Back to search

IKTPLUSS-IKT og digital innovasjon

Machine learning for computational efficient predictions of long-term congestion patterns in large-scale transport systems

Alternative title: Maskinlæring for beregningseffektive prediksjoner av langsiktige kømønstre i store transportsystemer

Awarded: NOK 12.0 mill.

Delays, lost leisure time, increased air pollution: Traffic jams are a source of significant socio-economic costs for companies and individuals in Norway, especially in the Oslo area. Urban planners need tools to evaluate where investments in road capacity are most effective in reducing traffic jams. A challenge with current tools (so-called strategic transport models) is that only highly specialized professionals can use them and that the calculation time can be up to several days. In this project, we aim to build a new type of prediction tool. Our tool will be based on machine learning. In order to be able to apply machine learning for long-term predictions, we have to train the model on data where population and road capacity vary. Our idea is to establish such training data based on agent-based traffic simulation models. The tool will be available open-access and it is expected to be much faster and much more user-friendly than current transport models. We will start up in August 2021 and plan to conclude in August 2025. The project is a collaboration between the Institute of Transport Economics, the University of Bergen (UiB), the Swedish National Road and Transport Institute, the AI-company Epigram AS, as well as the Norwegian Public Road Administration. Our project includes a PhD-project at the department of informatics at UiB.

PRELONG puts forward artificial intelligence (AI), in the form of machine learning, as an accessible and capable method to predict long-term outcomes and performances of large-scale transport systems. PRELONG will showcase the capability of AI to reliably predict effects of interventions to the transport systems (as road capacity increases and changes to the road toll structure) and that much faster (in a few seconds) than current transport models. Fast computation times and easy access are potential game changers in how we utilize transport models for effective transport planning. The overall data flow includes 1) Establishing synthetic travel populations 2) Run agent-based traffic simulations and iteratively calibrate underlying parameters in the simulator c) Train a binarized DNN on the simulated traffic data d) Implement the trained DNN within an open-access and user-friendly GIS-based sketch planning tool. The scenarios of the multiple runs with the traffic simulator (MATSim) will be careful predefined by an experimental design varying a) road toll structure b) speed limit c) road capacity on single road network links d) population in different zones in the Oslo metropolitan area. To ground DNN predictions to the empirical real world, we calibrate the detailed traffic simulator against real data. This enables the simulator to credibly predict a wide range of future scenarios at a high level of resolution. These simulator predictions are then used to train a neural network that can quickly approximate complex future scenarios in a sketch planning setup. We plan to use binarized neural networks analysed and interpreted using an exact encoding into propositional logic. PRELONG is a collaboration between the Institute of Transport Economics, the Department of Informatics at the University of Bergen, the Swedish National Road and Transport Institute, the AI-company Epigram AS, as well as the Norwegian Public Road Administration.

Activity:

IKTPLUSS-IKT og digital innovasjon