Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 22;15(1):26566.
doi: 10.1038/s41598-025-11835-9.

Prediction of traffic accidents trend with learning methods: a case study for Batman, Turkey

Enes Bakiş  1 , Mehmet Ali Erçetin  2 , Emrullah Acar  3 , İslam Gökalp  4 , Musa Yılmaz  5   6
Affiliations

Prediction of traffic accidents trend with learning methods: a case study for Batman, Turkey

Enes Bakiş et al. Sci Rep. .

Abstract

Assessing the trend of fatalities in recent years and forecasting road accidents enables society to make appropriate planning for prevention and control. This study analyses the road traffic accident data between the years 2013 and 2022 obtained for the province of Batman in Turkey, where it has not been considered before. The scope of the data analysed includes the fatalities and injuries of drivers, passengers and pedestrians. The road accident forecast for the next ten years up to 2032 is the focus of this study and numerous analyses using learning methods such as State Space Models (SSM), Artificial Neural Networks (ANN), Autoregressive Integrated Moving Average (ARIMA) and hybrid models (CNN + LSTM and Attention + GRU) have been performed on the available data. The predictions made with the above models give results with acceptable accuracy. However, they give different results depending on the parameters used. The models created with the data studied show that the number of road accidents and the related deaths and injuries will continue to increase over the next 10 years, starting in 2022. If the causes of road accidents are not eliminated and the situation remains stable as it is in 2022, the number of accidents, deaths and injuries is expected to double by 2032.

Keywords: Hybrid models; Learning methods; Prediction; Traffic accident.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Map of Batman, Turkey.
Fig. 2
Fig. 2
Work flow diagram of proposed approach.
Fig. 3
Fig. 3
Prediction graphs obtained for the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) Injured Pedestrian.
Fig. 4
Fig. 4
Prediction graphs obtained to forecast the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring(%).
Fig. 5
Fig. 5
Prediction graphs generated using ARIMA to forecast the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) Injured Pedestrian.
Fig. 6
Fig. 6
Prediction graphs generated using ARIMA to forecast the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring(%).
Fig. 7
Fig. 7
Prediction graphs obtained for the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) Injured Pedestrian.
Fig. 8
Fig. 8
Prediction graphs obtained for the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring(%).
Fig. 9
Fig. 9
Prediction graphs generated using SSM for the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) Injured Pedestrian.
Fig. 10
Fig. 10
Prediction graphs generated using SSM for the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring(%).
Fig. 11
Fig. 11
Predictions graphs obtained for the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) InjuredPedestrian.
Fig. 12
Fig. 12
Predictions graphs obtained for the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring (%).
Fig. 13
Fig. 13
Predictions graphs generated using ANN to forecast the attributes (a) Driver Fatalities (b) Passenger Fatalities (c) Pedestrian Fatalities (d) Injured Driver (e) Injured Passenger (f) Injured Pedestrian.
Fig. 14
Fig. 14
Predictions graphs generated using ANN to forecast the attributes (a) Total Fatalities (b) Total Injuring (c) Total Accident (d) Share Death(%) (e) Share Injuring(%).
Fig. 15
Fig. 15
Predictions graphs generated using hybrid models to predict the all attributes.
Fig. 16
Fig. 16
Forecasting graphs generated using Hybrid Models to forecast the first 5 attributes.
Fig. 17
Fig. 17
Forecasting graphs generated using Hybrid Models to forecast the last 4 attributes.
Fig. 18
Fig. 18
Sensitivity Analysis graphs of Hybrid Models.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Tedjopurnomo, D. A. et al. A survey on modern deep neural network for traffic prediction: trends, methods and challenges. IEEE Trans. Knowl. Data Eng.34 (4), 1544–1561 (2020).
    1. Santos, K., Dias, J. P. & Amado, C. A literature review of machine learning algorithms for crash injury severity prediction. J. Saf. Res.80, 254–269 (2022). - PubMed
    1. WHO, W.H.O. Global status report on road safety 2023. [cited 13.12.2023; (2023). Available from: https://www.who.int/publications/i/item/9789240086517
    1. Chen, S. et al. The global macroeconomic burden of road injuries: estimates and projections for 166 countries. Lancet Planet. Health. 3 (9), e390–e398 (2019). - PubMed
    1. (TUİK). T.İ.K. Karayolu Trafik Kaza İstatistikleri,. 2023 [cited 5.012.2023; Available from,. 2023 [cited 5.012.2023; Available from: (2022). https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-Istatistikl...

LinkOut - more resources