A Grid-Based Framework for E-Scooter Demand Representation and Temporal Input Design for Deep Learning: Evidence from Austin, Texas

2026-03-13

AI Summary

This study addresses the limitations of heuristic time input designs in shared e-scooter demand forecasting, which often lack systematic validation and hinder model performance. The authors construct a gridded spatiotemporal dataset by converting trip records into hourly origin–destination demand images. They propose a statistical approach for time input selection, integrating Pearson correlation analysis with error evaluation, and introduce a global activity mask to emphasize historically active regions. Using a UNet-based image-to-image prediction framework, their model achieves a 37% reduction in mean squared error for one-hour-ahead forecasting and a 35% reduction for 24-hour-ahead predictions compared to baselines using adjacent hours or fixed periodic inputs, significantly improving the capture of short-term persistence and daily/weekly cyclical patterns.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Time-Series/Data Streams
• Intelligent Robots: State Estimation

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Despite progress in deep learning for shared micromobility demand prediction, the systematic design and statistical validation of temporal input structures remain underexplored. Temporal features are often selected heuristically, even though historical demand strongly affects model performance and generalizability. This paper introduces a reproducible data-processing pipeline and a statistically grounded method for designing temporal input structures for image-to-image demand prediction. Using large-scale e-scooter data from Austin, Texas, we build a grid-based spatiotemporal dataset by converting trip records into hourly pickup and dropoff demand images. The pipeline includes trip filtering, mapping Census Tracts to spatial locations, grid construction, demand aggregation, and creation of a global activity mask that limits evaluation to historically active areas. This representation supports consistent spatial learning while preserving demand patterns. We then introduce a combined correlation- and error-based procedure to identify informative historical inputs. Optimal temporal depth is selected through an ablation study using a baseline UNET model with paired non-parametric tests and Holm correction. The resulting temporal structures capture short-term persistence as well as daily and weekly cycles. Compared with adjacent-hour and fixed-period baselines, the proposed design reduces mean squared error by up to 37 percent for next-hour prediction and 35 percent for next-24-hour prediction. These results highlight the value of principled dataset construction and statistically validated temporal input design for spatiotemporal micromobility demand prediction.

Problem

• e-scooter demand prediction
• temporal input design
• spatiotemporal modeling
• deep learning
• shared micromobility

Innovation

• grid-based representation
• temporal input design
• spatiotemporal demand prediction
• statistical validation
• e-scooter mobility