Makine Öğrenmesi Yöntemleri Kullanılarak Geliştirilen Buzlanma Tahmin Mobil Uygulaması
Year 2025,
Volume: 3 Issue: 2, 92 - 104, 31.12.2025
Mehmet Ali Nacak
,
Eda Sıçrar
,
Azize Kızıltepe
,
Büşra Aksakallı
,
Deniz Katipoğlu
,
Nursena Bayğın
Abstract
Kış aylarında yollarda meydana gelen buzlanma, trafik güvenliğini ciddi şekilde tehdit eden önemli bir sorundur. Özellikle sert iklim koşullarına sahip bölgelerde olumsuz hava şartları kazalara, maddi ve manevi kayıplara yol açmaktadır. Bu çalışmada, yol buzlanmasını önceden tahmin edebilen ve sürücülere gerçek zamanlı uyarılar gönderen bir mobil uygulama geliştirilmiştir. Meteorolojik verilerin API aracılığıyla otomatik olarak alınmasının, manuel veri girişinden kaynaklanan hataları azaltarak tahmin doğruluğunu artıracağı varsayılmıştır. Open-Meteo platformundan elde edilen sıcaklık, bağıl nem, çiğ noktası, rüzgâr hızı ve kar yağışı verileri işlenerek makine öğrenmesi modellerinde kullanılmıştır. Rastgele Orman (Random Forest), Destek Vektör Makineleri (SVM) ve Çok Katmanlı Algılayıcı (MLP) algoritmaları eğitilmiş ve performansları karşılaştırılmıştır. En yüksek doğruluk oranı, bu üç algoritmanın birleştirildiği Voting Classifier tabanlı ansambl modelinde elde edilmiştir. Geliştirilen model %93,20 doğruluk, %92,16 makro duyarlılık, %93,20 ağırlıklı duyarlılık, %91,56 makro F1 ve %93,25 ağırlıklı F1 skorları elde etmiştir. Bu sonuçlar özellikle yüksek riskli buzlanma sınıflarının doğru tahmininde önemli bir iyileşme sağlamıştır. Kullanıcı dostu arayüz ile sürücülere konuma bağlı erken uyarılar sunan bu sistem, trafik kazalarının önlenmesine ve sürücü farkındalığının artmasına katkı sağlamayı amaçlamaktadır. Geliştirilen mobil uygulama, yerel koşullara uyarlanabilir yapısı sayesinde ilerleyen süreçte farklı bölgelerde de uygulanabilir bir çözüm olarak değerlendirilebilir.
Ethical Statement
Bu çalışma, etik kurul izni gerektiren herhangi bir insan katılımcı, hayvan veya hassas veri içermemektedir. Bu nedenle etik kurul onayına gerek duyulmamıştır.
Supporting Institution
Bu çalışma, Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK) tarafından 2209-A Üniversite Öğrencileri Araştırma Projeleri Destekleme Programı kapsamında desteklenmiştir.
Project Number
1919B012427931
Thanks
Yazarlar, bu çalışmaya sağladıkları değerli katkılar ve desteklerinden dolayı Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK)’a ve Erzurum Teknik Üniversitesi’ne içten teşekkürlerini sunar.
References
-
E. Güney, Erzurum kent merkezindeki gizli buzlanma risk düzeyinin belirlenmesi ve akıllı ulaşım sistemleri, M.S. thesis, Inst. of Social Sciences, Sakarya Univ., Sakarya, Türkiye, 2024.
-
Z. Zhang, Z. Zhou, and J. He, Development of FBG-based road ice thickness monitoring sensor and its application on the traffic road, Optical Fiber Technology, vol. 89, Jan. 2025, Art. no. 104070, doi: 10.1016/j.yofte.2024.104070.
-
Turkish Statistical Institute, Highway Traffic Accident Statistics, 2024, Apr. 18, 2025. [Online]. Available: https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-%C4%B0statistikleri-2024-54056&dil=1. Accessed: May 19, 2025.
-
C. Gheorghe and A. Soica, Revolutionizing Urban Mobility: A Systematic Review of AI, IoT, and Predictive Analytics in Adaptive Traffic Control Systems for Road Networks, Electronics, vol. 14, no. 4, p. 719, Feb. 2025. doi: 10.3390/electronics14040719.
-
H. Zhang, Y. Liu, C. Zhang, and N. Li, “Machine Learning Methods for Weather Forecasting: A Survey,” Atmosphere, vol. 16, no. 1, p. 82, Jan. 2025, doi: 10.3390/atmos16010082.
-
H. Tıraşoğlu, Buzlanma tahmini için bir algoritma geliştirilmesi ve mobil uygulamasının gerçekleştirilmesi, M.S. thesis, Dept. of Computer Engineering, Gazi Univ., Ankara, Türkiye, 2017.
-
H. Kabaoğlu, E. Uçar, and F. Duran, “Buzlanma tahmini yapan mobil uygulama geliştirilmesi,” Politeknik Dergisi, vol. 24, no. 4, pp. 1543–1555, 2021.
-
S. B. Hong, H. S. Yun, S. G. Yum, S. Y. Ryu, I. S. Jeong, and J. Kim, Development of black ice prediction model using GIS-based multi-sensor model validation, Natural Hazards and Earth System Sciences, vol. 22, pp. 3435–3450, Oct. 2022. doi: 10.5194/nhess-22-3435-2022.
-
J. Jang, “Predicting nighttime black ice using atmospheric data for efficient winter road maintenance patrols,” Transportation Research Interdisciplinary Perspectives, Korea Institute of Civil Engineering and Building Technology, South Korea. [Online]. Available: https://www.sciencedirect.com/journal/transportation-research-interdisciplinary-perspectives. Accessed: May 19, 2025.
-
S. B. Hong and H. S. Yun, Predicting black ice-related accidents with probabilistic modeling using GIS-based Monte Carlo simulation, PLOS ONE, May 23, 2024, doi: 10.1371/journal.pone.0303605.
-
Ignis Trace, “Don ve buzlanmaya karşı rampa ve yol koruma yöntemleri,” Ignis Trace Blog, Dec. 15, 2024. [Online]. Available: https://www.ignistrace.com/bloglar/don-ve-buzlanmaya-karsi-rampa-ve-yol-koruma-yontemleri. Accessed: May 19, 2025.
-
Republic of Türkiye Ministry of Environment, Urbanization and Climate Change, “Sıcaklık,” Çevresel Göstergeler, 2023. [Online]. Available: https://cevreselgostergeler.csb.gov.tr/sicaklik-i-85727. Accessed: May 19, 2025.
-
M. Jin and D. G. McBroom, "Investigating Road Ice Formation Mechanisms Using Road Weather Information System (RWIS) Observations," Climate, vol. 12, no. 5, p. 63, May 2024. doi: 10.3390/cli12050063.
-
R. Rekuviene, S. Saeidiharzand, L. Mažeika, V. Samaitis, A. Jankauskas, A. K. Sadaghiani, G. Gharib, Z. Muganlı, and A. Koşar, "A review on passive and active anti-icing and de-icing technologies," Applied Thermal Engineering, vol. 250, p. 123474, Aug. 2024.)
-
Open-Meteo, “About Open-Meteo,” 2024. [Online]. Available: https://open-meteo.com/en/about. Accessed: Apr. 15, 2025.
-
A. Oğuzlar, “Veri Ön İşleme,” Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, no. 21, pp. 67–76, Jul. –Dec. 2003.
-
LearnArtificialIntelligence, “SMOTE: A Powerful Technique for Handling Imbalanced Data,” Medium, Sep.6,2023.[Online]. Available: https://medium.com/@thecontentfarmblog/smote-a-powerful-technique-for-handling-imbalanced-data-2375ad46103c. Accessed: May 19, 2025.
-
M. Z. A. Bhuiyan, M. A. H. Chowdhury, and M. S. Kaiser, “Ensemble learning for classification: A review,” IEEE Access, vol. 8, pp. 112–130, 2020.
-
S. S. S. R. Depuru, L. T. H. An, and S. S. S. R. Depuru, “A comparative study of ensemble learning techniques for classification,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 5, pp. 1456–1469, May 2020.
-
A. S. K. Pathan, M. S. Hossain, and M. A. H. Chowdhury, “Random Forest and Support Vector Machine for classification of weather data,” IEEE Transactions on Industrial Informatics, vol. 16, no. 3, pp. 1987–1995, Mar. 2020.
-
J. Smith, A. Johnson, and R. Williams, “Application of ensemble methods in predicting weather conditions,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 7, pp. 4567–4575, Jul. 2020.
-
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A:1010933404324.
-
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.
-
S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson, 2009.
Ice Formation Prediction Mobile Application Using Machine Learning Methods
Year 2025,
Volume: 3 Issue: 2, 92 - 104, 31.12.2025
Mehmet Ali Nacak
,
Eda Sıçrar
,
Azize Kızıltepe
,
Büşra Aksakallı
,
Deniz Katipoğlu
,
Nursena Bayğın
Abstract
Ice formation on roads during the winter months poses a serious threat to traffic safety. In regions with harsh winters, adverse weather conditions can lead to accidents causing significant material and psychological losses. The need for effective icing prediction and warning systems is increasing in order to minimize such accidents. In this study, a mobile application was developed to predict road icing in advance and provide real-time alerts to drivers. It was hypothesized that automatically retrieving meteorological data via an API would reduce errors caused by manual entry and improve prediction accuracy. Temperature, relative humidity, dew point, wind speed, and snowfall data obtained from the Open-Meteo platform were processed and utilized for icing prediction. To enhance prediction accuracy, various machine learning algorithms such as Random Forest, SVM, and MLP were trained and their performance was compared. In the final model, a Voting Classifier-based ensemble method that combines the strengths of these algorithms was employed. The developed ensemble model outperformed individual models, achieving 93.20% accuracy, 92.16% macro recall, 93.20% weighted recall, 91.56% macro F1, and 93.25% weighted F1 scores. These results particularly improved the accurate prediction of high-risk icing classes. Finally, a user-friendly interface was designed to provide drivers with early warnings based on the predicted level of risk. The findings are expected to contribute to raising driver awareness of icing risks and enhancing road safety.
Ethical Statement
This study does not involve any human participants, animals, or sensitive data requiring ethical approval. Therefore, an ethics committee report was not necessary.
Supporting Institution
This research was supported by The Scientific and Technological Research Council of Turkey (TÜBİTAK) under the 2209-A Research Project Support Program for Undergraduate Students.
Project Number
1919B012427931
Thanks
The authors would like to express their sincere gratitude to The Scientific and Technological Research Council of Turkey (TÜBİTAK) and Erzurum Technical University for their valuable support and contributions to this study.
References
-
E. Güney, Erzurum kent merkezindeki gizli buzlanma risk düzeyinin belirlenmesi ve akıllı ulaşım sistemleri, M.S. thesis, Inst. of Social Sciences, Sakarya Univ., Sakarya, Türkiye, 2024.
-
Z. Zhang, Z. Zhou, and J. He, Development of FBG-based road ice thickness monitoring sensor and its application on the traffic road, Optical Fiber Technology, vol. 89, Jan. 2025, Art. no. 104070, doi: 10.1016/j.yofte.2024.104070.
-
Turkish Statistical Institute, Highway Traffic Accident Statistics, 2024, Apr. 18, 2025. [Online]. Available: https://data.tuik.gov.tr/Bulten/Index?p=Karayolu-Trafik-Kaza-%C4%B0statistikleri-2024-54056&dil=1. Accessed: May 19, 2025.
-
C. Gheorghe and A. Soica, Revolutionizing Urban Mobility: A Systematic Review of AI, IoT, and Predictive Analytics in Adaptive Traffic Control Systems for Road Networks, Electronics, vol. 14, no. 4, p. 719, Feb. 2025. doi: 10.3390/electronics14040719.
-
H. Zhang, Y. Liu, C. Zhang, and N. Li, “Machine Learning Methods for Weather Forecasting: A Survey,” Atmosphere, vol. 16, no. 1, p. 82, Jan. 2025, doi: 10.3390/atmos16010082.
-
H. Tıraşoğlu, Buzlanma tahmini için bir algoritma geliştirilmesi ve mobil uygulamasının gerçekleştirilmesi, M.S. thesis, Dept. of Computer Engineering, Gazi Univ., Ankara, Türkiye, 2017.
-
H. Kabaoğlu, E. Uçar, and F. Duran, “Buzlanma tahmini yapan mobil uygulama geliştirilmesi,” Politeknik Dergisi, vol. 24, no. 4, pp. 1543–1555, 2021.
-
S. B. Hong, H. S. Yun, S. G. Yum, S. Y. Ryu, I. S. Jeong, and J. Kim, Development of black ice prediction model using GIS-based multi-sensor model validation, Natural Hazards and Earth System Sciences, vol. 22, pp. 3435–3450, Oct. 2022. doi: 10.5194/nhess-22-3435-2022.
-
J. Jang, “Predicting nighttime black ice using atmospheric data for efficient winter road maintenance patrols,” Transportation Research Interdisciplinary Perspectives, Korea Institute of Civil Engineering and Building Technology, South Korea. [Online]. Available: https://www.sciencedirect.com/journal/transportation-research-interdisciplinary-perspectives. Accessed: May 19, 2025.
-
S. B. Hong and H. S. Yun, Predicting black ice-related accidents with probabilistic modeling using GIS-based Monte Carlo simulation, PLOS ONE, May 23, 2024, doi: 10.1371/journal.pone.0303605.
-
Ignis Trace, “Don ve buzlanmaya karşı rampa ve yol koruma yöntemleri,” Ignis Trace Blog, Dec. 15, 2024. [Online]. Available: https://www.ignistrace.com/bloglar/don-ve-buzlanmaya-karsi-rampa-ve-yol-koruma-yontemleri. Accessed: May 19, 2025.
-
Republic of Türkiye Ministry of Environment, Urbanization and Climate Change, “Sıcaklık,” Çevresel Göstergeler, 2023. [Online]. Available: https://cevreselgostergeler.csb.gov.tr/sicaklik-i-85727. Accessed: May 19, 2025.
-
M. Jin and D. G. McBroom, "Investigating Road Ice Formation Mechanisms Using Road Weather Information System (RWIS) Observations," Climate, vol. 12, no. 5, p. 63, May 2024. doi: 10.3390/cli12050063.
-
R. Rekuviene, S. Saeidiharzand, L. Mažeika, V. Samaitis, A. Jankauskas, A. K. Sadaghiani, G. Gharib, Z. Muganlı, and A. Koşar, "A review on passive and active anti-icing and de-icing technologies," Applied Thermal Engineering, vol. 250, p. 123474, Aug. 2024.)
-
Open-Meteo, “About Open-Meteo,” 2024. [Online]. Available: https://open-meteo.com/en/about. Accessed: Apr. 15, 2025.
-
A. Oğuzlar, “Veri Ön İşleme,” Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, no. 21, pp. 67–76, Jul. –Dec. 2003.
-
LearnArtificialIntelligence, “SMOTE: A Powerful Technique for Handling Imbalanced Data,” Medium, Sep.6,2023.[Online]. Available: https://medium.com/@thecontentfarmblog/smote-a-powerful-technique-for-handling-imbalanced-data-2375ad46103c. Accessed: May 19, 2025.
-
M. Z. A. Bhuiyan, M. A. H. Chowdhury, and M. S. Kaiser, “Ensemble learning for classification: A review,” IEEE Access, vol. 8, pp. 112–130, 2020.
-
S. S. S. R. Depuru, L. T. H. An, and S. S. S. R. Depuru, “A comparative study of ensemble learning techniques for classification,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 5, pp. 1456–1469, May 2020.
-
A. S. K. Pathan, M. S. Hossain, and M. A. H. Chowdhury, “Random Forest and Support Vector Machine for classification of weather data,” IEEE Transactions on Industrial Informatics, vol. 16, no. 3, pp. 1987–1995, Mar. 2020.
-
J. Smith, A. Johnson, and R. Williams, “Application of ensemble methods in predicting weather conditions,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58, no. 7, pp. 4567–4575, Jul. 2020.
-
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A:1010933404324.
-
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995.
-
S. Haykin, Neural Networks and Learning Machines, 3rd ed., Pearson, 2009.