Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms
Traffic simulations play a crucial role in urban planning and mobility management by providing insights into transportation systems. However, their effectiveness heavily depends on accurate demand calibration, often requiring large amounts of observational data. This poses a challenge in settings w...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
TIB Open Publishing
2025-07-01
|
| Series: | SUMO Conference Proceedings |
| Subjects: | |
| Online Access: | https://www.tib-op.org/ojs/index.php/scp/article/view/2590 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849720449949237248 |
|---|---|
| author | Jakob Kappenberger Heiner Stuckenschmidt |
| author_facet | Jakob Kappenberger Heiner Stuckenschmidt |
| author_sort | Jakob Kappenberger |
| collection | DOAJ |
| description |
Traffic simulations play a crucial role in urban planning and mobility management by providing insights into transportation systems. However, their effectiveness heavily depends on accurate demand calibration, often requiring large amounts of observational data. This poses a challenge in settings with limited data availability. In this paper, we propose a methodology for calibrating SUMO scenarios under data-scarce conditions. To contextualize our approach, we first review existing SUMO scenarios and their demand calibration strategies. We then introduce the Mannheim SUMO Traffic Model (MaST) as a case study and employ the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to optimize route probabilities as input for the existing routeSampler tool provided by SUMO. Results indicate that our method significantly improves calibration accuracy compared to baseline approaches both for 3-hour and 24-hour scenarios. While our findings suggest that the proposed methodology can support demand calibration in data-limited environments, further research is needed to assess its generalizability and effectiveness in different contexts.
|
| format | Article |
| id | doaj-art-0fcbb69539b74cb0bfbc5a2d6cb02e92 |
| institution | DOAJ |
| issn | 2750-4425 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | TIB Open Publishing |
| record_format | Article |
| series | SUMO Conference Proceedings |
| spelling | doaj-art-0fcbb69539b74cb0bfbc5a2d6cb02e922025-08-20T03:11:55ZengTIB Open PublishingSUMO Conference Proceedings2750-44252025-07-01610.52825/scp.v6i.2590Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary AlgorithmsJakob Kappenberger0Heiner Stuckenschmidt1University of MannheimUniversity of Mannheim Traffic simulations play a crucial role in urban planning and mobility management by providing insights into transportation systems. However, their effectiveness heavily depends on accurate demand calibration, often requiring large amounts of observational data. This poses a challenge in settings with limited data availability. In this paper, we propose a methodology for calibrating SUMO scenarios under data-scarce conditions. To contextualize our approach, we first review existing SUMO scenarios and their demand calibration strategies. We then introduce the Mannheim SUMO Traffic Model (MaST) as a case study and employ the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to optimize route probabilities as input for the existing routeSampler tool provided by SUMO. Results indicate that our method significantly improves calibration accuracy compared to baseline approaches both for 3-hour and 24-hour scenarios. While our findings suggest that the proposed methodology can support demand calibration in data-limited environments, further research is needed to assess its generalizability and effectiveness in different contexts. https://www.tib-op.org/ojs/index.php/scp/article/view/2590Microscopic traffic simulationCalibrationEvolutionary AlgorithmSUMO Simulation Data |
| spellingShingle | Jakob Kappenberger Heiner Stuckenschmidt Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms SUMO Conference Proceedings Microscopic traffic simulation Calibration Evolutionary Algorithm SUMO Simulation Data |
| title | Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms |
| title_full | Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms |
| title_fullStr | Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms |
| title_full_unstemmed | Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms |
| title_short | Overcoming Data Scarcity in Calibrating SUMO Scenarios With Evolutionary Algorithms |
| title_sort | overcoming data scarcity in calibrating sumo scenarios with evolutionary algorithms |
| topic | Microscopic traffic simulation Calibration Evolutionary Algorithm SUMO Simulation Data |
| url | https://www.tib-op.org/ojs/index.php/scp/article/view/2590 |
| work_keys_str_mv | AT jakobkappenberger overcomingdatascarcityincalibratingsumoscenarioswithevolutionaryalgorithms AT heinerstuckenschmidt overcomingdatascarcityincalibratingsumoscenarioswithevolutionaryalgorithms |