Urbanite

A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics

Dataflow-based framework for Human-AI alignment in urban visual analytics

IEEE VIS 2025

Analyzing flood simulations with Urbanite — Analyzing flood simulations: provenance and data inspection, simulation nodes documented with dataflow- and node-level explanations, and results shown with UTK nodes.

Urbanite is a framework for human-AI collaboration in urban visual analytics that leverages a dataflow-based model allowing users to specify intent at multiple scopes, enabling interactive alignment across specification, process, and evaluation stages. The framework incorporates features for explainability, multi-resolution task definition across dataflows, nodes, and parameters, and supporting interaction provenance based on findings from a survey identifying existing challenges.

Publications

Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics

Gustavo Moreira, Leonardo Ferreira, Carolina Veiga, Maryam Hosseini, Fabio Miranda

IEEE Transactions on Visualization and Computer Graphics (IEEE VIS 2025), 2026

Paper arXiv Code

Team

Gustavo MoreiraUniversity of Illinois Chicago
Leonardo FerreiraUniversity of Illinois Chicago
Maryam HosseiniUniversity of California, Berkeley
Carolina VeigaUniversity of Illinois Urbana-Champaign
Fabio MirandaUniversity of Illinois Chicago

How to cite

BibTeX

@article{moreira2026urbanite,
  title = {Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics},
  volume = {32},
  doi = {10.1109/tvcg.2025.3634644},
  number = {1},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Moreira, Gustavo and Ferreira, Leonardo and Veiga, Carolina and Hosseini, Maryam and Miranda, Fabio},
  year = {2026},
  month = jan,
  pages = {1065--1075},
  eprint = {2508.07390},
  archiveprefix = {arXiv}
}