A reproducible grid-based pipeline converts Austin e-scooter trips into spatiotemporal demand images; a correlation-plus-error method plus ablation study on UNET selects temporal inputs that cut next-hour MSE by up to 37% and next-24-hour MSE by up to 35% versus simple baselines.
On the inefficiency of ride-sourcing services towards urban congestion,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Grid-Based Framework for E-Scooter Demand Representation and Temporal Input Design for Deep Learning: Evidence from Austin, Texas
A reproducible grid-based pipeline converts Austin e-scooter trips into spatiotemporal demand images; a correlation-plus-error method plus ablation study on UNET selects temporal inputs that cut next-hour MSE by up to 37% and next-24-hour MSE by up to 35% versus simple baselines.