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

cs.CVMar 13, 2026

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

Authors: Mohammad Sahnoon, Merkebe Getachew Demissie, Roberto Souza

Organizations: Department of Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada · Department of Civil Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada

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.

Figures & tables

Fig. 1: Trip counts per vehicle type in Austin’s raw micromobility dataset (15 million samples).

Filter Category	Condition Applied
Vehicle type	Retain e-scooter trips only.
Trip year	Retain trips occurring within the 2019 calendar year.
Trip duration	Keep trips between 1 and 120 minutes inclusive.
Trip distance	Keep trips between 0.1 and 35 kilometers inclusive.
Average speed	Keep trips with speed between 2 and 26 kilometers per hour inclusive.
Tract GEOID	Trip origin and destination must have valid census tract identifiers.

TABLE I: Filtering criteria applied to construct the final Austin, TX 2019 e-scooter dataset.

Fig. 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.

Panel of Figure 4 — Fig. 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.

Fig. 4: Average daily e-scooter demand in 2019, obtained by averaging daily trip counts across all days of the same weekday.

Fig. 5: Average hourly e-scooter demand in 2019, calculated by averaging trip counts for each hour of the day across all calendar days.

Panel of Figure 7 — Fig. 6: Spatial distribution of (a) trip origin and (b) trip destination intensities for Austin’s 2019 e-scooter dataset at the census tract level, highlighting high-demand tracts in central Austin, TX.

Fig. 7: Generation of the $240\,m\,\times\,220\,m$ rectangular grid over the selected census tracts within the Austin, TX municipal boundary.

Panel of Figure 9 — Fig. 8: Sample pick-up demand image generated for 4:00 p.m. on March 17, 2019. Subplot (a) uses pixel-based indexing of the raster grid, subplot (b) expresses the same demand field in projected UTM Zone 14N coordinates, and subplot (c) shows the demand field in geographic coordinates. The color legend indicates the ground-truth demand level associated with each pixel value and is included for visualization only. For model input, demand images are represented in black and white, where the intensity of each white pixel encodes the demand level.

Panel of Figure 10 — Fig. 9: Global binary activity mask used to define the operational footprint of the historically active e-scooter demand locations to guide model training and evaluation across both the pick-up and drop-off channels. Subplot (a) uses pixel-based indexing of the raster grid, subplot (b) expresses the same demand field in projected UTM Zone 14N coordinates, and subplot (c) shows the demand field in geographic coordinates.

Fig. 10: Channel-based input representation for spatiotemporal demand prediction. The figure illustrates the pick-up demand case, where historical demand images are stacked as ordered channels (e.g., $\mathrm{Ch.}~1,\mathrm{Ch.}~2,\ldots,\mathrm{Ch.}~n$ ). The same construction is extended to drop-off demand by appending the corresponding channels and producing a two-channel output, which is evaluated against the ground-truth target map. Pixel color coding is for demand-level visual illustration only.

Next-hour		Next 24-hour
Rank final ( $\tau$ )	$\tau$ (hours)	Rank final ( $\tau$ )	$\tau$ (hours)
1	1	1	24
4	2	3	25
17	3	10	26
11	22	9	48
5	23	12	143

TABLE II: Top 20 selected historical time lags (in hours) for next-hour and next 24-hour e-scooter demand prediction. Each lag

\tau

corresponds to demand observed at time

(t-\tau)

Prediction Horizon	Configuration Type	Channels	Time-lag set $\tau$ (hours)
Next-hour	Proposed method	36	$\{1,2,3,22,23,24,25,26,48,143,144,145,167,168,169,192,336,504\}$
	Recent adjacent history	36	$\{1,2,3,\ldots,17,18\}$
	Fixed-period history	36	$\{1,25,49,73,97,121,145,169,193,217,241,265,289,313,337,361,$
	Fixed-period history	36	$385,409\}$
Next 24-hour	Proposed method	18	$\{24,25,48,144,167,168,169,192,336\}$
	Recent adjacent history	18	$\{24,25,26,27,28,29,30,31,32\}$

TABLE III: Historical Time-lag configurations used to validate the proposed historical time-lag selection method under the next-hour and next 24-hour prediction horizons. For each configuration, the same set of time lags

\tau

is applied identically to pick-up and drop-off demand, resulting in separate input channels with a shared temporal structure.

Prediction Horizon	Configuration	Input Channels	MSE*	Time Lags ( $\tau$ ) (See Table II )
Next-hour	Minimum MSE	36	20.11	Top 18
Next-hour	Minimal non-inferior	Same as minimum-MSE configuration
Next 24-hour	Minimum MSE	26	61.20	Top 13
Next 24-hour	Minimal non-inferior	18	63.42	Top 9

TABLE IV: Optimal historical input configurations identified for each prediction horizon using the UNET model. The table reports the validation-set minimum-MSE configuration and the minimal non-inferior configuration determined through Holm-corrected non-inferiority testing.

Configuration	MSE	MAE	$R^{2}$	MaxAE
Proposed method	8.45	0.50	0.78	24.33
Recent adjacent history	11.40	0.57	0.57	34.51
Fixed-period history	13.48	0.61	0.55	38.03

TABLE V: Overall test-set performance of temporal input (time-lag) selection methodologies for next-hour e-scooter demand prediction using the UNET model, computed within the masked active region and reported as metrics averaged jointly over pick-up and drop-off demand channels.

Configuration	MSE	MAE	$R^{2}$	MaxAE
Proposed method	26.37	0.75	-0.77	50.47
Recent adjacent history	40.46	0.87	-1.71	64.46
Fixed-period history	30.86	0.85	-0.36	53.26

TABLE VI: Overall test-set performance of temporal input (time-lag) selection methodologies for next 24-hour e-scooter demand prediction using the UNET model, computed within the masked active region and reported as metrics averaged jointly over pick-up and drop-off demand channels.

Horizon	Comparison	Better Configuration	Holm corrected p-value
Next-hour	Proposed method vs. recent adjacent history	Proposed method	$5.78\times 10^{-40}$
	Proposed method vs. fixed-period history	Proposed method	$1.43\times 10^{-75}$
	Recent adjacent vs. fixed-period history	Recent adjacent history	$1.89\times 10^{-4}$
Next 24-hour	Proposed method vs. recent adjacent history	Proposed method	$1.15\times 10^{-35}$
	Proposed method vs. fixed-period history	Proposed method	$1.55\times 10^{-8}$
	Recent adjacent vs. fixed-period history	Fixed-period history	$2.53\times 10^{-32}$

TABLE VII: Holm-corrected pairwise statistical comparison between historical time-lag selection methodologies on test MSE for next-hour and next 24-hour e-scooter demand prediction. Results are based on two-sided Wilcoxon signed-rank tests applied to per-sample MSE distributions averaged jointly over pick-up and drop-off demand.

Spatiotemporal Forecasting

Spatiotemporal forecasting predicts how quantities change across locations and time, from traffic and weather to disease and environmental systems.

See all 423 papers

MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models
Feb 18, 2026Antonios Tziorvas, George S. Theodoropoulos, Yannis TheodoridisSpatiotemporal Forecasting Intelligent Transportation Systems
Department of Informatics, University of Piraeus, Piraeus, Greece.
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
Jul 7, 2026Ye ZihaoAttention Mechanisms Spatiotemporal Forecasting
Department of System Engineering City University of Hong Kong
LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction
Oct 2, 2026Xuxilu Zhang, Francesc SorigueraSpatiotemporal Forecasting Time Series Forecasting
BIT – Universitat Polit`ecnica de Catalunya – Barcelona Tech (UPC), Jordi Girona 1–3, Building B1, Office 111, Barcelona 08034, Spain.

Feb 18, 2026J/K move · Enter open · S save

MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models

Antonios Tziorvas, George S. Theodoropoulos, Yannis Theodoridis

Department of Informatics, University of Piraeus, Piraeus, Greece.

Spatiotemporal Forecasting Intelligent Transportation Systems Gradient-Boosted Decision Trees

Open paper AskPDF arXiv

Urban demand forecasting plays a critical role in optimizing routing, dispatching, and congestion management within Intelligent Transportation Systems. By leveraging data fusion and analytics techniques, traffic demand forecasting serves as a key intermediate measure for identifying emerging spatial and temporal demand patterns. In this paper, we tackle this challenge by proposing two gradient boosting model variations, one for classiffication and one for regression, both capable of generating demand forecasts at various temporal horizons, from 5 minutes up to one hour. Our overall approach effectively integrates temporal and contextual features, enabling accurate predictions that are essential for improving the efficiency of shared (micro-) mobility services. To evaluate its effectiveness, we utilize open shared mobility data derived from e-scooter and e-bike networks in five metropolitan areas. These real-world datasets allow us to compare our approach with state-of-the-art methods as well as a Generative AI-based model, demonstrating its effectiveness in capturing the complexities of modern urban mobility. Ultimately, our methodology offers novel insights on urban micro-mobility management, helping to tackle the challenges arising from rapid urbanization and thus, contributing to more sustainable, efficient, and livable cities.

Abstract

Spatiotemporal Forecasting

Explore similar work

MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models

STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting

LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction