How AI is Fighting Climate Change — Public Transportation

Martina_Kiewek
6 min readNov 15, 2020

--

AI’s role in the transportation industry

The global transportation sector is responsible for 23% of global energy-related carbon emissions, and experts predict that the figure is on track to double by 2050 if we don’t take action. With this in mind, how can we use AI to make the transportation industry more sustainable? When we think about AI in relation to transportation, our minds first jump to the quickly approaching possibility of autonomous vehicles. However, the versatile abilities of AI can also be applied in many other ways, and it is incredibly well suited to work with the transportation industry that has a massive amount of data that is constantly evolving. In this article, I will focus on how artificial intelligence is being used to improve the public transportation system by helping to determine flexible routes based on demand, track and communicate the location of vehicles, and organize bike-sharing infrastructure. Through these three applications, AI can make public transportation more efficient by reducing carbon emissions and more desirable by increasing reliability and decreasing time spent in transit.

Why is public transportation important for climate action?

Data shows that, on average, a two-car American family’s biggest contributor to their carbon footprint are private vehicles (55% of footprint), and that removing even just one of those vehicles in exchange for public transportation could result in savings of about 30% in greenhouse gas emissions. While the climate emergency will require significant, sustained action in almost every industry across the board, this is a great place to start, so let's explore how we can use artificial intelligence to create a better public transportation infrastructure that helps families transition away from private vehicles.

“Environmental Benefits of Public Transit.” KCATA, Kansas City Area Transportation Authority, 2020, www.kcata.org/about_kcata/entries/environmental_benefits_of_public_transit.

Demand responsive schedules and routes

Public transportation methods today typically have set locations and times on which they operate, schedules that are not responsive to customer demand or prevailing traffic conditions. One major way in which AI can improve on this system is through its ability to crunch large data sets and interpret them to design routes best optimized to get the active commuters to their destination as efficiently as possible. While buses rely on set schedules, AI-backed infrastructure is much more adaptive and can change depending on where people need to be picked up or dropped off at a particular time. For example, a company called BRIDJ based in Boston has reimagined public transportation using this technology. Commuters, instead of being restricted to traditional bus stops, can request a bus to pick them up at a nearby “stop”, even with short notice. This “stop” is not only more accessible to the commuter, but it also means that the bus will not make unnecessary stops or detours. This is made possible by an optimization algorithm that works to determine which vehicle size to use depending on the predicted amount of commuters, what stops it needs to make to minimize deviation and unnecessary stops while still providing service for as many people as possible. The algorithm creates a system with lower operating costs, flexible stops and timetables, and shorter journey times. Additionally, because BIRDJ is designed to work in conjunction with traditional public transportation systems, it effectively fills in the gaps present in city planning that leave certain populations without convenient access to adequate public transport. Without AI algorithms, it would not be possible to have such adaptive and fluid routes.

Vehicle tracking

With increasing prevalence, public transportation systems are being equipped with the technology to communicate with commuters to inform them of estimated arrival times, including live updates of delays and cancelations. This is made possible by Automatic Vehicle Location (AVL) systems that use GPS to track individual buses. During the past ten years, London has been using AVL to run iBus, a public infrastructure made up of over 9,300 buses. The live GPS data is used not only to provide accurate updates to commuters, but also to keep drivers informed of changing road conditions. Additionally, when a bus is running late, it can communicate with local traffic systems to get priority at stoplights. This technology has become normalized in our everyday lives because of navigation apps like google maps and Waze, but none of it would be possible without AI algorithms. Finally, the data gathered for AVL is adding to the massive database of information that can be used in the future to write even more accurate and powerful algorithms.

Hounsell, N.B., et al. “Data Management and Applications in a World-Leading Bus Fleet.” Transportation Research Part C: Emerging Technologies, Pergamon, 14 Jan. 2012, www.sciencedirect.com/science/article/pii/S0968090X11001707.

Impact of AI on bike-sharing

The BICO AI platform was built to help Micro mobility companies succeed, it has had a tremendous impact on city-wide bike-sharing projects in cities all over the world. Bike-sharing schemes work by having several stations at strategic points throughout the city where you can pick up and drop off bikes. In data presented on three cities using BICO’s AI, all three experienced an increase in daily ridership (0.75 more rides a day in Chicago, 1.5 in Guadalajara, and 5 more rides a day in Helsinki — per bike). Additionally, a large and fiscally demanding challenge associated with bike-share is having both bikes and open docks available at the required times and locations. In order to satisfy this need, redistribution trucks are needed to move the bikes from one station to another. By using BICO’s predictive and analytical capabilities, the distance driven by redistribution trucks over a period of 12 months decreased by 10,000 miles, saving money, reducing carbon emissions, and allowing for a reduction in fleet size. With the help of AI, bike-sharing programs are decreasing the carbon footprint of cities in an incredibly sustainable way.

“Enabling Success in Micromobility.” BICO, BICO AI, www.bico.ai/.

Conclusion:

This was by no means a comprehensive list of AI’s application within the transportation sector, but hopefully, it gave you an idea of the work that is being done. By making public transportation more accessible, reliable, and efficient, AI is helping us reduce greenhouse gas emissions. As more algorithms are put into place, we will have more data to work with and the algorithms will continue to improve. The science is clear, we have to start transitioning away from private gas-powered vehicles towards more sustainable means of transportation.

Martina Kiewek is a Student Ambassador in the Inspirit AI Student Ambassadors Program. Inspirit AI is a pre-collegiate enrichment program that exposes curious high school students globally to AI through live online classes. Learn more at https://www.inspiritai.com/.

Sources:

Abduljabbar, Rusul, et al. “Applications of Artificial Intelligence in Transport: An Overview.” MDPI, Multidisciplinary Digital Publishing Institute, 2 Jan. 2019, www.mdpi.com/2071-1050/11/1/189/htm.

Bishop, Richard. “U.S. States Are Allowing Automated Follower Truck Platooning While The Swedes May Lead In Europe.” Forbes, Forbes Magazine, 2 May 2020, www.forbes.com/sites/richardbishop1/2020/05/02/us-states-are-allowing-automated-follower-truck-platooning-while-the-swedes-may-lead-in-europe/?sh=6200ab60d7e8.

Conde, Maria L, and Ian Twinn. “How Artificial Intelligence Is Making Transport Safer, Cleaner, More Reliable and Efficient in Emerging Markets.” EM Compass, International Finance Corporation, Nov. 2019, www.ifc.org/wps/wcm/connect/7c21eaf5-7d18-43b7-bce1-864e3e42de2b/EMCompass-Note-7www.ifc.org/wps/wcm/connect/7c21eaf5-7d18-43b7-bce1-864e3e42de2b/EMCompass-Note-75-AI-making-transport-safer-in-Emerging-Markets.pdf?MOD=AJPERES&CVID=mV7VCeN5-AI-making-transport-safer-in-Emerging-Markets.pdf?MOD=AJPERES&CVID=mV7VCeN.

“Critical Issues in Transportation 2019.” Critical Issues in Transportation 2019: Policy Snapshot | The National Academies Press, Transportation Research Board, 2019, www.nap.edu/resource/25314/criticalissues/.

“The Direct Impact of AI on Bike-Share.” Sharing Ideas to Solve Urban Challenges, Smart Cities World, 29 Oct. 2018, www.smartcitiesworld.net/news/news/the-direct-impact-of-ai-on-bike-share-3488.

“Enabling Success in Micromobility.” BICO, BICO AI, www.bico.ai/.

“Environmental Benefits of Public Transit.” KCATA, Kansas City Area Transportation Authority, 2020, www.kcata.org/about_kcata/entries/environmental_benefits_of_public_transit.

Floman, Roni. “What Can And Can’t Artificial Intelligence Do For Public Transport? Separating Myth From Reality.” Optibus, 23 Mar. 2020, www.optibus.com/what-can-and-cant-artificial-intelligence-do-for-public-transport-separating-myth-from-reality/.

Hounsell, N.B., et al. “Data Management and Applications in a World-Leading Bus Fleet.” Transportation Research Part C: Emerging Technologies, Pergamon, 14 Jan. 2012, www.sciencedirect.com/science/article/pii/S0968090X11001707.

Joshi, Naveen. “How AI Can Transform The Transportation Industry.” Forbes, Forbes Magazine, 30 July 2019, www.forbes.com/sites/cognitiveworld/2019/07/26/how-ai-can-transform-the-transportation-industry/?sh=2990f6274964.

Liang, Shidong, et al. “Multiobjective Optimal Formulations for Bus Fleet Size of Public Transit under Headway-Based Holding Control.” Journal of Advanced Transportation, Hindawi, 10 Jan. 2019, www.hindawi.com/journals/jat/2019/2452348/.

Liu, Tao, and Avishai (Avi) Ceder. “Analysis of a New Public-Transport-Service Concept: Customized Bus in China.” Transport Policy, Pergamon, 24 Feb. 2015, www.sciencedirect.com/science/article/abs/pii/S0967070X15000256.

Richardson, Jake. Electric Cars Mostly Run On Electricity From Renewable Energy Or Natural Gas, Clean Technica, 6 Feb. 2018, cleantechnica.com/2018/02/06/evs-dont-run-electricity-coal-power-plants/.

solo, pollo. “Machine Learning: The Engine inside Tesla’s Automated Driving Technology.” Technology and Operations Management, Nov. 2018, digital.hbs.edu/platform-rctom/submission/machine-learning-the-engine-inside-teslas-automated-driving-technology/.

Sign up to discover human stories that deepen your understanding of the world.

Free

Distraction-free reading. No ads.

Organize your knowledge with lists and highlights.

Tell your story. Find your audience.

Membership

Read member-only stories

Support writers you read most

Earn money for your writing

Listen to audio narrations

Read offline with the Medium app

--

--

Martina_Kiewek
Martina_Kiewek

Written by Martina_Kiewek

Mexican high school student living in Philadelphia. I am passionate about STEM, social justice, and basketball.

Responses (1)

Write a response