A neural network travel demand model
Dnr:
NAISS 2024/22-471
Type:
NAISS Small Compute
Principal Investigator:
Joel Fredriksson
Affiliation:
Kungliga Tekniska högskolan
Start Date:
2024-04-02
End Date:
2025-05-01
Primary Classification:
10201: Computer Sciences
Webpage:
Allocation
Abstract
The model is a deep neural network for simulating activity-based travel demand. It is a novel implementation that is able to evaluate 22,009 trip options across various activities, destinations, and transportation modes. It features a Global Context Module that inter-connects all alternatives' evaluations, to dynamically adjust options' attractiveness relative to that of others.