Satellite image classification with neural quantum kernels

TL;DR

This paper introduces a quantum machine learning approach using neural quantum kernels for classifying satellite images, specifically solar panels, demonstrating competitive results and scalability up to 8 qubits.

Contribution

It presents a novel quantum kernel-based classification method for satellite imagery, combining classical pre-processing with quantum neural network-derived kernels.

Findings

Competitive accuracy with classical methods

Robustness of quantum approach demonstrated

Scalability up to 8 qubits achieved

Abstract

Achieving practical applications of quantum machine learning for real-world scenarios remains challenging despite significant theoretical progress. This paper proposes a novel approach for classifying satellite images, a task of particular relevance to the earth observation (EO) industry, using quantum machine learning techniques. Specifically, we focus on classifying images that contain solar panels, addressing a complex real-world classification problem. Our approach begins with classical pre-processing to reduce the dimensionality of the satellite image dataset. We then apply neural quantum kernels (NQKs)-quantum kernels derived from trained quantum neural networks (QNNs)-for classification. We evaluate several strategies within this framework, demonstrating results that are competitive with the best classical methods. Key findings include the robustness of or results and their scalability, with successful performance achieved up to 8 qubits.