Leveraging a Hybrid Quantum-Classical Framework for Subsurface Target Detection in Radar Sounding System: Challenges and Opportunities

In this article, we explore the potential of quantum machine learning (QML) for subsurface feature extractions from radar sounder (RS) signals. We propose a hybrid quantum-classical (HQC) learning paradigm that leverages parameterized quantum circuits (PQCs) to generate probability amplitudes based on quantum properties such as superposition and entanglement. These amplitudes are synergistically integrated with the classical deep neural networks that are efficient in learning high-dimensional contextual features for downstream prediction tasks. The present research work is structured around two objectives. First, we investigate the role of quantum circuits in the latent space for transferring back-and-forth rich discriminative spatial context from the encoder to the decoder for segmentation. Second, we investigate how the probabilistic amplitudes derived from quantum circuits are significant in integrating into the classical models to provide new insights for RS signals segmentation. The performance of the hybrid architectures has been studied in small-scale settings by simulating the expected behavior of the quantum circuits on a classical machine. The experimental results have demonstrated the viability of QML frameworks on MCoRDS-1 and MCoRDS-3 datasets for RS signal segmentation. Qualitatively, they are capable of delineating the spatial extent of the bedrock from noise. Additionally, we conduct a comparative analysis between the Qiskit Aer Simulator and the IBM FakeBackend Simulator to highlight the computational trade-offs and validate fidelity of two simulators for scalable experimentation. Therefore, our work opens up new avenues of research for future RS data analysis leading to more precise and efficient subsurface target segmentation.