The choice of low-carbon travel modes by residents directly affects the low-carbon development of transportation. Whereas, the current study of behavior prediction models lacks the accuracy and interpretability. We propose the theoretical framework of residents' low-carbon travel choice behavior at the microlevel and construct the Stacking ensemble learning prediction model on basis of residents' low carbon travel data. Through integrating various data such as transportation facility data and real-time weather observation data, we utilize machine learning algorithms to improve the prediction accuracy of residents' low-carbon travel choice, and explore the impact of different influencing factors on their choice behaviors.
Predictions of Low-carbon Travel Mode Choices for Residents Based on Stacking Ensemble Learning Prediction Model
07.08.2024
432850 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Travel mode choices of residents in developing cities: A case study of Lusaka, Zambia
DOAJ | 2024
|Snowfall Impact on Travel Mode Choices
ASCE | 2018
|Discrete Continuous Travel Mode Choices based on Simulated Travel Demand: a MDCEV Model Application
Elsevier | 2025
|Mobility, Poverty, and Gender: Travel ‘Choices’ of Slum Residents in Nairobi, Kenya
Taylor & Francis Verlag | 2010
|