A neural network travel demand model

A neural network travel demand model - LSTM implementation

SUPR uses JavaScript for certain functions. We cannot guarantee that you will be able to use the system with JavaScript disabled.

Dnr:

NAISS 2025/22-702

Type:

NAISS Small Compute

Principal Investigator:

Joel Fredriksson

Affiliation:

Kungliga Tekniska högskolan

Start Date:

2025-05-05

End Date:

2026-06-01

Primary Classification:

10201: Computer Sciences

Webpage:

Allocation

Alvis at C3SE: 500 GPU-h/month
Mimer at C3SE: 500 GiB

Abstract

The model to be developed 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. Furthermore, it adds a LSTM to remember previous actions that the agent has taken earlier the same day.