Could an AI Write a Transportation Plan?

Could an AI Write a Transportation Plan?

Could an artificial intelligence accomplish portions of our job as transportation professionals? I have my doubts. I can accept an AI analyzing complex data, beating humans at chess, or automating routine tasks. But the role of a professional is safe, right? ChatGPT is making me wonder.

ChatGPT, a tool from OpenAI, has been gaining a lot of attention lately. And for good reason. It only took a few minutes using—or, to be more descriptive, chatting with—the AI to understand why. I started by asking a simple question:

No alt text provided for this image

What is TSMO in the transportation world?

TSMO stands for "Transportation Systems Management and Operations." It is a term used to describe a broad range of strategies, technologies, and practices that are used to improve the safety, efficiency, and performance of transportation systems. TSMO approaches typically focus on optimizing the use of existing transportation infrastructure and resources, rather than building new roads or expanding capacity. Some common TSMO strategies include traffic management, incident response, traveler information, and demand management. By implementing TSMO measures, transportation agencies can help to reduce congestion, improve air quality, and make transportation systems more sustainable and resilient.


The answer is accurate, but uninspiring. One Google search provides the same answer. So I continued to explore:

No alt text provided for this image

Give me a few sources for more information on TSMO

I'm sorry, but I am not currently able to browse the internet or access external sources of information. As a large language model trained by OpenAI, my knowledge is based solely on the text that has been input to me. I do not have the ability to browse the web or access external sources of information.


Disappointing. I try another question.

No alt text provided for this image

Give me a few more examples of TSMO strategies

Here are a few additional examples of TSMO strategies that can be used to improve the safety, efficiency, and performance of transportation systems:

  1. Intelligent transportation systems (ITS): These are technologies that use sensors, cameras, and other devices to collect data about traffic conditions and provide real-time information to transportation agencies and drivers. ITS can be used for a variety of purposes, such as traffic signal control, incident detection, and traveler information.
  2. Active traffic management (ATM): This is a set of techniques that are used to manage traffic flow and reduce congestion on highways. ATM strategies can include variable speed limits, lane control signals, and dynamic shoulder lanes.
  3. Freeway service patrols (FSP): These are teams of trained personnel who patrol highways and respond to incidents, such as crashes, disabled vehicles, and debris. FSPs can provide quick clearance of incidents and help to reduce congestion and improve safety on highways.
  4. Transportation demand management (TDM): This is a set of strategies that are used to reduce the demand for car travel and encourage the use of alternative modes, such as public transit, biking, and walking. TDM strategies can include carpooling, ridesharing, and telecommuting programs.
  5. Traveler information systems (TIS): These are systems that provide real-time information to travelers about traffic conditions, transit schedules, and other relevant information. TIS can be delivered through a variety of channels, such as websites, mobile apps, and highway signage.


Good information. But, again, somewhat easy to find elsewhere. I continue chatting:

No alt text provided for this image

Tell me more about TDM

Transportation demand management (TDM) is a set of strategies that are used to reduce the demand for car travel and encourage the use of alternative modes of transportation. TDM strategies can help to reduce congestion, improve air quality, and make transportation systems more sustainable and resilient. Some common TDM strategies include:

  1. Carpooling and ridesharing programs: These programs encourage people to share rides with others who are traveling to the same destination. Carpooling and ridesharing can reduce the number of cars on the road, improve traffic flow, and save money for both the individuals participating and society as a whole.
  2. Public transit incentives: These are programs that provide incentives, such as discounts or rewards, to encourage people to use public transit instead of driving. Public transit incentives can be used to promote the use of buses, trains, or other forms of mass transit.
  3. Non-motorized transportation programs: These programs promote the use of non-motorized modes of transportation, such as walking and biking. Non-motorized transportation programs can include infrastructure improvements, such as bike lanes and pedestrian walkways, as well as education and outreach efforts to encourage more people to walk and bike.
  4. Telecommuting programs: These are programs that encourage employees to work from home or other remote locations, rather than commuting to an office. Telecommuting can reduce the number of cars on the road, improve air quality, and provide benefits to both employees and employers.

TDM strategies can be implemented by transportation agencies, employers, or other organizations. By reducing the demand for car travel, TDM strategies can help to make transportation systems more efficient, sustainable, and resilient.


Now it is starting to feel like I am having a conversation. But, this AI is supposedly adept at writing well. Let's find out.

No alt text provided for this image

Write a one page plan for a transportation agency to implement TDM strategies

Transportation demand management (TDM) strategies can help transportation agencies reduce the demand for car travel and encourage the use of alternative modes of transportation. Implementing TDM strategies can improve traffic flow, reduce congestion, and make transportation systems more sustainable and resilient.

To implement TDM strategies, a transportation agency can follow these steps:

  1. Identify target areas: The first step is to identify the areas where TDM strategies can be most effective. These may be areas with high levels of congestion, limited public transit options, or a large number of employees who commute to work by car.
  2. Develop a plan: Next, the transportation agency should develop a plan for implementing TDM strategies in the target areas. The plan should include specific goals and objectives, as well as a timeline and budget. The plan should also identify which TDM strategies will be used and how they will be implemented.
  3. Engage stakeholders: TDM strategies are often most effective when they are implemented with the support and involvement of key stakeholders, such as employers, community organizations, and local governments. The transportation agency should engage with these stakeholders to seek their input and support for the TDM plan.
  4. Implement TDM strategies: Once the plan is developed, the transportation agency can begin implementing the TDM strategies in the target areas. This may involve implementing carpooling and ridesharing programs, providing incentives for public transit use, improving infrastructure for non-motorized transportation, or promoting telecommuting programs.
  5. Monitor and evaluate: Finally, the transportation agency should monitor and evaluate the effectiveness of the TDM strategies over time. This may involve collecting data on traffic flow, mode shift, and other metrics, and using this information to refine and improve the TDM plan.

By following these steps, a transportation agency can effectively implement TDM strategies and achieve its goals for reducing the demand for car travel and improving the performance of its transportation system.


Now I am getting impressed. This is a well written document, complete with decent content and a nice structure. I decide to push it a bit further. If AI is going to replace a professional, I should treat it like one.

No alt text provided for this image

Make it from the Ohio Department of Transportation

To implement transportation demand management (TDM) strategies, the Ohio Department of Transportation (ODOT) can follow these steps:

  1. Identify target areas: The first step is to identify the areas in Ohio where TDM strategies can be most effective. These may be areas with high levels of congestion, limited public transit options, or a large number of employees who commute to work by car.
  2. Develop a plan: Next, ODOT should develop a plan for implementing TDM strategies in the target areas. The plan should include specific goals and objectives, as well as a timeline and budget. The plan should also identify which TDM strategies will be used and how they will be implemented.
  3. Engage stakeholders: TDM strategies are often most effective when they are implemented with the support and involvement of key stakeholders, such as employers, community organizations, and local governments. ODOT should engage with these stakeholders to seek their input and support for the TDM plan.
  4. Implement TDM strategies: Once the plan is developed, ODOT can begin implementing the TDM strategies in the target areas. This may involve implementing carpooling and ridesharing programs, providing incentives for public transit use, improving infrastructure for non-motorized transportation, or promoting telecommuting programs.
  5. Monitor and evaluate: Finally, ODOT should monitor and evaluate the effectiveness of the TDM strategies over time. This may involve collecting data on traffic flow, mode shift, and other metrics, and using this information to refine and improve the TDM plan.

By following these steps, the Ohio Department of Transportation can effectively implement TDM strategies and achieve its goals for reducing the demand for car travel and improving the performance of its transportation system.


The AI is keeping up with me. And, we have a half-decent template ODOT could start with. But, it is essentially an outline of sorts. If this were a real engineer working on the task, we would notice gaps in the content. So, I make a realistic request:

No alt text provided for this image

Add a section on performance measures

To effectively implement transportation demand management (TDM) strategies, it is important to establish performance measures that can be used to evaluate the success of the strategies. These performance measures should be specific, measurable, achievable, relevant, and time-bound. Some examples of performance measures for TDM strategies include:

  • The percentage of employees who participate in a carpooling or ridesharing program
  • The number of miles traveled by carpoolers or ridesharers
  • The number of trips taken on public transit
  • The number of miles traveled by non-motorized modes, such as walking and biking
  • The number of telecommuting days per employee
  • The number of vehicles on the road during peak hours
  • The average travel time during peak hours

By tracking these performance measures over time, a transportation agency can evaluate the effectiveness of its TDM strategies and make adjustments as needed to achieve its goals.


The progression surprises me. This sounds like an applicable section on performance measures. Another ChatGPT competency is writing tone. I make one final request:

No alt text provided for this image

Make the introduction sound more exciting

Transportation demand management (TDM) is an exciting and innovative approach to improving the safety, efficiency, and sustainability of transportation systems. By implementing TDM strategies, transportation agencies can reduce congestion, improve air quality, and make transportation systems more resilient. Through the use of carpooling and ridesharing programs, public transit incentives, non-motorized transportation programs, and telecommuting programs, TDM can help to reduce the demand for car travel and encourage the use of alternative modes of transportation. By following a plan and tracking performance measures, transportation agencies can effectively implement TDM strategies and achieve their goals for improving their transportation systems.


Fascinating. The AI re-wrote the original introduction in an exciting tone and, unprompted by me, incorporated a bit about performance measures.

At this point I am convinced:

  • This technology is unlike any tool I?have used before.
  • Us mere humans can no longer get away with mediocre writing.
  • AI is likely to impact transportation in ways we are not currently predicting.



One final observation

Another defining feature of AI is the ability to improve. ChatGPT is no exception. It took me, with my limited human intelligence, a few days to draft this LinkedIn article. When I revisited my TSMO conversation a few days later, I noticed that my second question—which originally generated a disappointing answer—prompted a more useful response.

No alt text provided for this image

Give me a few sources for more information on TSMO

Here are a few sources where you can find more information on Transportation Systems Management and Operations (TSMO):

  1. Federal Highway Administration (FHWA): The FHWA is a division of the US Department of Transportation and is responsible for providing leadership, technology, and financial assistance to states and localities for the construction, maintenance, and operation of the nation's highway system. The FHWA has a webpage dedicated to TSMO, which includes resources, guidance, and best practices for implementing TSMO measures: https://www.fhwa.dot.gov/tsmo/
  2. Institute of Transportation Engineers (ITE): The ITE is a professional society that represents transportation engineers, planners, and other professionals around the world. The ITE has a number of resources related to TSMO, including publications, webinars, and professional development courses: https://www.ite.org/technical-resources/transportation-systems-management-and-operations/
  3. Transportation Research Board (TRB): The TRB is a division of the National Academies of Sciences, Engineering, and Medicine and conducts research on a wide range of transportation issues. The TRB has a number of committees and task forces that focus on TSMO, and their website includes a wealth of information on TSMO research and best practices: https://www.trb.org/TransportationSystemsManagementOperations.aspx
  4. National Transportation Operations Coalition (NATO): NATO is a coalition of transportation agencies and organizations that work to improve the efficiency and effectiveness of transportation operations. NATO has a number of resources related to TSMO, including guidance documents, case studies, and training materials: https://www.ops.fhwa.dot.gov/tsmo/tsmo_nato.htm

I hope these sources are helpful in learning more about TSMO.


Thankfully, it appears most of the URLs in this response are broken. I was beginning to worry about our future.

I only have one final request for the AI:

ChatGPT, please write a conclusion for this LinkedIn post. Mention that I know human expertise is still valuable. Give credit to AI for their ability to assist in writing, researching, and any other observations you would like to include.?

Adam Moore

Construction Project Manager at 3C Industries, LLC. Head Varsity Basketball Coach at Triad High School

2 年

The world is definitely changing. Knowing which questions to ask will be a skill to have in the future.

Pete Costello

President @ Pete Costello, LLC | Transportation Analytics and Smart Cities

2 年

John, another colleague did this exercise and also received some impressive results. It looks like we ALL have to up our game! Happy holidays

Celine LePage

Keep your people, business, and assets safe with samdesk

2 年

Interesting to see the AI responses evolve during your conversation! Your comments about ChatGPT providing “an outline of sorts” and a structured response was particularly striking to me. I can see the benefits of using AI to speed up the writing process for documentation, plans, reports, etc. by cutting out “the mental noise” many authors experience at the beginning of a project. As you mentioned, a professional may still identify errors or omissions in ChatGPT’s content, but it’s better than most humans can do on a first draft. Losing the intimidating “blank page” at the beginning of the writing process doesn’t hurt either!

要查看或添加评论,请登录

John MacAdam的更多文章

  • Thoughts on Professional Self-Employment

    Thoughts on Professional Self-Employment

    TL;DR: I finally know how to answer the question: "What are you doing for a living?" The workplace landscape is…

    1 条评论
  • Building a Sustainable Side Hustle

    Building a Sustainable Side Hustle

    My experience building a profitable side business. Have you ever built a fire in a hurry? The kind you light quickly —…

    9 条评论
  • The Gamification of Training AI

    The Gamification of Training AI

    I have had three experiences training machine learning models—two professionally and one personally. In each case…

    4 条评论
  • One Year of Self-Employment: Reflections and Lessons Learned

    One Year of Self-Employment: Reflections and Lessons Learned

    My Journey So Far One year ago, I started a new adventure by leaving my full-time job at ODOT and becoming an…

    16 条评论
  • Design Tips for Engineers

    Design Tips for Engineers

    Engineers are not usually great graphic designers. This does not mean our documents and presentations have to be poorly…

    4 条评论
  • Thoughts on the Task List

    Thoughts on the Task List

    I have a fondness for software. I use software for basically everything: writing code, analyzing data, writing reports,…

    4 条评论
  • Books Improving the Quality of My Work

    Books Improving the Quality of My Work

    I love reading books. Almost any type of book.

    1 条评论
  • An Update Regarding My Business

    An Update Regarding My Business

    This week marks six months of running my own business. And, thankfully, I think I finally figured out what I am doing.

    8 条评论
  • Thoughts on Criticism

    Thoughts on Criticism

    There are two moments of criticism I remember very clearly: The first time I released an app on the App Store The first…

    9 条评论
  • Covid Reduced Traffic… So Where Are We Now?

    Covid Reduced Traffic… So Where Are We Now?

    Think back to March and April of 2020. A few things disappeared seemingly overnight: toilet paper, the stock market…

社区洞察

其他会员也浏览了