Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach

Ayşin Ceren Arslan; Merve Ozkan; Kürşat Yıldız

doi:10.17798/bitlisfen.1848616

Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach

Abstract

Autonomous vehicle technologies are reshaping traffic safety and urban mobility; however, software and sensor failures, legal uncertainties, and mixed traffic environments continue to pose significant accident risks. Recent fatal incidents during real-world testing underline the critical need for effective risk prediction approaches. While existing studies mainly focus on accident causes and probabilities, deep learning research is often limited to in-vehicle sensor data. This study proposes a hybrid framework integrating machine learning and deep learning models with Geographic Information Systems (GIS)-based spatial analysis to predict both the occurrence and severity of autonomous vehicle accidents and to identify high-risk locations and conditions. The results show that Support Vector Machine (SVM) and Artificial Neural Network (ANN) models perform effectively in accident severity prediction, while ANN achieves superior performance in accident occurrence prediction under balanced data conditions. The proposed approach offers a data-driven basis for risk-aware route planning and dynamic safety management in intelligent transportation systems.

Keywords

Supporting Institution

The authors received no financial or institutional support for this study.

Ethical Statement

Ethical approval was not required for this study as it was based on anonymized secondary data and did not involve human or animal subjects.

Thanks

The author would like to express sincere gratitude to the thesis advisors for their continuous support, insightful comments, and academic guidance during the preparation of this study.

References

S. Bayındır, “Autonomous driving systems and their applications,” Journal of Intelligent Transportation, 2021.
L. Chen, “AI-driven perception systems in autonomous driving,” IEEE Transactions on Intelligent Vehicles, 2020.
SAE International, Taxonomy and Definitions for Terms Related to Driving Automation Systems (SAE J3016), 2021.
J. M. Anderson, N. Kalra, K. D. Stanley, P. Sorensen, C. Samaras, and O. A. Oluwatola, Autonomous Vehicle Technology: A Guide for Policymakers. Santa Monica, CA, USA: RAND Corporation, 2016.
National Highway Traffic Safety Administration, Autonomous Vehicle Crash Reports Summary. U.S. Department of Transportation, 2024.
B. Ren, H. Liu, and X. Zhao, “Failure analysis of autonomous vehicle perception systems,” Journal of Automotive Safety, 2021.
M. Bulut, “Machine learning-based crash prediction models for autonomous vehicles,” Transportation Safety Review, 2024.
S. Pour, M. Ahmed, and J. Lee, “Crash prediction using multi-model machine learning approaches,” Accident Analysis & Prevention, 2022.

T. Endashaw, “Spatial patterns of autonomous vehicle crashes using GIS-based clustering,” International Journal of Urban Mobility, 2025.
A. Ulu, “Geographical distribution of autonomous vehicle crashes: A spatial analysis,” Urban Computing Journal, 2024.
A. Mimi et al., “Hybrid GIS and machine learning frameworks for crash hotspot detection,” Journal of Geospatial Analysis, 2025.
R. Singh, “GIS-based safe routing strategies for autonomous vehicles,” Smart Mobility Letters, 2025.
Q. Jiao, Y. Zhang, and L. Han, “Spatial–machine learning integration for traffic risk prediction,” Sensors and Autonomous Systems, 2025.
D. J. Fagnant and K. Kockelman, “Preparing a nation for autonomous vehicles: Opportunities, barriers and policy recommendations,” Transportation Research Part A: Policy and Practice, vol. 77, pp. 167–181, 2015.
National Highway Traffic Safety Administration, Automated Vehicles Crash Report. U.S. Department of Transportation, 2024.
H. Zhou, H. Xu, C. Zhang, and Y. Wang, “Traffic accident prediction using machine learning: A survey and analysis,” IEEE Access, vol. 9, pp. 42363–42381, 2021.
S. Grigorescu, B. Trasnea, T. Cocias, and G. Macesanu, “A survey of deep learning techniques for autonomous driving,” Journal of Field Robotics, vol. 37, no. 3, pp. 362–386, 2020.
K. Xie and X. Yan, “Detecting traffic accident clusters with network kernel density estimation and local spatial statistics: An integrated approach,” Journal of Transport Geography, vol. 31, pp. 64–71, 2013.
E. W. Dijkstra, “A note on two problems in connexion with graphs,” Numerische Mathematik, vol. 1, pp. 269–271, 1959.
Y. L. Chen and H. H. Yang, “Finding the first K shortest paths in a time window network,” Computers and Operations Research, vol. 31, no. 4, pp. 499–513, 2004.
B. W. Silverman, Density Estimation for Statistics and Data Analysis. Chapman and Hall, 1986.
T. K. Anderson, “Kernel density estimation and K-means clustering to profile road accident hotspots,” Accident Analysis & Prevention, vol. 41, no. 3, pp. 359–364, 2009.
M. Abdel-Aty, C. Lee, C. Siddiqui, and K. Choi, “Real-time crash risk assessment using traffic data,” Transportation Research Record, vol. 2237, pp. 45–54, 2013.
C. Wang, M. Quddus, and S. Ison, “The effect of traffic and road characteristics on road safety: A review and future research direction,” Safety Science, vol. 75, pp. 43–55, 2015.
L. Y. Chang, “Analysis of freeway accident frequencies using artificial neural networks,” Safety Science, vol. 43, no. 8, pp. 541–559, 2005.

Details

Primary Language

English

Subjects

Transportation and Traffic, Geographical Information Systems (GIS) in Planning

Journal Section

Research Article

Authors

Ayşin Ceren Arslan ^*
0009-0008-3001-221X
Türkiye

Merve Ozkan
0000-0002-1071-2541
Türkiye

Kürşat Yıldız
0000-0003-2205-9997
Türkiye

Publication Date

September 30, 2026

Submission Date

December 24, 2025

Acceptance Date

July 1, 2026

Published in Issue

Year 2026 Volume: 15 Number: 3

DOI

https://doi.org/10.17798/bitlisfen.1848616

IZ

https://izlik.org/JA66XY87NX

Cite

RIS / Bibtex

APA

Arslan, A. C., Ozkan, M., & Yıldız, K. (2026). Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 15(3), 1082-1095. https://doi.org/10.17798/bitlisfen.1848616

AMA

1.Arslan AC, Ozkan M, Yıldız K. Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2026;15(3):1082-1095. doi:10.17798/bitlisfen.1848616

Chicago

Arslan, Ayşin Ceren, Merve Ozkan, and Kürşat Yıldız. 2026. “Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 15 (3): 1082-95. https://doi.org/10.17798/bitlisfen.1848616.

EndNote

Arslan AC, Ozkan M, Yıldız K (September 1, 2026) Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 15 3 1082–1095.

IEEE

[1]A. C. Arslan, M. Ozkan, and K. Yıldız, “Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach”, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 15, no. 3, pp. 1082–1095, Sept. 2026, doi: 10.17798/bitlisfen.1848616.

ISNAD

Arslan, Ayşin Ceren - Ozkan, Merve - Yıldız, Kürşat. “Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 15/3 (September 1, 2026): 1082-1095. https://doi.org/10.17798/bitlisfen.1848616.

JAMA

1.Arslan AC, Ozkan M, Yıldız K. Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2026;15:1082–1095.

MLA

Arslan, Ayşin Ceren, et al. “Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach”. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 15, no. 3, Sept. 2026, pp. 1082-95, doi:10.17798/bitlisfen.1848616.

Vancouver

1.Ayşin Ceren Arslan, Merve Ozkan, Kürşat Yıldız. Spatial Prediction And Safe Route Optimization of Autonomous Vehicle Accidents: Machine Learning And Gis-Based Integrated Approach. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi. 2026 Sep. 1;15(3):1082-95. doi:10.17798/bitlisfen.1848616