Next Article in Journal
Mapping Spatiotemporal Diffusion of COVID-19 in Lombardy (Italy) on the Base of Emergency Medical Services Activities
Next Article in Special Issue
An Unsupervised Crop Classification Method Based on Principal Components Isometric Binning
Previous Article in Journal
Multiple Global Population Datasets: Differences and Spatial Distribution Characteristics
Previous Article in Special Issue
Dual Path Attention Net for Remote Sensing Semantic Image Segmentation
Article

Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data

1
Institute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology, 76131 Karlsruhe, Germany
2
ci-Tec GmbH, 76137 Karlsruhe, Germany
*
Author to whom correspondence should be addressed.
ISPRS Int. J. Geo-Inf. 2020, 9(11), 638; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9110638
Received: 3 September 2020 / Revised: 15 October 2020 / Accepted: 21 October 2020 / Published: 27 October 2020
(This article belongs to the Special Issue Geospatial Artificial Intelligence)
Average speed information, which is essential for routing applications, is often missing in the freely available OpenStreetMap (OSM) road network. In this contribution, we propose an estimation framework, including different machine learning (ML) models that estimate rural roads’ average speed based on current road information in OSM. We rely on three datasets covering two regions in Chile and Australia. Google Directions API data serves as reference data. An appropriate estimation framework is presented, which involves supervised ML models, unsupervised clustering, and dimensionality reduction to generate new input features. The regression performance of each model with different input feature modes is evaluated on each dataset. The best performing model results in a coefficient of determination R2=80.43%, which is significantly better than previous approaches relying on domain-knowledge. Overall, the potential of the ML-based estimation framework to estimate the average speed with OSM road network data is demonstrated. This ML-based approach is data-driven and does not require any domain knowledge. In the future, we intend to focus on the generalization ability of the estimation framework concerning its application in different regions worldwide. The implementation of our estimation framework for an exemplary dataset is provided on GitHub. View Full-Text
Keywords: machine learning; regression; OpenStreetMap; volunteered geographical information; supervised learning; unsupervised learning; Self-Organizing Maps; estimation framework; average speed machine learning; regression; OpenStreetMap; volunteered geographical information; supervised learning; unsupervised learning; Self-Organizing Maps; estimation framework; average speed
Show Figures

Figure 1

MDPI and ACS Style

Keller, S.; Gabriel, R.; Guth, J. Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data. ISPRS Int. J. Geo-Inf. 2020, 9, 638. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9110638

AMA Style

Keller S, Gabriel R, Guth J. Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data. ISPRS International Journal of Geo-Information. 2020; 9(11):638. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9110638

Chicago/Turabian Style

Keller, Sina, Raoul Gabriel, and Johanna Guth. 2020. "Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data" ISPRS International Journal of Geo-Information 9, no. 11: 638. https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9110638

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop