Artificial Intelligence, Smart Topological Data Analysis and Chaos in Business Continuity Management: The Case of COVID-19 in Birmingham Airport

The latest state-of-the-art empirical methods from chaos theory have incorporated smart topological data analysis (STDA) combining chaos theory methods, topological machine learning, adaptive artificial intelligence systems, topological data analysis and fractal analysis methods for attractor reconstruction and the topological study of the dynamics, with impact on risk science and complexity research. In the current work, we apply a topological adaptive AI system to the study of Birmingham airport’s air traffic dynamics, and employ topological data analysis, chaos theory methods and multifractal analysis to research the resulting dynamics. Our results show the presence of a form of stochastic chaos with a low-dimensional attractor associated with a long wave dynamics in the pre-COVID-19 period, which continues in the COVID-19 crisis and subsequent recovering around a rising trend, with the topological AI system able to adapt to the COVID-19 crisis and predict with high performance the dynamics during this period. Multifractal analysis methods, applied to the adaptive topological AI system’s residuals, show that the dynamical noise affecting the chaotic attractor is multifractal, with a multifractal phase transition occurring during the COVID-19 recovery period. Implications of the methods and results for business continuity management are drawn.