We aspire to develop Complex Network, Data Mining and Machine Learning algorithms to discover unknown and actionable patterns and insights hidden deep inside the city and urbanization. By developing computational methods for processing and analyzing large scale urban data, we aim to understanding complex urban behavior and to inform the design of efficient urban systems. These studies are interdisciplinary with physics and information science.
City Simulation and Optimization
We are dedicated to using data science and artificial intelligence to solving global urbanization problems. Based on the existing limited urban data, we aim to building large-scale city simulator with the key technologies of AI-enabled data generation and high performance simulation engine. Based on the simulation, we develop reinforcement learning based intelligent solutions for a broad coverages of urban optimization for transportation system, environment control, energy scheduling, and urban emergency management (public health, atmospheric pollution, etc.).
We conduct empirical studies of governance polices, user behaviors, and their interactions within the cities via mixed methods of qualitative and quantitative, using large-scale observational urban studies as well as smaller-scale studies of users via survey, interview, and field experiment. These studies help government and stakeholders decide how to plan, finance and manage urban areas. These studies are interdisciplinary with management science (urban planning, public management, and economics) with information science (electronic information and computer science).