Speakers
Description
Reliable isotope identification is essential in radiation monitoring and nuclear engineering, especially when measurements are affected by attenuation, noise, and low resolution detectors. This project explores a quantum machine learning approach for classifying isotopes using attenuated radiation data acquired with a custom built Geiger based detection system. We implement a variational quantum classifier (VQC) in Qiskit, employing angle and amplitude encoding strategies to map spectral features into quantum states. Training and evaluation are performed using both simulated and real hardware through IBM Quantum Experience, and compared against standard classical models. This work aims to assess the feasibility and potential advantages of quantum enhanced classification in realistic radiological scenarios, providing a hybrid framework that bridges quantum computation and nuclear instrumentation.