developments in the theory of Quantum Machine Learning (QML) and refer them to the subject of remote sensing. We propose the following This work was funded by the European Space Agency, and supported by the ESA Φ-lab ([https://philab.esa.int/](https://philab.esa.int/)) AI-enhanced Quantum Computing for Earth Observation (QC4EO) initiative, under ESA contract No. 4000137725/22/NL/GLC/my. AM and JM were supported by the Priority Research Areas Anthropocene and Digiworld under the program Excellence Initiative – Research University at the Jagiellonian University in Krakw. JN was supported by the Silesian University of Technology grant for maintaining and developing research potential. understanding for quantum advantage in machine learning. We claim quantum advantage if: 1. the algorithm run on physical quantum machine solves the machine learning task obtaining better performance than on a classic machine, 2. the simulation of the quantum algorithm is not efficient (in terms of cost, energy use, runtime, . . . ) on a classic machine. One of the industries that might profit in employing quantum technologies for pattern recognition and data analysis is remote sensing. With the constantly increasing amount of data produced in space and specific requirements for data handling, it is natural to look for new technologies which could excel in those tasks. Indeed, scientists are already exploring this topic from the perspective of Quantum Machine Learning [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] . Therefore, we recognize the need for a high-level review of the topic. In Sec. 2 we introduce the notion of Quantum Machine Learning and discuss potential advantages of exploring this subject. In Sec. 3 we review major challenges for QML to achieve quantum advantage. In Sec. 4 we perform a study on one of those challenges. Sec. 5 concludes the paper. 2. QUANTUM MACHINE LEARNING Quantum machine learning refers to the intersection of quantum computing and machine learning. It encompasses the

FAQs

What is the main focus of the paper on quantum technologies in remote sensing?

The paper investigates how Quantum Machine Learning (QML) can be applied to remote sensing and what it may offer for analyzing space-generated data.

How does the paper define quantum advantage in QML?

Quantum advantage is claimed when a quantum machine run achieves better performance on the learning task than a classic machine, and when simulating the quantum algorithm classically is not efficient in cost, energy, or runtime.

What challenge does the paper study to understand limitations of quantum advantage?

It studies kernel value concentration, a phenomenon that adversely impacts the runtime of quantum computers, evaluating how it affects potential quantum advantage for remote sensing.

Aug 4, 2026

Uploaded by Ava Thompson