Introduction:
Transportation planning is a complex undertaking that requires accurate and reliable data to make the most informed decisions. AirSage, with its industry-leading mobility data, is often approached to explain why their data should be used for travel demand models and other transportation projects. Additionally, the debate between using modeled output or output derived from a synthetic population for a travel demand model arises frequently. In this blog post, we will explore why it is essential to understand the nuances of the inputs in your travel demand model and why black box output is not an appropriate choice for planning.
The Importance of Knowing the Ingredients in Your Data:
As transportation professionals, we understand that details matter. To achieve accurate forecasts for transportation projects, it's crucial to base your model on the behaviors of the actual population rather than relying on someone else's simulated data. Undoubtedly, different people represented in your model do different things, and that's why leveraging a large sample size is indispensable. Using modeled output can only offer insights based on specific potential scenarios and assumptions, such as average vehicle occupancies or predispositions towards carpooling or using alternative modes of transportation.
The Pitfalls of Black Box Output:
Although other mobility data providers may produce comprehensive outputs, it is not recommended to leverage output from one black box as an input for another black box. The challenge lies in explaining the assumptions behind these outputs to constituents or a Council. Without understanding the underlying assumptions, it is challenging, if not impossible, to draw conclusions about what motivates people to choose specific modes of transportation and when to make a trip.
Unveiling the Unique Characteristics of Different Communities:
We know that residents of different neighborhoods have varying tendencies to use non-auto modes of transportation, and certain people make trips at specific times or days compared to others. These intricate details get lost when relying on modeled output as an input for understanding how people conduct trips in your travel demand model. By blindly accepting these outputs as ground-truth, we fail to acknowledge that the output is merely various representations of what someone else perceives as reality. Moreover, the people that produce these outputs often lack the localized knowledge that transportation planners and consultants possess, which hinders the output accuracy.
The Need to Show Our Math:
Transportation planners have a responsibility to credibly demonstrate transparency and confidence in the data and conclusions they present. In public hearings, it is necessary to explain the elements that went into the planning process before drawing conclusions and making recommendations. Responding with, "this is what the output says" is insufficient. Professionals must delve into the nuances of the details and methodologies behind their conclusions, valuing datasets differently and providing a higher level of confidence in their recommendations. After all, recommendations for transportation improvements are costly and rely on tax-payer dollars.
Conclusion:
When it comes to transportation planning, understanding your data is paramount. AirSage's industry-leading mobility data offers the opportunity to understand transportation behaviors and patterns accurately, enabling better informed decision-making. Avoiding black box output and synthetic populations ensures that your travel demand model incorporates the unique characteristics of your actual population. By "showing your math" and explaining the intricacies of the planning process, transportation professionals can provide reliable recommendations based on real-world insights. Choose transparency, accuracy, and confidence by using AirSage data for your transportation projects.
