Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models
Predicting passenger flow within a city is crucial for intelligent transportation management systems, especially in the context of urban development, post-pandemic policy changes, and infrastructure improvements. Traditional macro models have limitations in accurately capturing the complex structure...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-09-01
|
Series: | Multimodal Transportation |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2772586323000175 |
_version_ | 1797690237882728448 |
---|---|
author | Omkar Parishwad Sida Jiang Kun Gao |
author_facet | Omkar Parishwad Sida Jiang Kun Gao |
author_sort | Omkar Parishwad |
collection | DOAJ |
description | Predicting passenger flow within a city is crucial for intelligent transportation management systems, especially in the context of urban development, post-pandemic policy changes, and infrastructure improvements. Traditional macro models have limitations in accurately capturing the complex structure of real traffic flows, and recent advancements in machine learning offer promising approaches for improving transportation simulations. This research aims to compare the effectiveness of traditional simulation models with a selective machine learning (ML) model for traffic flow prediction in Oslo, Norway. Sensitivity and scenario analyses are conducted to examine the models’ parameters and derive the city’s characteristics. Results substantiate that the traditional Spatial Interaction model (SIM), although interpretable and requiring fewer parameters, has limitations in accurately capturing real flow structures and exhibits greater variability compared to the ML model. Statistical analyses support these findings and raise questions about the validity of the ML model’s results over the SIM. The research highlights the potential of ML models to identify trends in passenger flows and simulate traffic flows in different scenarios related to city development. Overall, the research presents a decision support system for planners and policymakers to predict traffic flow accurately and efficiently. It highlights the benefits and drawbacks of both the traditional SIM and ML models, contributing to the ongoing discussion of the role of machine learning in transportation modeling. |
first_indexed | 2024-03-12T01:56:40Z |
format | Article |
id | doaj.art-ec10643b9d64497c8cee1f4397c024b6 |
institution | Directory Open Access Journal |
issn | 2772-5863 |
language | English |
last_indexed | 2024-03-12T01:56:40Z |
publishDate | 2023-09-01 |
publisher | Elsevier |
record_format | Article |
series | Multimodal Transportation |
spelling | doaj.art-ec10643b9d64497c8cee1f4397c024b62023-09-08T04:34:25ZengElsevierMultimodal Transportation2772-58632023-09-0123100085Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-modelsOmkar Parishwad0Sida Jiang1Kun Gao2Corresponding author at: Chalmers University of Technology, Sweden.; Chalmers Institute of Technology, Architecture and Civil Engineering, Gothenburg, 41296, SwedenWSP,Transport Advisory, Globen, Stockholm, 12188, SwedenChalmers Institute of Technology, Architecture and Civil Engineering, Gothenburg, 41296, SwedenPredicting passenger flow within a city is crucial for intelligent transportation management systems, especially in the context of urban development, post-pandemic policy changes, and infrastructure improvements. Traditional macro models have limitations in accurately capturing the complex structure of real traffic flows, and recent advancements in machine learning offer promising approaches for improving transportation simulations. This research aims to compare the effectiveness of traditional simulation models with a selective machine learning (ML) model for traffic flow prediction in Oslo, Norway. Sensitivity and scenario analyses are conducted to examine the models’ parameters and derive the city’s characteristics. Results substantiate that the traditional Spatial Interaction model (SIM), although interpretable and requiring fewer parameters, has limitations in accurately capturing real flow structures and exhibits greater variability compared to the ML model. Statistical analyses support these findings and raise questions about the validity of the ML model’s results over the SIM. The research highlights the potential of ML models to identify trends in passenger flows and simulate traffic flows in different scenarios related to city development. Overall, the research presents a decision support system for planners and policymakers to predict traffic flow accurately and efficiently. It highlights the benefits and drawbacks of both the traditional SIM and ML models, contributing to the ongoing discussion of the role of machine learning in transportation modeling.http://www.sciencedirect.com/science/article/pii/S2772586323000175Intelligent transportation systemsPassenger flow predictionSpatial interaction modelTraffic simulationSensitivity analysisTransport planning |
spellingShingle | Omkar Parishwad Sida Jiang Kun Gao Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models Multimodal Transportation Intelligent transportation systems Passenger flow prediction Spatial interaction model Traffic simulation Sensitivity analysis Transport planning |
title | Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models |
title_full | Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models |
title_fullStr | Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models |
title_full_unstemmed | Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models |
title_short | Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models |
title_sort | investigating machine learning for simulating urban transport patterns a comparison with traditional macro models |
topic | Intelligent transportation systems Passenger flow prediction Spatial interaction model Traffic simulation Sensitivity analysis Transport planning |
url | http://www.sciencedirect.com/science/article/pii/S2772586323000175 |
work_keys_str_mv | AT omkarparishwad investigatingmachinelearningforsimulatingurbantransportpatternsacomparisonwithtraditionalmacromodels AT sidajiang investigatingmachinelearningforsimulatingurbantransportpatternsacomparisonwithtraditionalmacromodels AT kungao investigatingmachinelearningforsimulatingurbantransportpatternsacomparisonwithtraditionalmacromodels |