MrDaniel Feghali

Daniel Feghali is a PhD researcher at Imperial College London working across quantum computing, machine learning, and industrial process optimisation. His research focuses on developing and evaluating quantum and quantum-inspired methods for optimisation and machine learning, with an emphasis on identifying where these approaches can offer meaningful advantages over established classical methods.

A major strand of his work focuses on quantum annealing and QUBO formulations for combinatorial optimisation problems, including feature selection and process optimisation. Alongside this, he develops and evaluates a range of quantum machine learning algorithms, including quantum kernel methods, variational quantum models, and quantum recurrent architectures for time-series forecasting. His work also investigates tensor-network methods for sequential modelling as a quantum-inspired alternative to conventional recurrent architectures.

These methods are primarily applied to semiconductor wastewater treatment, where complex and highly dynamic treatment processes present challenging prediction and optimisation problems. Daniel investigates how quantum, hybrid quantum-classical, and classical approaches can be used to improve process modelling and optimisation, while rigorously benchmarking their performance under realistic industrial conditions.

Before beginning his PhD, Daniel studied Civil Engineering at Imperial College London, graduating with First Class Honours.