325
edits
Transportation: Difference between revisions
→Modal shift
| (5 intermediate revisions by 2 users not shown) | |||
Line 22:
=== Improving vehicle efficiency ===
* '''[[Designing efficient vehicles]]:''' Margin emission reduction can be achieved by designing more energy-efficient vehicles, for example by improving engines or brake systems. ML can help engine design, aerodynamic research or additive manufacturing.
* '''[[Improving driving efficiency]]:''' Margin emission reduction can be achieved by a more efficient driving, which includes a better speed management or routing decisions. ML has been extensively applied to autonomous driving, and some applications enable energy gains.
*'''[[Optimizing public transportation services]]:''' So that many commuters use public transportation services, more energy-efficient that private vehicles, this services must propose time-efficient and reliable options. ML can be used in various ways, for example by predicting bus arrival time and their uncertainty.
=== Alternative fuels and electrification ===
* [[Electric vehicles driving cycle optimization|'''Electric vehicles driving cycle optimization''']]: Optimizing the driving efficiency of electric vehicle has specific challenges related to batteries. ML can help predict various relevant metrics such as battery state based on driving cycles.
*[[Electric vehicle charging infrastructure|'''Electric vehicle charging infrastructure''']]: Deploying electric vehicles at scale requires an adequate charging infrastructure, with various planning, scheduling and management issues. ML can help for example with predicting usage of the infrastructure and load prediction.
*'''[[Accelerated Science|Accelerated science]] for alternative fuels:''' Alternative fuels have the potential to provide low-carbon solutions while retaining the properties of fossils, but most of them remain at an early stage of development. Machine learning can help accelerate this development by learning patterns in experimental or operational data in order to guide future experiments/operations.
* '''Electric vehicle [[demand response]]:''' Battery electric vehicles are typically not used for more than a fraction of the day, allowing them to act as energy storage for the grid at other times, where charging and discharging is controlled for example by price signals. ML can help enable demand response application by forecasting or controlling signals.
=== Modal shift ===
* [[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 cycling as mode of transport|'''Fostering 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.
== Background Readings ==
Line 53:
==Conferences, Journals, and Professional Organizations==
=== Major conferences ===
=== Major journals ===
* '''Transportation Research parts A-E:''' A set of transportation journals focusing on policy and practice ([https://www.journals.elsevier.com/transportation-research-part-a-policy-and-practice A]), methodology ([https://www.journals.elsevier.com/transportation-research-part-b-methodological B]), emerging technologies ([https://www.journals.elsevier.com/transportation-research-part-c-emerging-technologies C]), links with the environment ([https://www.journals.elsevier.com/transportation-research-part-d-transport-and-environment D]), and logistics ([https://www.journals.elsevier.com/transportation-research-part-e-logistics-and-transportation-review E]).
* '''Transport reviews:''' A journal providing authoritative and up to date research-based reviews of transport related topics that are informative to those that are knowledgeable in the subject area. Website [https://www.tandfonline.com/action/journalInformation?show=aimsScope&journalCode=ttrv20 here].
=== Major organizations ===
*'''Transportation Research Board''': "As part of the National Academies of Sciences, Engineering, and Medicine, the Transportation Research Board (TRB) provides leadership in transportation improvements and innovation through trusted, timely, impartial, and evidence-based information exchange, research, and advice regarding all modes of transportation." Website [http://www.trb.org/Main/Home.aspx here].
*'''International Transport Forum''': An inter-governmental organization "promot[ing] carbon-neutral mobility to help stop climate change" and "provid[ing] decision makers with tools to select CO<sub>2</sub> mitigation measures that deliver on their climate commitment." Website [https://www.itf-oecd.org/decarbonising-transport here].
Line 58 ⟶ 66:
==Libraries and Tools==
{{SectionStub}}
==Data==
| |||