Temperature ranking method for spatio-temporal road accident clusters to prioritize urban black spots

Introduction. The relevance of the study is due to the need to shift from the cumulative road traffic accidents (RTAs) tracking to dynamic assessment methods that can identify points with the highest risk for targeted resource allocation. The aim of the work is to develop and test a temperature ranking method for the intelligent identification and ranking of local accident clusters.

Materials and Methods. The research is based on calculating an integral temperature indicator for a road network location as the weighted sum of all RTAs in its vicinity, with an exponential decay of the contribution over time. The approaches used include spatio-temporal clustering, parametric weighting of RTA types based on frequency and controllability criteria, and mathematical modeling with a memory parameter (τ). The methodological apparatus is implemented as a PHP software module integrated into data analysis systems.

Results. The research findings include: 1) an algorithm is formalized which quantitatively differentiates the risk at locations with the same number of RTAs but different event structures and recency; 2) a three-level system of weights for RTA types is proposed and justified; 3) a comparative pilot test on real data from three intersections in Kaliningrad (2022-2024) is carried out showing correct ranking of locations by current risk level.

Discussion and Conclusions. The scientific novelty lies in integrating spatial proximity, temporal relevance, and typological significance of events into a single adaptable indicator. The practical value of the method is related to providing road management authorities and traffic police with a tool for well-founded planning accident reduction on road networks.

1. Gantimurova Yu.O. Application of topographic analysis to identify areas of concentration of road accidents. Sbornik nauchnykh trudov Angarskogo gosudarstvennogo tekhnicheskogo universiteta. 2024; № 21: 189-192. (In Russ.).

2. Goryaev N.K. Collection, processing and analysis of open data on road accidents. Vestnik Sibirskogo gosudarstvennogo avtomobilno-dorozhnogo universiteta. 2023; Vol. 20, № 5(93): 574-585. (In Russ.)

3. Kamh H., Alyami S.H., Khattak A., Alyami M., Almujibah H. «Exploring Road Traffic Accidents Hotspots Using Clustering Algorithms and GISBased Spatial Analysis» in IEEE Access, vol. 13, pp. 60944-60954, 2025, https://doi.org/10.1109/ACCESS.2024.3443245

4. Soltani A., Roohani Qadikolaei M. Spacetime analysis of accident frequency and the role of built environment in mitigation. Transport Policy. 2024. Vol. 150. P. 189–205. https://doi.org/10.1016/j.tranpol.2024.02.006

5. Singh N., Kumar M. A novel analytical framework to identify and classify accident hotspots integrating gradient classifier and spatial clustering. Earth Sci Inform 18, 168 (2025). https://doi.org/10.1007/s12145-024-01540-y

6. Israelev L.A. Geoinformation method for identifying and analyzing areas of concentration of road accidents. InterKarto. InterGIS. 2024. Vol. 30, № 2: 445-455. (In Russ.)

7. Syed Saqib Ali Kazmi, Mehreen Ahmed, Rafia Mumtaz, Zahid Anwar, Spatiotemporal Clustering and Analysis of Road Accident Hotspots by Exploiting GIS Technology and Kernel Density Estimation, The Computer Journal, Volume 65, Issue 2, February 2022, Pages 155–176, https://doi.org/10.1093/comjnl/bxz158

8. Al Hamami M, Matisziw TC. Measuring the spatiotemporal evolution of accident hot spots. Accid Anal Prev. 2021 Jul;157:106133. https://doi.org/10.1016/j.aap.2021.106133. Epub 2021 May 11. PMID: 33989871.

9. Alsahfi, T. Spatial and Temporal Analysis of Road Traffic Accidents in Major Californian Cities Using a Geographic Information System. ISPRS Int. J. GeoInf. 2024, 13, 157. https://doi.org/10.3390/ijgi13050157

10. Khosravi Y., Hosseinali F., Adresi, M. Identifying accident prone areas and factors influencing the severity of crashes using machine learning and spatial analyses. Sci Rep 14, 29836 (2024). https://doi.org/10.1038/s41598-024-81121-7

11. H.Thi Le, Vu, T.Phuong Thi and Do, T.Phuong Thi. «A study on identifying and analyzing road traffic incident hotspots on National Highway 1A, Thanh Hoa province, Vietnam, employing Statistical and GIS Techniques». Journal of Mining and Earth Sciences, 65(6), pp.22-33. https://doi.org/10.46326/JMES.2024.65(6).03

12. Abdrhman H., Qiu, Y., Shams, H., Damos, M. GIS-Based Identification of Traffic Incident Hot Spots and Severity Index in Khartoum, Sudan. TuijinJishu/Journal of Propulsion Technology, Volume 45, Issue 4, 2024, ISSN 1001-4055, https://propulsiontechjournal.com/index.php/journal/article/view/8436/5289.

13. Berhanu Y., Schroeder D., Teklu B., Alemayehu E. Spatial analysis of road traffic accidents: Identifying hotspots for improved road safety in Addis Ababa, Ethiopia. Cogent Engineering, Volume 10, Issue 2, 2023. https://doi.org/10.1080/23311916.2023.2269655

14. Truong, Long T & Somenahalli, Sekhar V. 2011. Using GIS to Identify Pedestrian-Vehicle Crash Hot Spots and Unsafe Bus Stops. Journal of Public Transportation, 14 (1): 99-114. http://doi.org/10.5038/2375-0901.14.1.6

15. Derya Birant, Alp Kut, ST-DBSCAN: An algorithm for clustering spatial–temporal data, Data & Knowledge Engineering, Volume 60, Issue 1, 2007, Pages 208-221, ISSN 0169-023X. https://doi.org/10.1016/j.datak.2006.01.013

16. Yunxuan L., Shuo, W., Xin, G., Meng, L., Yanyan, C. A Spatial-Temporal Kernel Density Estimate Method for Traffic Violation Hotspot Identification, 23rd COTA International Conference of Transportation Professionals, 2023, Pages 1626-1636.https://doi.org/10.1061/9780784484869.155

17. Han Y., Hu Y., Zhu H., Wang F. A cyclically adjusted spatio-temporal kernel density estimation method for predictive crime hotspot analysis, Annals of GIS, Volume 29, Issue 1, 2023, Pages 177-191. https://doi.org/10.1080/19475683.2023.2166584

18. Rico Krueger, Prateek Bansal, Prasad Buddhavarapu, A new spatial count data model with Bayesian additive regression trees for accident hot spot identification, Accident Analysis & Prevention, Volume 144, 2020, 105623, ISSN 0001-4575, https://doi.org/10.1016/j.aap.2020.105623

19. Poletaikin A.N. Development of data mining system for the identification of accident blackspots in the context of the age composition of road accident participants. Nauchnye zapiski NGUEU. 2025; № 2: 49-61. (In Russ.)

20. Behboudi Noushin, Sobhan Moosavi, Rajiv Ramnath. Recent advances in traffic accident analysis and prediction: A comprehensive review of machine learning techniques. arXiv preprint arXiv:2406.13968 (2024). https://doi.org/10.48550/arXiv.2406.13968

21. Gao P., Shuai B., Zhang R., Wang B. STCAGNN-RNKDE: a traffic accident prediction model for spatiotemporal combinatorial attention graph neural networks using Ripley’s K and network kernel density estimation. Reliability Engineering & System Safety, Volume 265, 2026. https://doi.org/10.1016/j.ress.2025.111593

22. Muduli K., Sahu D., Ghosh I. An Adaptable Framework for Identifying and Prioritising Road Traffic Accident Hotspots. Traffic & Transportation, Volume 37, Issue 2, 2025, Pages 321-337. https://doi.org/10.7307/ptt.v37i2.751

23. Abid, Dr. Rana Ibrahim. Identifying Spatial Patterns of Road Accidents in Madaba City by Applying Getis-Ord Gi* Spatial Statistic. International Journal of Engineering and Advanced Technology, Volume 13, Issue 4, 2024, Pages 1-8. https://doi.org/10.35940/ijeat.C4387.13040424

24. Köfteci S., Yalçın M.A., QGIS-based Analysis of Traffic Accident Regions in Muratpasa District in Antalya City. Gazi University Journal of Science Part A: Engineering and Innovation, Volume 11, Issue 4, 2024, Pages 771-779. https://doi.org/10.54287/gujsa.1581268

25. Siregar A.Z., Awaluddin M, Wahyuddin Y. Identification of Traffic Accidents Vulnerability Level Using Kernel Density And K-Medoids Methods (Case Study: Depok and Kalasan Districts, Sleman Regency). Jurnal Ilmiah Geomatika, Volume 3, Issue 1, 2023. https://doi.org/10.31315/imagi.v3i1.9241