Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mohammad Sahnoon Merkebe Getachew Demissie, Roberto Souza

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.

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

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.
Paper Structure (29 sections, 18 equations, 10 figures, 7 tables)

This paper contains 29 sections, 18 equations, 10 figures, 7 tables.

Table of Contents

  1. Related Work
  2. Dataset and Spatiotemporal Processing Pipeline
  3. Raw Dataset and Data Source
  4. Spatiotemporal Processing for Final Dataset Creation
  5. Final Dataset Statistics and Spatiotemporal Demand Patterns
  6. Transformation of Trip Records into Grid-Based Hourly Demand Images
  7. Construction of the Global Binary Activity Mask
  8. Experimental Setup
  9. Prediction Horizons and Experimental Scope
  10. Temporal Dataset Splitting and Leakage Prevention
  11. Input Representation and Spatiotemporal Channel Construction
  12. Deep Learning Model
  13. Loss Function
  14. Evaluation Metrics
  15. Masked error-based metrics
  16. ...and 14 more sections

Figures (10)

  • Figure 1: Trip counts per vehicle type in Austin's raw micromobility dataset (15 million samples).
  • Figure 2: Spatial coverage of the final 2019 e-scooter dataset. The figure displays all 205 unique Census Tracts (in black) that appear as trip origins or destinations, along with the Austin city limits (in red) used for spatial filtering.
  • Figure 3: Distribution of core trip characteristics for the processed 2019 e-scooter dataset: (a) trip duration in minutes, (b) trip distance in kilometers, and (c) trip average speed in kilometers per hour.
  • Figure 4: Average daily e-scooter demand in 2019, obtained by averaging daily trip counts across all days of the same weekday.
  • Figure 5: Average hourly e-scooter demand in 2019, calculated by averaging trip counts for each hour of the day across all calendar days.
  • ...and 5 more figures