Abstract
Modeling human activity dynamics is important for many application domains. However, there are problems inherent in modeling population information, since the number of people inside a given area can change dynamically over time. Here, a cyberGIS-enabled spatiotemporal population model is developed by combining Twitter data with urban infrastructure registry data to estimate human activity dynamics. This model is an object-class oriented space–time composite model, in which real-world phenomena are modeled as spatiotemporal objects, and people can move from one object to another over time. In this research, all spatiotemporal objects are aggregated into 14 spatiotemporal object classes, and all objects in a given space at different times can be projected down to a spatial plane to generate a common spatiotemporal map. A temporal weight matrix is derived from Twitter activity curves for each spatiotemporal object class and represents population dynamics for each object class at different hours of a day. Finally, model performance is evaluated by using a comparison to registered census data. This spatiotemporal human activity dynamics model was developed in a cyberGIS computing environment, which enables computational and data intensive problem solving. The results of this research can be used to support spatial decision-making in various application areas such as disaster management where population dynamics plays an important role.
Original language | English (US) |
---|---|
Article number | 7 |
Journal | Computational Urban Science |
Volume | 1 |
Issue number | 1 |
DOIs | |
State | Published - Dec 2021 |
Externally published | Yes |
All Science Journal Classification (ASJC) codes
- Urban Studies
- Artificial Intelligence
- Computer Science Applications
- Environmental Science (miscellaneous)
Keywords
- Object-oriented space–time composite model
- Social media data mining
- Spatiotemporal data modeling
- Urban infrastructure data