Riders on the Storm: Exploring Meteorological and Temporal Impacts on Shared E-Scooters (SES) in Munich, Germany

Pobudzei, Maryna; Sellaouti, Anis; Tießler, Michaela; Hoffmann, Silja

doi:10.1109/isc255366.2022.9922429

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gaining insights into how weather and time influence different types of trips could offer valuable guidance for policymakers and transport planners. This knowledge can assist in integrating alternative transportation options and adapting existing modes to provide protection against weather conditions [51]. [56] also highlighted that the current lack of detailed user data prevents a comprehensive analysis of how different types of users, such as women, older adults, commuters, and tourists, are affected by weather conditions.…”

Section: Stated Preference Surveymentioning

confidence: 99%

Shared E-scooter Usage Analysis considering the Effect of Weather Conditions and Land Use: Qatar Case Study

Elhenawy,

Mohammed,

Tahmasseby

et al. 2024

Preprint

View full text Add to dashboard Cite

Shared e-scooters are gaining popularity as a solution for first and last-mile connectivity in urban areas. This study conducted in Doha, Qatar, aimed to understand how weather and land use patterns affect e-scooter usage, utilizing various datasets. Given the novelty of micromobility systems in Qatar and their sensitivity to the local hot and humid climate, the study employed a comprehensive analytical approach. Analysis revealed that e-scooter demand spikes on weekends, particularly in the afternoon. Influential land use factors include proximity to universities and employment centers, while a higher presence of Qatari females in an area correlates with reduced usage, pointing to cultural influences. Weather conditions, especially humidity and extreme temperatures, significantly impact e-scooter demand. The study employed the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm for trip clustering and the Random Forest (RF) algorithm to model trip counts, considering temperature and humidity. Insights showed humidity as a critical predictor of hourly e-scooter trip counts. These findings underscore the importance of considering weather, land use, the relationship between land use characteristics and weather variations, and finally cultural factors in optimizing e-scooter services. By integrating data analysis and machine learning, the study offers valuable insights for enhancing urban mobility and transportation planning in GCC countries, promoting sustainable urban mobility.

show abstract

Section: Stated Preference Surveymentioning

confidence: 99%