journal article·2025-08-19Open access

Using Neural Networks to Predict the Frequency of Traffic Accidents by Province in Poland

Piotr Gorzelańczyk, Jacek Zabel, Edgar Sokolovskij

Applied Sciences· Volume 15· Issue 16

Abstract

Road traffic fatalities remain a significant global issue, despite a gradual decline in recent years. Although the number of accidents has decreased—partly due to reduced mobility during the pandemic—the figures remain alarmingly high. To further reduce these numbers, it is crucial to identify regions with the highest accident rates and predict future trends. This study aims to forecast traffic accident occurrences across Poland’s provinces. Using official police data on annual accident statistics, we analyzed historical trends and applied predictive modeling in Statistica to estimate accident rates from 2022 to 2040. Several neural network models were employed to generate these projections. The findings indicate that a significant reduction in road accidents is unlikely in the near future, with rates expected to stabilize rather than decline. The accuracy of predictions was influenced by the random sampling distribution used in model training. Specifically, a 70-15-15 split (70% training, 15% testing, and 15% validation) yielded an average error of 1.75%, and an 80-10-10 split reduced the error to 0.63%, demonstrating the impact of sample allocation on predictive performance. These results highlight the importance of dataset partitioning in accident forecasting models.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Air Quality Monitoring and Forecasting · Traffic Prediction and Management Techniques · Energy Load and Power Forecasting

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Transport, Stanislaw Staszic State University of Applied Sciences in Pila, Podchorazych Str. 10, 64-920 Pila, Poland

Laboratory of Vision Science and Optometry, Faculty of Physics and Astronomy, Adam Mickiewicz University of Poznan, Uniwersytetu Poznanskiego Str. 2, 61-614 Poznan, Poland

Department of Automobile Engineering, Faculty of Transport Engineering, Vilnius Gediminas Technical University, Plytinės Str. 25, 10105 Vilnius, Lithuania

References (28)

Show source-provided references
1. WHO (2018). The Global Status on Road Safety 2018, WHO. Available online: https://iris.who.int/bitstream/handle/10665/276462/9789241565684-eng.pdf?sequence=1.
2. Vehicle velocity relation to slipping trajectory change: An option for traffic accident reconstruction10.7307/ptt.v30i4.2720 ↗
3. The impact of basic traffic flow characteristics on traffic accident occurrence on 2-lane rural roads in Serbia10.3846/transport.2025.20543 ↗
4. Prediction of road accident risk for vehicle fleet based on statistically processed tire wear model10.7307/ptt.v34i4.3997 ↗
5. Risk analysis of road traffic accidents in Ukraine10.3846/transport.2024.23190 ↗
6. Gorzelańczyk, P., and Sokolovskij, E. (2025). Using neural networks to forecast the amount of traffic accidents in Poland and Lithuania. Sustainability, 17.10.3390/su17051846 ↗
7. Fractional integration methods and short Time series: Evidence from asimulation study10.1093/pan/mpv026 ↗
8. (2022, April 17). Forecasting Based on Time Series. Available online: http://pis.rezolwenta.eu.org/Materialy/PiS-W-5.pdf.
9. Procházka, J., Flimmel, S., Čamaj, M., and Bašta, M. (2017). Modelling the Number of Road Accidents. Applications of Mathematics and Statistics in Economics. International Scientific Conference, Szklarska Poręba, 30 August–3 September 2017, Publishing House of the University of Economics in Wrocław.10.15611/amse.2017.20.29 ↗
10. Sunny, C.M., Nithya, S., Sinshi, K.S., Vinodini, V.M.D., Lakshmi, A.K.G., Anjana, S., and Manojkumar, T.K. (2018, January 7–9). Forecasting of Road Accident in Kerala: A Case Study. Proceedings of the 2018 International Conference on Data Science and Engineering (ICDSE), Kochi, India.10.1109/ICDSE.2018.8527825 ↗
11. Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., and Zurada, J.M. (2013). Forecasting Time Series with Multiple Seasonal Cycles Using Neural Networks with Local Learning. Artificial Intelligence and Soft Computing ICAISC 2013, Springer. Lecture Notes in Computer Science.10.1007/978-3-642-38658-9 ↗
12. Szmuksta-Zawadzka, M., and Zawadzki, J. (2022, April 17). Forecasting on the Basis of Holt-Winters Models for Complete and Incomplete Data. Research Papers of the Wrocław University of Economics 2009, No. 38. Available online: http://bazekon.icm.edu.pl/bazekon/element/bwmeta1.element.ekon-element-000164937729.
13. Time series modeling in traffic safety research10.1016/j.aap.2017.11.030 ↗
14. Global road fatality trends’estimations based on country-wise microlevel data10.1016/j.aap.2017.11.035 ↗
15. Prognozowanie liczby wypadków drogowych na Podkarpaciu
16. Application of neural networks to forecast the number of road accidents in provinces in Poland10.1016/j.heliyon.2022.e12767 ↗
17. Impact of the COVID-19 pandemic on road traffic accident forecasting in Poland and Slovakia10.1515/eng-2022-0370 ↗
18. (2022, April 17). Central Statistical Office. Available online: www.gus.pl.
19. (2022, April 17). Province Names in English. Available online: https://polandtravel.agency/regions-of-poland/.
20. (2022, April 17). Statistic Road Accident. Available online: https://statystyka.policja.pl/.
21. Building machines that learn and think like people10.1017/S0140525X16001837 ↗
22. Becoming Human (2019, August 10). How Netflix Uses AI, Data Science, and Machine Learning—From a Product Perspective. Available online: www.becominghuman.ai.
23. Forbes (2020, September 12). The Amazing Ways eBay Is Using Artificial Intelligence to Boost Business Success. Available online: www.forbes.com.
24. Wu, Y., Schuster, M., Chen, Z., Le, Q.V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., and Macherey, K. (2020). Google’s neural machine translation system: Bridging the gap between human and machine translation. arXiv.
25. The application of neural networks in the work of forensic experts in child abuse cases
26. Wójcik, A. (2014). Autoregressive Vector Models as a Response to the Critique of Multi-Equation Structural Econometric Models, Publishing House of the University of Economics in Katowice.
27. Comparison of the performance of coupled gradient and quasi-Newtonian BFGS algorithms in the problem of optimizing power distribution in a power system
28. Change in the Mobility of Polish Residents during the COVID-19 Pandemic