Quantum-enhanced satellite image classification

2026-02-20

AI Summary

This work addresses the challenge of insufficient accuracy in multi-class satellite image classification for high-stakes remote sensing applications by proposing a hybrid quantum-classical approach. The method leverages many-body spin Hamiltonians to generate quantum features on an IBM quantum processor, which are then fused with a ResNet50 transfer learning model. To the best of our knowledge, this is the first demonstration of reproducible quantum-enhanced performance on a real-world satellite imagery task, overcoming recent limitations of near-term quantum devices in practical machine learning. Experimental results show that the proposed approach improves classification accuracy from the ResNet50 baseline of 83% to 87%, achieving an absolute gain of 2–3 percentage points.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Multi-modal Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

We demonstrate the application of a quantum feature extraction method to enhance multi-class image classification for space applications. By harnessing the dynamics of many-body spin Hamiltonians, the method generates expressive quantum features that, when combined with classical processing, lead to quantum-enhanced classification accuracy. Using a strong and well-established ResNet50 baseline, we achieved a maximum classical accuracy of 83%, which can be improved to 84% with a transfer learning approach. In contrast, applying our quantum-classical method the performance is increased to 87% accuracy, demonstrating a clear and reproducible improvement over robust classical approaches. Implemented on several of IBM's quantum processors, our hybrid quantum-classical approach delivers consistent gains of 2-3% in absolute accuracy. These results highlight the practical potential of current and near-term quantum processors in high-stakes, data-driven domains such as satellite imaging and remote sensing, while suggesting broader applicability in real-world machine learning tasks.

Problem

• satellite image classification
• quantum-enhanced
• multi-class classification
• remote sensing
• accuracy improvement

Innovation

• quantum feature extraction
• many-body spin Hamiltonians
• quantum-classical hybrid
• satellite image classification
• near-term quantum processors