Regime-adaptive partial differential equations for interpretable multi-ethnic urban modeling
Seyed Navid Mashhadi Moghaddam, Huhua Cao, Tao Jin, Ruibo Han, Diba Rashidi · 2025
Read Regime-adaptive partial differential equations for interpretable multi-ethnic urban modeling by Seyed Navid Mashhadi Moghaddam, Huhua Cao, Tao Jin, Ruibo Han, Diba Rashidi (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12663275.txt.
Description
Seyed Moghaddam, Huhua Cao, Tao Jin, Ruibo Han, and Diba Rashidi build a city model that predicts how ethnic groups spread, without hiding its logic. Machine learning models for social questions often trade clarity for accuracy. Their model blends physics-style equations with a set of expert neural units, each tuned to a phase of settlement such as colonization, rapid jumps, or decline. A router sends each case to the right expert.
Tested on two decades of Toronto census data, the model forecast group patterns five and ten years out and beat seven rival models by a wide margin. It also surfaced cross-group influence and differing settling styles that older methods missed. The paper argues that built-in knowledge can give both accuracy and clarity.
Catalog record
| CREATOR | Seyed Navid Mashhadi Moghaddam, Huhua Cao, Tao Jin, Ruibo Han, Diba Rashidi |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 192 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |