Neural-Network-Based Calibration of Macroscopic Traffic Flow Models

Akwir, Nkiediel Alain; Chedjou, Jean Chamberlain; Kyamakya, Kyandoghere

doi:10.1007/978-3-319-58996-1_7

Cited by 4 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To provide physical baselines for the performance comparison, the LWR, PW, ARZ models are calibrated with the obtained field data. For model calibration, we follow the method by Akwir et al (2018), where the hybrid scheme of neural network and nonlinear partial differential equation is used to dynamically adjust all outputs of the three models to obtain their calibrated parameters. Figs 10-11 plot the estimated flow and speed from the three physical models versus the ground truth.…”

Section: Comparison With Physical Models (Traffic Flow Models)mentioning

confidence: 99%

Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation

Yuan

Zhang

Yang

et al. 2021

Transportation Research Part B: Methodological

View full text Add to dashboard Cite

Section: Comparison With Physical Models (Traffic Flow Models)mentioning

confidence: 99%

Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation

Yuan

Zhang

Yang

et al. 2021

Transportation Research Part B: Methodological

View full text Add to dashboard Cite

“…GA can be applied to solve a variety of optimization problems that are not well suited for standard optimization algorithms, including problems, in which the objective function is discontinuous, non-differentiable, stochastic, or highly nonlinear [2]. Procedures involved in a GA can be summarized in 6 steps that are as follows:…”

Section: Calibration Using a Combined Objective Function And Genetic mentioning

confidence: 99%

“…Hydrological models are important for monitoring, planning, and managing water resources. Their development is 2 School of Earth and Ocean Sciences, Cardiff University, Cardiff, UK 3 School of Geographical Sciences University of Bristol, Bristol, UK required to better understand natural processes and assess changes in the water cycle, and their response to climate change and anthropogenic modifications. From a mathematical point of view, hydrological modeling is the process of describing and quantifying a "real-world system" on the basis of forcing and input data, model parameters, and their initial values [31].…”

Section: Introductionmentioning

confidence: 99%

Comparing multi-objective optimization techniques to calibrate a conceptual hydrological model using in situ runoff and daily GRACE data

et al. 2018

View full text Add to dashboard Cite

Hydrological models are necessary tools for simulating the water cycle and for understanding changes in water resources. To achieve realistic model simulation results, real-world observations are used to determine model parameters within a "calibration" procedure. Optimization techniques are usually applied in the model calibration step, which assures a maximum similarity between model outputs and observations. Practical experiences of hydrological model calibration have shown that single-objective approaches might not be adequate to tune different aspects of model simulations. These limitations can be as a result of (i) using observations that do not sufficiently represent the dynamics of the water cycle, and/or (ii) due to restricted efficiency of the applied calibration techniques. To address (i), we assess how adding daily Total Water Storage (dTWS) changes derived from the Gravity Recovery And Climate Experiment (GRACE) as an extra observations, besides the traditionally used runoff data, improves calibration of a simple 4-parameter conceptual hydrological model (GR4J, in French: modèle du Génie Ruralà 4 paramètres Journalier) within the Danube River Basin. As selecting a proper calibration approach (in ii) is a challenging task and might have significant influence on the quality of model simulations, for the first time, four evolutionary optimization techniques, including the Non-dominated Sorting Genetic Algorithm II (NSGA-II), the Multi-objective Particle Swarm Optimization (MPSO), the Pareto Envelope-Based Selection Algorithm II (PESA-II), and the Strength Pareto Evolutionary Algorithm II (SPEA-II) along with the Combined objective function and Genetic Algorithm (CGA) are tested to calibrate the model in (i). A number of quality measures are applied to assess cardinality, accuracy, and diversity of solutions, which include the Number of Pareto Solutions (NPS), Generation Distance (GD), Spacing (SP), and Maximum Spread (MS). Our results indicate that according to MS and SP, NSGA-II performs better than other techniques for calibrating GR4J using GRACE dTWS and in situ runoff data. Considering GD as a measure of efficiency, MPSO is found to be the best technique. CGA is found to be an efficient method, while considering the statistics of the GR4J's 4 calibrated parameters to rank the optimization techniques. The Nash-Sutcliffe model efficiency coefficient is also used to assess the predictive power of the calibrated hydrological models, for which our results indicate satisfactory performance of the assessed calibration experiments.

show abstract

“…These advances allow the learning process to be regularized with the information contained in the differential equations of the physical system. As traffic flow dynamics can be described by differential equations, these new insights were applied to TSE [20]- [23] and it was shown that they can outperform comparable conventional methods in performance [24], [25]. Also, the fusion of LDD and FCD can be further improved using physics-informed TSE [26].…”

Section: Introductionmentioning

confidence: 99%

Traffic State Estimation with Loss Constraint

Dahmen

Loder

Tilg

et al. 2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

Traffic state estimation is relevant for real-time traffic control, providing travel information as well as for expost analysis of traffic patterns. While the output is usually the average speed and vehicle flow along street segments, the type of input data and the existing methods to obtain the output are diverse. Recently, physics-informed data-driven approaches started to emerge that enrich the estimation process with information taken from physical models. In traffic, so far, these have been the continuity equation and the fundamental diagram, designed to describe fully the traffic dynamics along links and corridors. In this paper, we propose a simpler and practiceready physics-informed machine learning approach that informs the estimation through the well-established fundamental diagram in a loss constraint. It is designed for a link-level analysis where traffic homogeneity along the considered link is assumed. We apply the proposed method to full-trajectory drone data from Athens, Greece, demonstrate the applicability of our proposed approach, and point out its potential to future applications, e.g., a filter for control algorithms.*Allister Loder further acknowledges the support from the German Federal Ministry for Digital and Transport for the funding of the project TEM-PUS, grant no. 01MM20008K. Data source: open-traffic.epfl.ch (pNEUMA)

show abstract

Neural-Network-Based Calibration of Macroscopic Traffic Flow Models

Cited by 4 publications

References 35 publications

Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation

Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation

Comparing multi-objective optimization techniques to calibrate a conceptual hydrological model using in situ runoff and daily GRACE data

Traffic State Estimation with Loss Constraint

Contact Info

Product

Resources

About