Calibrating adaptive smoothing methods for freeway traffic reconstruction

2026/02/02 by Junyi Ji, Derek Gloudemans, Gergely Zachár +4
Engineering · #Air Traffic Management and Optimization #Traffic Prediction and Management Techniques #Traffic control and management #cs.LG

paper · pdf · doi:10.1186/s12544-026-00818-0

openalex publication_date 2026/07/16 · openalex created_date 2026/07/17 · openalex updated_date 2026/07/31

Abstract

The adaptive smoothing method (ASM) is a widely used approach for traffic state reconstruction. This article presents a Python implementation of ASM, featuring end-to-end calibration using real-world ground truth data. The calibration is formulated as a parameterized kernel optimization problem. The model is calibrated using data from a full-state observation testbed, with input from a sparse radar sensor network. The implementation is developed in PyTorch, enabling integration with various deep learning methods. We evaluate the results in terms of speed distribution, spatio-temporal error distribution, and spatial error to provide benchmark metrics for the traffic reconstruction problem. We further demonstrate the usability of the calibrated method across multiple freeways. This article is reproducible and can serve as a benchmark for various freeway operation tasks.

Citations

• Real-World Deployment and Assessment of a Multi-Agent Reinforcement Learning-Based Variable Speed Limit Control System
• Efficient and Robust Freeway Traffic Speed Estimation under Oblique Grid using Vehicle Trajectory Data
• Scalable analysis of stop-and-go waves: Representation, measurements and insights
• Stop-and-go wave super-resolution reconstruction via iterative refinement
• FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
• Virtual trajectories for I-24 MOTION: data and tools
• A Macro-Micro Approach to Reconstructing Vehicle Trajectories on Multi-Lane Freeways with Lane Changing
• Traffic State Estimation from Vehicle Trajectories with Anisotropic Gaussian Processes
• I-24 MOTION: An instrument for freeway traffic science
• Reproducibility in Optimization: Theoretical Framework and Limits
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Adam: A Method for Stochastic Optimization
• Congested traffic states in empirical observations and microscopic simulations
• Multistep traffic forecasting by dynamic graph convolution: Interpretations of real-time spatial correlations

Related

• An adaptive smoothing method for traffic state identification from incomplete information
• Physics-informed Machine Learning for Calibrating Macroscopic Traffic Flow Models
• Stop-and-go wave super-resolution reconstruction via iterative refinement
• Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approach
• Learning-based Traffic State Reconstruction using Probe Vehicles