Skip to content

How Can Digitization in the Private Sector Benefit Everyone?

Publication: Goods Movement 2030: An Urban Freight Blog
Publication Date: 2023

We’ve dug into how digitization continues to spark new developments in the urban freight landscape across the private and public sectors alike — with cities lagging behind digitization veterans like Amazon.

As Urban Freight Lab members noted at the fall meeting, it’s understandable why the private sector is ahead. Digitization helps companies improve operations toward lowering costs, saving time and money, and keeping customers satisfied. In other words, digitization helps companies with their fundamental concern: The bottom line.

And yet, companies’ choices and behavior in using digital tools can have the effect of helping more than their bottom lines. Private sector digitization can have spillover benefits, winding up helping communities and society at large, too. (To be clear, when we talk here about societal benefits, that includes mitigating and/or reducing the negative impacts of delivering goods to our homes and businesses.) But too often we treat the private and public sectors as wholly separate and siloed systems — though clearly they’re not.

The efficiencies digitization supports in urban freight might well wind up contributing to quality of life in city neighborhoods and communities. Those efficiencies can impact everything from congestion and traffic flow to pollution and Co2 emissions that contribute to climate change.

In this blog, we map three digitization moves in the private sector that could generate benefits for the public.

Recommended Citation:
"How Can Digitization in the Private Sector Benefit Everyone?" Goods Movement 2030 (blog). Urban Freight Lab, February 14, 2023.

Physics-Informed Machine Learning of Parameterized Fundamental Diagrams

Download PDF  (2.10 MB)
Publication: arXiv
Volume: 2208.0088
Publication Date: 2022

Fundamental diagrams describe the relationship between speed, flow, and density for some roadway (or set of roadway) configuration(s). These diagrams typically do not reflect, however, information on how speed-flow relationships change as a function of exogenous variables such as curb configuration, weather or other exogenous, contextual information. In this paper we present a machine learning methodology that respects known engineering constraints and physical laws of roadway flux–those that are captured in fundamental diagrams– and show how this can be used to introduce contextual information into the generation of these diagrams. The modeling task is formulated as a probe vehicle trajectory reconstruction problem with Neural Ordinary Differential Equations (Neural ODEs). With the presented methodology, we extend the fundamental diagram to non-idealized roadway segments with potentially obstructed traffic data. For simulated data, we generalize this relationship by introducing contextual information at the learning stage, i.e. vehicle composition, driver behavior, curb zoning configuration, etc, and show how the speed-flow relationship changes as a function of these exogenous factors independent of roadway design.

Authors: Thomas MaxnerDr. Andisheh Ranjbari, James Koch, Vinay Amatya, Chase Dowling
Recommended Citation:
Koch, J., Maxner, T., Amatya, V.C., Ranjbari, A., & Dowling, C.P. (2022). Physics-informed Machine Learning of Parameterized Fundamental Diagrams.