I am a University Academic Fellow (UAF) in the School of Geography at the University of Leeds. My research areas are agent-based modelling, decision making in complex systems, AI and multi-agent systems, urban analytics and housing markets. I obtained PhD in Economics from Iowa State University under supervisor Prof. Leigh Tesfatsion in 2014. I worked as a researcher at the James Hutton Institute in Aberdeen, Scotland between 2014 and 2019. I joined the University of Leeds as a UAF of Urban Analytics in 2019. I am originally from Shanghai, China.
My main research areas are agent-based modelling, urban analytics and complex decision making enabled by AI. I am interested in the bottom-up transition of complex urban systems under major socio-economic and environmental shocks, such as climate change and the fourth industrial revolution. I want to understand how cities as self-organised complex systems respond to external shocks and evolve under a constantly changing environment. In the past, I have looked at various aspects of urban systems, including the housing market, the labour market, transport and energy system. I am also interested in decision making in complex systems. For example, I have studied the decision to become a vegetarian/vegan under social influence. I have also looked at global food trade in a complex trade network and the resulting food and nutrition security. Recently, I am interested in applying AI algorithms especially reinforcement learning in multi-agent systems, including applications of AI in urban adaptation to climate change, housing market dynamics and criminal behaviour in an urban system.
Ge, J., & Polhill, G. (2016). Exploring the Combined Impact of Factors Influencing Commuting Patterns and CO2 Emission in Aberdeen Using an Agent-Based Model. Journal of Artificial Societies and Social Simulation, 19(3). http://jasss.soc.surrey.ac.uk/19/3/11.html
We develop an agent-based transport model using a realistic GIS-enabled road network and the car following method. The model can be used to study the impact of social interventions such as flexi-time and workplace sharing, as well as large infrastructure such as the construction of a bypass or highway. The model is developed in Netlogo version 5 and requires road network data in GIS format to run.
The code shared here accompanies the paper at https://doi.org/10.1371/journal.pone.0208451. It simulates the effects of various economic trade scenarios on the phenomenon of the ‘disappearing middle’ in the Scottish beef and dairy farming industries. The ‘disappearing middle’ is a situation in which there is a simultaneous observed decline in medium-sized enterprises and rise in the number of small and large-scale enterprises.
The integrated and spatially-explicit ABM, called DIReC (Demography, Industry and Residential Choice), has been developed for Aberdeen City and the surrounding Aberdeenshire (Ge, Polhill, Craig, & Liu, 2018). The model includes demographic (individual and household) models, housing infrastructure and occupancy, neighbourhood quality and evolution, employment and labour market, business relocation, industrial structure, income distribution and macroeconomic indicators. DIReC includes a detailed spatial housing model, basing preference models on house attributes and multi-dimensional neighbourhood qualities (education, crime, employment etc.).
The dynamic ABM simulates the interactions between individuals, households, the labour market, businesses and services, neighbourhoods and economic structures. It is empirically grounded using multiple data sources, such as income and gender-age distribution across industries, neighbourhood attributes, business locations, and housing transactions. It has been used to study the impact of economic shocks and structural changes, such as the crash of oil price in 2014 (the Aberdeen economy heavily relies on the gas and oil sector) and the city’s transition from resource-based to a green economy (Ge, Polhill, Craig, & Liu, 2018).
The purpose of the model is to study the impact of global food trade on food and nutrition security in countries around the world. It will incorporate three main aspects of trade between countries, including a country’s wealth, geographic location, and its trade relationships with other countries (past and ongoing), and can be used to study food and nutrition security across countries in various scenarios, such as climate change, sustainable intensification, waste reduction and dietary change.
The purpose of this model is to introduce a new individual decision-making method, BNE, into the ABM of pedestrian evacuation to properly simulate individual behaviours and movements. The model was built to balance between fast evacuation and high comfortability, which is a general conflict in the domain of pedestrian research. The interactions of pedestrians with their neighbours as well as surroundings was also considered in order to simulate a more realistic pedestrian evacuation. This model ultimately aims to explore the influences of BNE on pedestrian flows from various perspectives, especially pedestrian comfort and exit time in an emergency evacuation with different parameter configurations.
Three behavioural models were evaluated: Shortest Route (SR), Random Follow (RF) and BNE. The behavioural models were used to generate four moving patterns (i.e. model configurations): SR, RF, BNE mixed with SR, and BNE mixed with RF.
Using data from the British Social Attitude Survey, we develop an agent-based model to study the effect of social influence on the spread of meat-eating behaviour in the British population.