Transportation

''This page is about the intersection of transportation and machine learning in the context of climate change mitigation and adaptation. For an overview of transportation as a whole, please see the Wikipedia page on this topic.'' Transportation systems form a complex web that is fundamental to an active and prosperous society. Globally, the transportation sector accounts for about a quarter of energy-related CO2 emissions. In contrast to the electricity sector, however, transportation has not made significant progress to lower its CO2 emissions and much of the sector is regarded as hard to decarbonize. This is because of the high energy density of fuels required for many types of vehicles, which constrains low-carbon alternatives, and because transport policies directly impact end-users and are thus more likely to be controversial.

Passenger and freight transportation are each responsible for about half of transport GHG emissions. Both freight and passengers can travel by road, by rail, by water, or by air (referred to as transport modes). Different modes carry vastly different carbon emission intensities. At present, more than two-thirds of transportation emissions are from road travel, but air travel has the highest emission intensity and is responsible for an increasingly large share. Strategies to reduce GHG emissions from transportation include:


 * Reducing transport activity,
 * Improving vehicle efficiency,
 * Alternative fuels and electrification,
 * Modal shift (shifting to lower-carbon options, like rail).

Each of these mitigation strategies offers opportunities for ML. While many of us probably think of autonomous vehicles and ride-sharing when we think of transport and ML, these technologies have uncertain impacts on GHG emissions, potentially even increasing them. In reality, ML can play a role for decarbonizing transportation that goes much further. ML can improve vehicle engineering, enable intelligent infrastructure, and provide policy-relevant information. Many interventions that reduce GHG emissions in the transportation sector require changes in planning, maintenance, and operations of transportation systems, even though the GHG reduction potential of those measures might not be immediately apparent. ML can help in implementing such interventions, for example by providing better demand forecasts. Typically, ML strategies are most effective in tandem with strong public policies.

Reducing transportation activity

 * Understanding mobility patterns: Large amounts of geolocated traces are being collected that enable to analyze mobility patterns, which can be useful for example for planning transportation networks. ML can help find relevant patterns, such as transportation modes.
 * Modeling demand for passenger and freight transportation: Designing efficient transportation systems requires to know well the transportation demand in order to be well adapted to it. ML can improve standard demand modelling tools such as discrete choice models.
 * Enabling low-carbon shared mobility: For shared mobility to be a low-carbon option, it needs to effectively enable to reduce the number of kilometers travelled by pooling users. ML can help real-time decision for example for ride-hailing services.
 * Routing for freight and passenger vehicles: By taking the best possible route, aircrafts, cars and other vehicles can get to their destination with less energy compared to the choices that are most often made. ML can help navigate through large number of possible choices to find optimal pathways.
 * Freight consolidation: Bundling shipments together through freight consolidation can dramatically reduce the number of trips and associated GHG emissions. ML can optimize complex relationship between the various dimensions involved in shipping decisions, such as shipment mode and origin-destination pairs.

Improving vehicle efficiency

 * Designing efficient vehicles
 * Improving driving efficiency
 * Optimizing public transportation services

Alternative fuels and electrification

 * Electric vehicles driving cycle optimization
 * Electric vehicle charging infrastructure
 * Accelerated science for alternative fuels
 * Electric vehicle demand response

Modal shift

 * Understanding passenger modal preferences
 * Fostering urban cycling
 * Supporting public transportation network expansion

Background Readings

 * Chapter 8: "Transport" in the IPCC Fifth Assessment Report (2014) : An overview of climate change mitigation from freight and passenger transport. Available here.
 * Leveraging digitalization for sustainability in urban transport (2019) : A perspective on opportunities, risks, and policy actions for digitalization in urban transport systems.
 * Decarbonizing intraregional freight systems with a focus on modal shift (2018) : An overview of "strategies for decarbonizing freight transportation...and literature and data relevant to estimating the global decarbonization potential through modal shift."
 * The Future of Trucks (2017) : A report from the International Energy Agency on road freight, and its implications for energy and the environment.

Community

 * 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 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 CO2 mitigation measures that deliver on their climate commitment." Website here.
 * International Transport Energy Modeling (iTEM): "[A]n open group of people and organizations interested in the role of energy in the world's transport system." Website here.

Data

 * US Commodity Flow Survey: Commodity flows as surveyed by the US Census Bureau every 5 years.
 * National and sub-national agencies report traffic counts at different spatial and temporal resolutions, e.g. Germany or California