Academic Biography
I am a PhD researcher at the University of Oxford working on machine learning and explainable AI for large-sample hydrology, with a focus on improving the prediction and physical understanding of hydrological extremes, such as floods. My research combines time-series modelling, extreme value theory, and interpretable machine learning to study flood generation mechanisms across spatial and temporal scales. I am interested in how data-driven models can move beyond prediction to reveal physical insight, helping uncover the multi-scale processes and temporal dependencies that drive extreme flow behaviour. I collaborate with UKCEH and the Hydro-Jules team in the UK, to investigate how climate variability shapes global flow regimes, and I contribute LSTM-based flood analyses to national model intercomparison projects. My work sits at the intersection of hydrology, hydro-meteorology, and AI, with the goal of building large-sample models that are both accurate and scientifically meaningful. I bring this research perspective together with a foundation in Engineering and experience spanning the UK water industry and water quality research, allowing me to connect advanced computational methods with real-world environmental systems and decision-making.