Human Mobility

Human mobility research aims to understand how people move through space and time, focusing on patterns, predictions, and the implications for urban planning, public health, and transportation. Current research heavily utilizes machine learning, particularly transformer-based models and large language models (LLMs), to analyze trajectory data, generate synthetic mobility data, and predict future movements, often incorporating contextual information like socio-demographics and events. These advancements offer improved accuracy and interpretability in mobility modeling, enabling more effective resource allocation, infrastructure development, and public health interventions. Furthermore, research is actively addressing biases in existing datasets and developing privacy-preserving methods for data analysis and synthesis.