APPENDIX A

Survey Questions

Part A) Introduction/Familiarity with ML methods

A1) My agency/organization is located in: [Answer: Select from the List of States]

A2) Which one of the following best describes your agency/organization?

• State Department of Transportation (DOT)
• Turnpike and/or Bridge Authority
• County/City DOT
• City/Municipality
• Public transit agency/authority
• Metropolitan Planning Organization (MPO) or Council of Government
• Other, Please specify: ________________

A3) Within your agency, please select an option that best describes the departmental unit you work for.

• Central or district administration, finance/fiscal, human resources, public relations, procurement
• Research and development
• Engineering – traffic operations, transportation systems operations and management
• Engineering – road safety
• Engineering – maintenance, asset management
• Engineering – construction, rehabilitation, materials
• Mobility planning, demand management, tolling, land use
• Public transportation, alternative modes of mobility
• Rail transport, freight transportation, port operations
• Information technology, information security

Other, please specify: _________________

A4) How familiar is your agency with ML methods and tools (examples include artificial neural networks, deep learning, decision trees, support vector machines, K-Nearest Neighbors (KNN), K-means, random forest, logistic regression, gradient boosting methods, reinforcement learning)?

• Very familiar (we have developed or used several ML applications)
• Somewhat familiar (we have ML projects in early stage of development)
• Not very familiar (we are aware of ML but have not started actively exploring them)
• Not at all familiar (we are not aware of any ML methods or tools that are applicable to our agency operations)

A5) Does your agency have a Data Scientist/Engineer position classification?

1. If yes, how many data scientists/engineers do you employ? _____
2. If not, does your agency have any positions that provide data scientist-type services or have similar skill sets within your agency?

• Yes

If yes: Please enter the number of people in these types of positions employed by the agency: ____

• No

A6) Does your agency have any ML applications (models or tools which have been shared for use by agency staff) currently deployed and/or being developed?

• Yes
• No (If no, skip to Part C: Question C1)

A7) What ML methods has your agency used or are in the development phase for one or more applications?

Artificial Neural Networks (ANN), Deep Learning (DL)

Decision trees, random forests

Support Vector Machines (SVM)

KNN, K-means

Logistic regression

Gradient boosting methods

Reinforcement learning methods

Others, please specify______________

Part B) ML applications developed/used in-house or deployed as commercial products

B1) Which in-house ML applications (including applications developed that leverage available open-source code such as pre-trained neural networks) is your agency currently using? Please indicate the applications that your organization uses the most often and indicate whether you utilize open-source code.

B2) What commercial ML products (e.g., video analytics programs for traffic volumes, algorithms for detecting incidents, image-based methods for detecting pavement or road conditions) is your agency currently using? Please indicate the products that your organization uses the most often.

B3) Other than the ML applications currently being used, what additional ML applications are currently being explored or are under consideration for future implementation by your agency? List as many as possible and their application areas.

B4) For which of the following application areas has your agency developed/implemented/procured ML solutions? [Check all that apply]

Cybersecurity (e.g., ML algorithms to detect intrusion/cyberattacks)

Transportation systems management and operations (TSMO) (e.g., ML algorithms to detect incidents or estimate traffic conditions)

Commercial Vehicle and Freight Operations (e.g., image-based truck classification algorithms)

Accessible Transportation (e.g., wheelchair detection at pedestrian signals)

Transit Operations and Management (e.g., AI-powered transit signal priority)

Emergency Management (e.g., ML for processing drone images of the scene)

Asset Management and maintenance (e.g., traffic sign recognition from image data)

Construction, rehabilitation, materials (e.g., self-driving construction machinery to perform repetitive tasks)

Transportation planning demand forecasting, land use (e.g., ML models for estimating mode choice)

1.

Other, please specify: _____________

B5) How satisfied is your agency with the ML applications currently in use? (e.g., in terms of meeting original objectives, producing implementable results, etc.)

• Very satisfied
• Somewhat satisfied
• Not very satisfied
• Not at all satisfied, please explain why ____________________

B6) Please select one of the most widely adopted ML applications that your agency currently uses most often and provide a brief description of the application (please include a hyperlink that can be accessed externally if available):

For the stated ML application above [insert the application name here], please provide the following information:

B6-a) Which one of the following would best characterize the maturity level of this ML application?

• R&D: Application is in the research and development stage.
• Prototype: Application has been tested and is now a prototype
• Production: Application is in production and has been implemented in the field
• Other, please specify: ____________

B6-b) What is the type of input data for this ML application?

• Real-time video or imagery
• Image data (off-line analysis)
• Real-time sensor data _-- (if selected, please specify the sensor type)
• Other, please specify: ___________

B6-c) How long did it take for your agency to fully implement/develop this application?

• Less than 1 year
• 1-2 years
• 2-3 years
• More than 3 years_

B6-d) How long has your agency been using this ML application (in practice for supporting daily operations)?

• Less than 1 year

• o 1-2 years
• 3-4 years
• 5-6 years
• 6-10 years
• More than 10 years

B6-e) The typical users of this application are {check all that apply}

Those within my agency/in-house

The general public

Other state agencies

Private industry

Others, please specify: _______

B6-f) The implementation scale of this ML application:

• Nationwide
• Statewide
• Regional
• Single Site
• Other, please specify: __________

B6-g) What is the estimated annual operating cost for this ML application (the operating cost may include licensing, maintenance, personnel, etc.)?

• <= $50K
• $50K - $100K
• $100K - $200K
• $200K - $300K
• $300K - $400K
• > $400K

B6-h) What are the main benefits of using ML methods for this particular application?

B6-i) What challenges or issues (e.g., institutional, legal, technical, operational, etc.) did your organization face while developing and implementing this ML application? Can you impart any lessons learned?

[Go to question C2]

Part C) Ongoing and future development of ML applications

C1) What ML applications are currently being explored or are under consideration for future implementation by your agency? List as many as possible. [Include an option for none. If none, go to C3.]

C2) What is your agency’s main motivation for considering/using ML methods for developing current and/or future applications?

Processing large amounts of data

Reduction in labor cost

Effectiveness of ML methods compared to traditional methods

Others, please specify: ________

C3) What challenges does your agency foresee in the development and adoption of future ML applications? (Note: We can either ask their ranking of these challenges or ask them to select up to 3 from the list below)

Lack of AI/ML skilled workforce

Stakeholder perception

Data availability

Cost

Lack of dedicated funding

Lack of other resources

Safeguarding the privacy and security of sensitive data

Computational resources

Trustworthiness

Equity and ethical issues

Maturity of ML technology

Others, please specify: _____________

C4) Briefly describe your agency’s vision for adopting ML methods and applications in the near future, if any.

C5) Does your agency have a roadmap for ML adoption? If so, please briefly describe it.

Part D) Please provide your contact information. This information will be used in case the research team needs clarification or has follow-up questions.

► Please enter the name of the public agency/organization you are working for:

► Your Name (optional)

► Your Email Address (optional)

► Job Title (optional)