On Circuit-Based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification

Abstract

This article aims to investigate how circuit-based hybrid Quantum Convolutional Neural Networks (QCNNs) can be successfully employed as image classifiers in the context of remote sensing. The hybrid QCNNs enrich the classical architecture of CNNs by introducing a quantum layer within a standard neural network. The novel QCNN proposed in this work is applied to the Land Use and Land Cover (LULC) classification, chosen as an Earth Observation (EO) use case, and tested on the EuroSAT dataset used as reference benchmark. The results of the multiclass classification prove the effectiveness of the presented approach, by demonstrating that the QCNN performances are higher than the classical counterparts. Moreover, investigation of various quantum circuits shows that the ones exploiting quantum entanglement achieve the best classification scores. This study underlines the potentialities of applying quantum computing to an EO case study and provides the theoretical and experimental background for futures investigations.

Quantum Computing and Simulations for Energy Applications: Review and Perspective

“…15,302,303 Additionally, quantum machine learning techniques have shown promise for image classification in remote sensing applications. 300,304 Simulating material properties and performance is also crucial for sensor design; for example, complex systems such as MOFs are widely used for the sensitive detection of gases and ions. 305 Thus, the design and optimization of next-generation sensing technologies and materials is an additional area in which quantum computers can significantly benefit the energy sector.…”

“…High-performance sensors are also required throughout the energy sector, for applications such as pipeline integrity, greenhouse gas monitoring, resource discovery, and grid monitoring, among others. ,− One emerging application of quantum computational techniques is the optimization of sensing platforms. , Quantum simulation may also be used to improve the performance of quantum sensing technologies; for example, a quantum simulator has been used to gain new insights into the entanglement between nitrogen vacancy centers in diamond, which is a widely used material for quantum sensing applications. ,, Additionally, quantum machine learning techniques have shown promise for image classification in remote sensing applications. , Simulating material properties and performance is also crucial for sensor design; for example, complex systems such as MOFs are widely used for the sensitive detection of gases and ions . Thus, the design and optimization of next-generation sensing technologies and materials is an additional area in which quantum computers can significantly benefit the energy sector.…”

Hyperparameter optimization of hybrid quantum neural networks for car classification

“…In a VQA, a parametrized quantum circuit (PQC) is optimized by a classical outer loop to solve a specific task like finding the ground state of a given Hamiltonian or classifying data based on given input features. As qubit numbers are expected to stay relatively low within the next years, hybrid alternatives to models realized purely by PQCs have been explored [25][26][27][28][29][30]. In these works, a quantum model is combined with a classical model and optimized end-to-end to solve a specific task.…”

Beyond Ansätze: Learning Quantum Circuits as Unitary Operators

“…Quantum machine learning (QML) continues to be one of the most compelling application areas of quantum computing, particularly in the noisy, intermediate scale quantum (NISQ) era [Preskill, 2018]. The field has already seen a broad range of QML applications investigated, including image classification [Wilson et al, 2018;Adachi and Henderson, 2015], predicting quantum states associated with a one-dimensional symmetryprotected topological phase [Cong et al, 2019], election forecasting [Henderson et al, 2019], financial applications [Alcazar et al, 2019;Kashefi et al, 2020], synthetic weather modeling [Enos et al, 2021] or Earth observation Sebastianelli et al, 2021]. The unique properties of quantum computers powering QML applications are tested against classical algorithms, with the goal of observing higher accuracy, faster training, fewer required training samples, or other beneficial improvements.…”