Graph convolutional network for modeling corridor-based urban transformation: Revealing spatial coherence in land-use change in Erbil

Mustafa Aziz Amen, Hourakhsh Ahmad Nia, Amen Mustafa Aziz · 2026

Read Graph convolutional network for modeling corridor-based urban transformation: Revealing spatial coherence in land-use change in Erbil by Mustafa Aziz Amen, Hourakhsh Ahmad Nia, Amen Mustafa Aziz (2026) 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/plos-pone-0357090.txt.

Description

Mustafa Aziz Amen, Hourakhsh Ahmad Nia, and Amen Mustafa Aziz asked a forecasting question about Erbil, Iraq. Did the city's street layout in 2004 foretell which homes would become shops over the next twenty years? Their 2026 study rebuilt the old network of 279 intersections. It scored each street segment's importance in several ways. It then raced two prediction models against each other. One was a graph neural network that learns from neighbors.

Both models predicted conversions well. The graph model was slightly more precise. It produced smoother, more continuous commercial corridors. The simpler regression caught a few more true conversions. How straight a street ran proved the strongest single clue. City planners could use such forecasts to prepare corridors for commercial pressure before it arrives piecemeal.

Catalog record

CREATORMustafa Aziz Amen, Hourakhsh Ahmad Nia, Amen Mustafa Aziz
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE55986
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0357090

Browse the full library · About the Tower of Babel