# Transportation Scenario Planning with Graph Neural Networks

arXiv: https://arxiv.org/abs/2110.13202 · HTML: https://mlsanity.com/paper/2110.13202/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 10 of 10)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Learning Geo-Contextual Embeddings for Commuting Flow Prediction](https://mlsanity.com/paper/2005.01690/) (2020)
- [Reimagining City Configuration: Automated Urban Planning via Adversarial Learning](https://mlsanity.com/paper/2008.09912/) (2020)
- [A Machine Learning Approach to Modeling Human Migration](https://mlsanity.com/paper/1711.05462/) (2017)
- [Shadow Accrual Maps: Efficient Accumulation of City-Scale Shadows Over Time](https://mlsanity.com/paper/1907.04435/) (2019)

## Abstract (arXiv)

Providing efficient human mobility services and infrastructure is one of the major concerns of most mid-sized to large cities around the world. A proper understanding of the dynamics of commuting flows is, therefore, a requisite to better plan urban areas. In this context, an important task is to study hypothetical scenarios in which possible future changes are evaluated. For instance, how the increase in residential units or transportation modes in a neighborhood will change the commuting flows to or from that region? In this paper, we propose to leverage GMEL, a recently introduced graph neural network model, to evaluate changes in commuting flows taking into account different land use and infrastructure scenarios. We validate the usefulness of our methodology through real-world case studies set in two large cities in Brazil.