Anthony Miller

Biography

My research focuses on the analysis, prediction, and long-term behaviour of nonlinear dynamical systems through the combination of mathematical modelling, time-series analysis, and machine learning. Many nonlinear systems encountered in science and engineering exhibit complex behaviour that cannot be solved analytically, requiring a combination of numerical simulation, statistical analysis, and data-driven approaches to understand and predict their evolution. A particular area of interest is the forecasting of chaotic and weakly predictable systems using artificial intelligence and machine learning techniques. My work explores how dynamical information extracted from nonlinear systems can be combined with modern learning algorithms to improve prediction accuracy and extend forecasting horizons. This includes the development of techniques based on the Kuramoto Order Parameter (KOP) to identify weakly synchronised trajectories that provide informative training data for machine learning models. More broadly, I am interested in nonlinear dynamics, chaos, time-series forecasting, synchronisation phenomena, and the integration of physics-informed and data-driven methods for analysing complex systems. My research combines numerical methods, nonlinear time-series analysis, machine learning, and artificial intelligence to develop robust approaches for understanding and predicting the behaviour of complex dynamical systems. I am an Associate Member of the Institute of Mathematics and its applications (AMIMA), and a member of the London Mathematical Society (LMS).

Qualifications

• BSc (Hons) Mathematics University of Manchester (1996)

• MSc Theoretical Physics by Research University of Warwick (2000)

Thesis