arXiv subjects

Serio Agriesti

Publications and source records attributed to Serio Agriesti.

6 recordsLinked to original sources

arXiv2026

Learning to Learn the Macroscopic Fundamental Diagram using Physics-Informed and meta Machine Learning techniques

The Macroscopic Fundamental Diagram is a popular tool used to describe traffic dynamics in an aggregated way, with applications ranging from traffic control to incident analysis. However, estimating the MFD for a given network requires large numbers of loop detectors, which is not always available in practise. This article proposes a framework to alleviate the data scarcity challenge harnessing Meta-Learning, a subcategory of Machine Learning that trains models to understand and adapt to new tasks on their own. We use Meta-Learning to identify and exploit transferable patterns from data-rich cities to cities where not enough data is available to estimate the MFD. The developed model is trained and tested by leveraging data from multiple cities and exploiting it to model the MFD of other cities with different shares of detectors and topological structures. The proposed Meta-Learning framework is applied to an ad-hoc Multi-Task Physics-Informed Neural Network, specifically designed to estimate the MFD. Results show an average MAE improvement in flow prediction of around 50% across cities (depending on the subset of loop detectors tested). The Meta-Learning framework thus successfully generalises across diverse urban settings and improves performance on cities with limited data, demonstrating the potential of using Meta-Learning when a limited number of detectors is available. We directly test this assumption by applying the Meta-Learning outputs to unseen cities to simulate a real-life application scenario and the wide applicability of the proposed methodology. Finally, the proposed framework is validated against traditional Transfer Learning approaches and tested with FitFun, a model for FD estimation from the literature, to prove its transferability.

cs.LG↗

arXiv2026

Metalearning traffic assignment for network disruptions with graph convolutional neural networks

Building machine-learning models for estimating traffic flows from OD matrices requires an appropriate design of the training process and a training dataset spanning over multiple regimes and dynamics. As machine-learning models rely heavily on historical data, their predictions are typically accurate only when future traffic patterns resemble those observed during training. However, their performance often degrades when there is a significant statistical discrepancy between historical and future conditions. This issue is particularly relevant in traffic forecasting when predictions are required for modified versions of the network, where the underlying graph structure changes due to events such as maintenance, public demonstrations, flooding, or other extreme disruptions. Ironically, these are precisely the situations in which reliable traffic predictions are most needed. In the presented work, we combine a machine-learning model (graph convolutional neural network) with a meta-learning architecture to train the former to quickly adapt to new graph structures and demand patterns, so that it may easily be applied to scenarios in which changes in the road network (the graph) and the demand (the node features) happen simultaneously. Our results show that the use of meta-learning allows the graph neural network to quickly adapt to unseen graphs (network closures) and OD matrixes while easing the burden of designing a training dataset that covers all relevant patterns for the practitioners. The proposed architecture achieves a R^2 of around 0.85 over unseen closures and OD matrixes.

cs.LG↗

arXiv2025

Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment

The Traffic Assignment Problem is a fundamental, yet computationally expensive, task in transportation modeling, especially for large-scale networks. Traditional methods require iterative simulations to reach equilibrium, making real-time or large-scale scenario analysis challenging. In this paper, we propose a learning-based approach using Message-Passing Neural Networks as a metamodel to approximate the equilibrium flow of the Stochastic User Equilibrium assignment. Our model is designed to mimic the algorithmic structure used in conventional traffic simulators allowing it to better capture the underlying process rather than just the data. We benchmark it against other conventional deep learning techniques and evaluate the model's robustness by testing its ability to predict traffic flows on input data outside the domain on which it was trained. This approach offers a promising solution for accelerating out-of-distribution scenario assessments, reducing computational costs in large-scale transportation planning, and enabling real-time decision-making.

cs.LG↗

arXiv2024

An equilibrium-seeking search algorithm for integrating large-scale activity-based and dynamic traffic assignment models

This paper proposes an iterative methodology to integrate large-scale behavioral activity-based models with dynamic traffic assignment models. The main novelty of the proposed approach is the decoupling of the two parts, allowing the ex-post integration of any existing model as long as certain assumptions are satisfied. A measure of error is defined to characterize a search space easily explorable within its boundaries. Within it, a joint distribution of the number of trips and travel times is identified as the equilibrium distribution, i.e., the distribution for which trip numbers and travel times are bound in the neighborhood of the equilibrium between supply and demand. The approach is tested on a medium-sized city of 400,000 inhabitants and the results suggest that the proposed iterative approach does perform well, reaching equilibrium between demand and supply in a limited number of iterations thanks to its perturbation techniques. Overall, 15 iterations are needed to reach values of the measure of error lower than 10%. The equilibrium identified this way is then validated against baseline distributions to demonstrate the goodness of the results.

cs.CY↗

arXiv2023

A Bayesian Optimization approach for calibrating large-scale activity-based transport models

The use of Agent-Based and Activity-Based modeling in transportation is rising due to the capability of addressing complex applications such as disruptive trends (e.g., remote working and automation) or the design and assessment of disaggregated management strategies. Still, the broad adoption of large-scale disaggregate models is not materializing due to the inherently high complexity and computational needs. Activity-based models focused on behavioral theory, for example, may involve hundreds of parameters that need to be calibrated to match the detailed socio-economical characteristics of the population for any case study. This paper tackles this issue by proposing a novel Bayesian Optimization approach incorporating a surrogate model in the form of an improved Random Forest, designed to automate the calibration process of the behavioral parameters. The proposed method is tested on a case study for the city of Tallinn, Estonia, where the model to be calibrated consists of 477 behavioral parameters, using the SimMobility MT software. Satisfactory performance is achieved in the major indicators defined for the calibration process: the error for the overall number of trips is equal to 4% and the average error in the OD matrix is 15.92 vehicles per day.

cs.LG↗

arXiv2021

Assignment of a Synthetic Population for Activity-based Modelling employing Publicly Available Data

Agent based modelling has acquired the spotlight in the transportation domain both in scientific literature and in real life applications, thanks to its capability to deal with the ever-growing complexity of transportation systems, including future disrupting mobility technologies and services such as automated driving, Mobility as a Service, and micromobility. Different software emerged, dedicated to the simulation of disaggregate travel demand framing individual choices based on the profile of each agent. Still, the actual research work exploiting these models is scarce and the professionals with the knowledge to use them are few. This may be ascribed to the large amount of needed input data or to a lack of commercial solutions and of research production detailing the process leading to the actual simulations. In this paper, a methodology to spatially assign a synthetic population by exploiting publicly available aggregate data is presented and implemented on a case study. In doing so, the paper provides a systematic approach for a quick and efficient treatment of the data needed for activity-based demand generation. Finally, the obtained dataset, representing a synthetic population of the city of Tallinn, Estonia, and its spatial assignment, is described so that it may be exploited by fellow researchers, since both the tools needed for spatial assignment and the resulting dataset are made available as open source.

stat.AP↗