Transportation: Difference between revisions

 
Line 36:
 
* [[Understanding passenger modal preferences|'''Understanding passenger modal preferences''':]] In order for large fractions of trips to be shifted from unsustainable transportation modes (e.g. private vehicles) to more sustainable modes (e.g. public transportation), it is key to understand why passengers currently use a mode rather than another one, and under which conditions would they be willing to change their habits. ML can help understand data and model behaviors related to trips and their motivations.
* [[Fostering urban cycling as mode of transport|'''Fostering urban cycling as mode of transport''']]: Cycling is a low-carbon, healthy way to commute in cities, but inhabitants often use this mode less than they would like to due to inappropriate biking infrastructure, which makes cycling more complicated and dangerous. ML can be used in the planning and management of new biking infrastructure, in particular in the context of shared bike services.
*'''[[Supporting public transportation network expansion]]:''' In the absence of a well-ramified public transportation network (which can include trains, subways, buses and other modes), the populations in the areas poorly covered have little access to low-carbon transportation options. ML can be used in the planning and design process of new public transit lines.
*'''[[Enabling low-carbon multi-modal mobility solutions]]:''' In cities with modern transportation systems, the fastest way to get a one's destination can be to use a combination of several modes, for example a shared bike combined with a subway. ML can be used to develop apps and services to generate such itineraries using several low-carbon options.