# Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics

arXiv: https://arxiv.org/abs/2007.15486 · HTML: https://mlsanity.com/paper/2007.15486/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 6 of 6)

- [Spatiotemporal Data Mining: A Survey on Challenges and Open Problems](https://mlsanity.com/paper/2103.17128/) (2021)
- [A Visual Analytics System for Improving Attention-based Traffic Forecasting Models](https://mlsanity.com/paper/2208.04350/) (2022)
- [Modeling Spatial Nonstationarity via Deformable Convolutions for Deep Traffic Flow Prediction](https://mlsanity.com/paper/2101.12010/) (2021)
- [TimeTuner: Diagnosing Time Representations for Time-Series Forecasting with Counterfactual Explanations](https://mlsanity.com/paper/2307.09916/) (2023)
- [TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic](https://mlsanity.com/paper/2403.04812/) (2024)
- [TrafPS: A Visual Analysis System Interpreting Traffic Prediction in Shapley](https://mlsanity.com/paper/2203.06213/) (2022)

## Abstract (arXiv)

Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks. However, the widely known modifiable areal unit problem within such aggregation processes can lead to perturbations in the network inputs. This issue can significantly destabilize the feature embeddings and the predictions, rendering deep networks much less useful for the experts. This paper approaches this challenge by leveraging unit visualization techniques that enable the investigation of many-to-many relationships between dynamically varied multi-scalar aggregations of urban traffic data and neural network predictions. Through regular exchanges with a domain expert, we design and develop a visual analytics solution that integrates 1) a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, 2) a Morans I Scatterplot that provides local indicators of spatial association analysis, and 3) a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales. We evaluate our approach through a series of case studies involving a real-world dataset of Shenzhen taxi trips, and through interviews with domain experts. We observe that geographical scale variations have important impact on prediction performances, and interactive visual exploration of dynamically varying inputs and outputs benefit experts in the development of deep traffic prediction models.