Academic Interests

Intersection of machine learning and complex urban and spatial systems

• • Planetary urban modeling: Modeling different urban phenomena at the scale of planet using open source geo-data streams

  • Data driven urban computing for fast and scalable modeling of urban flows (e.g. flood, wind, heat, etc.)

  • City as text: Data driven hierarchical representation of urban stocks (e.g. floor plans, buildings, parcels, neighborhoods, etc.)

  • Health and place (e.g. urban characteristics and urban air pollution)

  • Urban economy and real estate dynamics

  • Transportation networks dynamics

  • Multidimensional geo-visualizations and spatial search

Data driven modeling across disciplines

• • Structural design and optimization

  • Dynamical networks and systemic risk

  • Financial time series forecasting 

  • Manufacturing and supply chain systems

  • Atmospheric science

Machine learning and deep learning literacy for non-computer scientists

• • Teachings and codes

Other computational and modeling concepts (Mainly from 2006-2010)

• • Agent based modeling

  • System dynamics

  • Optimization methods

  • Multi criteria decision-making