Upload
others
View
4
Download
0
Embed Size (px)
Citation preview
Preparing for today and tomorrow.Michael Pack, CATT Laboratory
.
Pack’s Pointers on how agencies can better prepare for data today and
the unknown(s) of tomorrow.
2
Data is here, and more is coming!!!Trillions of daily measurements transportation from both traditional ITS and emerging CAV technologies.
• Know what’s available?• Effectively integrate data into operations and planning?• Avoid getting burned by bad contract terms and/or over-hyped,
underperforming technologies?• Build or leverage open and trustworthy tools/technologies
But how will agencies…
3
Data alone isn’t the answer.
Data from Everywhere
Big Data
DataProviders
You (and your poor
staff)
• Agencies need:• Policy guidance, • Tools & technologies, • Research & development, and• Thought leadership that helps reduce anxiety and increase big-data capabilities
To prevent this scenario:
5
• Data is only useful when it is• easily accessible, • usable, and • understandableTo managers, planners, operations, and ITS applications…
Invest in Tools to Make Fused Data Easy to work with
To be effective, you need the following:
Data Tools DomainExpertise Insights
Fusion, Statistics,& Integration
Analysis &Visualization
+ + =
Good performance measures are like a really good movie
• They (1) tell a compelling story from beginning to end (2) about a compelling issue, and they (3) make important discoveries/observations along the way.
• There is no single number that can do this!
• You need several key measures that, when combined, point out the state of your system in a meaningful, and easily understood way.
10
Performance Measures = Story Telling
Who is your audience?
Vs.
11
- Engineers- Planners- Operators
- Legislators- Media
- Decision Makers- Public
Data-driven Journalism
DATA
FILTER
VISUALIZE
STORY
Clean, structure and transform
Mine for specific, relevant information
Develop simple charts, graphs and other compelling imagery
Tell the story so the message you want to convey comes across completely, clearly and concisely to your target audience
14
• Right-of-way issues:• Traffic.com sensors
(selling the data back)• Fiber (give me three
strands)
• Connected & Autonomous Vehicles
• Who will own this data?
• We tax and toll (not well)
• We require vehicle registrations and drivers licenses
• Why not require data?!
• If we don’t make headway now, it will be too late….
Federal and State Data Policies and Laws must plan for the future!
6 Heavy Brakingevents
23 Traction ControlEngagements
Red Signal in 2.5 seconds
High % of abnormal freight re-routing
Rollover
Abnormal Fuel Consumption
Fast Wiper Use by 300 vehicles
A day in D.C.—Archived Connected & Autonomous Vehicle Data
16
• Don’t just train Transportation Engineers to do this stuff.
• Hire other skill-sets and teach them about transportation• Data Journalists / Analysts / Data Scientists
• Consultants can do this, too, but….• Think long-term (don’t hire then fire)• Train staff and transfer knowledge
• Partner with Universities (or other similar institutions)
• Invest in Research
Invest in your technical capacity
17
The Big Data movement and fusion is really about enabling technologies• Can do hard things faster & bigger• Integrating Transportation & non Transportation Data sets• Statisticians, data scientists, and visualization experts working with transportation domain
experts• Prediction becomes possible. Planning, Operations, & Public Information become proactive,
not reactive.
The Big Data movement is about more than just data…
“I keep saying that the sexy job in the next 10 years will be statisticians,
and I’m not kidding.” ~ Hal Varian, chief economist at Google, specializing in
microeconomics and information economics.
19
• Blockchain
• Machine Learning
• Artificial Intelligence (AI)
• Business Intelligence
• The Cloud
• Agile
• Etc.
Buzzwords, Shiny Objects, and Peer Pressure
Know what they mean. Don’t confuse them. Understand their relevance. Don’t think they’ll solve all your problems.
Big Data: Savior or Big Fat Tease
Expectations
Time
Innovation Trigger
Peak of InflatedExpectations
Trough ofDisillusionment
Slope of Enlightenment
Plateau ofProductivity
23
• The cloud is EXTREMELY cost effective when you do things the way they want you to do them!
• Don’t assume the cloud will save you money or improve capabilities
• You don’t have to be in the cloud to be effective and innovative
• The cloud should not be used for everything
• The cloud is not “all or nothing”
• Not all clouds are created equally
• Virtualization is not the same thing as cloud computing
The Cloud (hype, sales, or savior?)
25
• Well-intentioned people confuse open source and open data.
• Making institutional investments based on a misunderstanding of terms can have drastic impacts!
• Open Source typically applies to software and applications
• Open Data applies to DATA
Open Data vs. Open Source (there’s a difference!)
26
• Trips and Routing Data
• People Movement Analytics
• ATSPM without Infrastructure
• Connected Vehicle Data without Infrastructure
• Multi-modal Integration
New and Innovative: ITS without Infrastructure
COVID-19 Key Insights U.S. Nation-Wide Daily Multimodal Travel Data for All Travel Modes
27MARYLANDTRANSPORTATIONINSTITUTE
30
• Known Knowns, Known Unknowns, and Unknown Unknowns
• Data isn’t going to get anysmaller.
• Deploying infrastructure will become increasingly less necessary.
• Get your (Current) house in order • Or else the latest and greatest thing won’t matter. • You won’t be ready.
• Tools (should) make some of this easier:• Think of Tableau as the new Excel.
• But that means that expectations are going to go up, too!
• We need to invest together and pool our resources for data management and analytics.
Pack’s Predictions for the Future…
31
• Why???
• The US Transportation System is fragmented!
• No single agency has a complete picture of the system.
• This has implications for • Economic competitiveness• Quality of life• Public safety of citizens• National security
• And up to 50% of all research money is spent on finding/formatting data—that’s a shameful waste!
• Follow the NWS model.
The need for a national data repository
Next steps
32
Thank you!
Michael L. Pack
Director, CATT Laboratory
240.676.4060