Back to Research Areas

Traffic Forecasting

Traffic forecasting applies machine learning and deep learning techniques to accurately predict future traffic conditions, helping cities reduce congestion and improve daily travel for everyone. Traffic forecasting is about using smart technology like machine learning and deep learning to predict traffic patterns before they happen. By analyzing data from sensors, GPS, and historical trends, these methods can forecast where traffic will be heavy and when, making it easier to plan for smoother, faster commutes. Also, these predictions help cities manage traffic more efficiently, cut down on delays, and improve road safety, while also enabling real-time decision-making to prevent congestion. As cities get smarter and technology advances, traffic forecasting continues to improve, offering more accurate estimations and valuable insights into the road networks’ mechanics and spatiotemporal relations that benefit everyone on the road.

Traffic Forecasting

More on this topic

Projects

Publications

From Travel Times to Lane-Based Hourly Traffic Flow: An Explainable Machine Learning Framework

Revisiting the Non-recurrent Traffic Incident Identification Problem for Real-Time Applications Using Theory-Aware Unsupervised Learning

Quantum neural networks with data re-uploading for urban traffic time series forecasting

A theory-informed multivariate causal framework for trustworthy short-term urban traffic forecasting

Traffic demand prediction using a social multiplex networks representation on a multimodal and multisource dataset

Urban Arterial Traffic Volume and Travel Time Estimation with Use of Data Driven Models

Unlocking the full potential of deep learning in traffic forecasting through road network representations: A critical review

A Causal Deep Learning Framework for Traffic Forecasting

Efficient Traffic Demand Forecasting Using A Meaningful Representation With Social Multiplex Networks and Community Detection

Methodological framework of creating the Levitate Policy Support Tool for Connected and Automated Transport Systems

Dilated LSTM networks for short-term traffic forecasting using network-wide vehicle trajectory data

Road traffic forecasting: Recent advances and new challenges

Optimization of traffic forecasting: Intelligent surrogate modeling

Improving short-term traffic forecasts: To combine models or not to combine?

Short-term traffic forecasting: Where we are and where we’re going

Testing and comparing neural network and statistical approaches for predicting transportation time series

Temporal aggregation in traffic data: implications for statistical characteristics and model choice

Comparing traffic flow time-series under fine and adverse weather conditions using recurrence-based complexity measures

Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?

Enhancing predictions in signalized arterials with information on short-term traffic flow dynamics

Temporal evolution of short‐term urban traffic flow: a nonlinear dynamics approach

Spatio‐temporal short‐term urban traffic volume forecasting using genetically optimized modular networks

Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume

Pattern-based short-term urban traffic predictor

Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach

Short‐term traffic forecasting: Overview of objectives and methods

PHD Theses

Traffic Theory Inspired Spatiotemporal and Multimodal Deep Learning Models for Trustworthy Short-Term Urban Traffic Forecasting

News

General Assembly of the ACUMEN EU project, Luxembourg 🇱🇺

The 9th IEEE Conference on MT-ITS, Luxembourg 🇱🇺

Kick-off of the FEDORA EU project, Brussels 🇧🇪

Artificial Intelligence for Road Safety and Mobility Workshop, May 2025, Athens 🇬🇷