SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2026 / Cilt: 15 Sayı: 2

Time Series and Machine Learning Methods for Estimating Missing Meteorological Data: The Western Black Sea Basin Case

Eksik Meteorolojik Verilerin Zaman Serisi ve Makine Öğrenmesi Yöntemleri Kullanılarak Tahmin Edilmesi: Batı Karadeniz Havzası Örneği

Yusuf Kaya(BEYKENT ÜNİVERSİTESİ)0000-0002-0923-2217
Berna Aksoy(ZONGULDAK BÜLENT ECEVİT ÜNİVERSİTESİ)0000-0001-6925-1594
İsmail Hakkı Özölçer(ZONGULDAK BÜLENT ECEVİT ÜNİVERSİTESİ)0000-0002-8404-0522
Pages
54–67
Publication Date
2025-07-21
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Thus, impact of deviations due to data loss in future drought analyses is minimized.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:The development of artificial intelligence applications is rapidly advancing today.
📊
Key Findings & Data:This increases the importance of data for all artificial intelligence subfields.
💡
Conclusion & Impact:Thus, impact of deviations due to data loss in future drought analyses is minimized.
🔬Design:Modeling & Simulation
📍Scope:2000 Verileri
⚙️Variables:Eksik veri · sarima · yağış

Abstract

The development of artificial intelligence applications is rapidly advancing today. It enables making existing data meaningful through a wide range of applications. This increases the importance of data for all artificial intelligence subfields. The accuracy, continuity and meaningfulness of data are very important for training and testing the models. Discontinuities or errors are likely to occur in data obtained from long-term physical measurements. It is inevitable for meteorological data, which are highly influenced by external factors to have gaps. Mentioned situation causes negative effects on the analysis reliability of meteorological data, which plays a significant role in climate change and hydrological modelling. Within the scope of this study, monthly precipitation measurements of meteorological observation stations in the city centers of seven different provinces in the Western Black Sea basin were examined. The gaps in the monthly rainfall data measured between 2000 and 2023 were estimated using time series, statistical and machine learning approaches. In the modelling process, ARIMA, SARIMA, ARIMAX, XGBOOST, and mean imputation methods were employed. The analyses revealed that SARIMA models, which consider seasonal effects, provided more consistent results, as demonstrated by performance metrics. The completed data form the basis for advanced drought analysis. Thus, impact of deviations due to data loss in future drought analyses is minimized.

Özet

Yapay zekâ uygulamalarının gelişimi günümüzde hızla devam etmektedir. Geniş bir uygulama yelpazesiyle elde var olan verinin anlamlı hale getirilmesini sağlamaktadır. Bu durum tüm yapay zekâ alt grupları için verinin önemini arttırmaktadır. Verinin doğruluğu, sürekliliği ve anlamlılığı modellerin eğitilmesi ve test edilmesi için oldukça önemlidir. Uzun süreli fiziksel ölçümlere dayalı elde edilen verilerde süreksizlikler veya hatalar olması olasıdır. Dışsal faktörlerin oldukça etkili olduğu meteorolojik verilerde eksikler olması kaçınılmazdır. Bu durum iklim değişikliği ve hidrolojik modellemelerde önemli bir yer tutan meteorolojik verilerin analiz güvenliğini negatif etkilemesine neden olmaktadır. Bu çalışma kapsamında Batı Karadeniz havzasında yer alan yedi farklı ilin şehir merkezlerindeki meteorolojik gözlem istasyon aylık yağış ölçümleri incelenmiştir. Ölçümleri yapılan 2000-2023 yıllarındaki aylık yağış verilerindeki eksiklikler zaman serisi, istatiksel ve makine öğrenmesi yaklaşımları ile tahmin edilmeye çalışılmıştır. Modellemelerde ARIMA, SARIMA, ARIMAX, XGBOOST ve ortalama ile tamamlama yöntemleri kullanılmıştır. Yapılan analizlerde mevsimsel etkileri dikkate alan SARIMA modellerinin daha uyumlu sonuçlar verdiği performans metrikleri ile ortaya konulmuştur. Tamamlanan veriler ileri düzey kuraklık analizlerine altlık oluşturmaktadır. Böylece ileride yapılacak kuraklık analizlerinin veri kayıplarından kaynaklı sapmalardan etkilenmesi minimize edilmiştir.

🔖

Cite This Article

Kaya, Y., Aksoy, B., Özölçer, İ. H. (2025). Time Series and Machine Learning Methods for Estimating Missing Meteorological Data: The Western Black Sea Basin Case. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 15 Sayı: 2, 54–67. https://doi.org/10.7212/karaelmasfen.1637034

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (23)

  1. Bentéjac, C., Csörgo, A., Martínez-Muñoz, G. 2021. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54. https://doi.org/10.xxxx
  2. Bierens, HJ. 1987. ARMAX model specification testing, with an application to unemployment in the Netherlands. Journal of Econometrics, 35(1):161–190. https://doi.org/10.1016/0304-4076(87)90086-8
  3. Box, GE., Jenkins, GM., Reinsel, G. 1970. Forecasting and control. Time Series Analysis, 3, 75.
  4. Box, GEP., Jenkins, GM., Reinsel, GC. 2008. Time series analysis: Forecasting and control (4th ed.). New Jersey: John Wiley & Sons, Inc. ISBN: 978-0470272848
  5. Chen, T., Guestrin, C. 2016. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, s. 785–794. ACM. https://doi.org/10.1145/2939672.2939785
  6. Cryer, JD., Chan, KS. 2008. Time series analysis: With applications in R. New York: Springer-Verlag. ISBN: 978-0-387-75958-6.
  7. Dabral, PP., Murry, MZ. 2017. Modelling and forecasting of rainfall time series using SARIMA. Environmental Processes, 4:399–419. https://doi.org/10.1007/s40710-017-0226-y
  8. Dempster, AP., Laird, NM., Rubin, DB. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B (Methodological), 39(1):1–38. https://doi.org/10.2307/2984875
  9. Fan, J., Shan, R., Cao, X., Li, P. 2009. The analysis of the tertiary industry with the ARIMAX model. Journal of Mathematics Research, 1(2):156. https://doi.org/10.5539/jmr.v1n2p156
  10. García Laencina, PJ., Sancho Gómez, JL., Figueiras Vidal, AR., Verleysen, M. 2009. K nearest neighbours with mutual information for simultaneous classification and missing data imputation. Neurocomputing, 72(7–9):1483–1493. https://doi.org/10.1016/j.neucom.2008.11.026
  11. Huntra, P., Keener, TC. 2017. Evaluating the impact of meteorological factors on water demand in the Las Vegas Valley using time-series analysis: 1990–2014. International Journal of Geo-Information, 6(8), 249. https://doi.org/10.3390/ijgi6080249
  12. Schafer, JL., Graham, JW. 2002. Missing data: Our view of the state of art. Psychological Methods, 7(2):147-177. https://doi.org/10.1037/1082-989X.7.2.147
  13. Stekhoven, DJ., Bühlmann, P. 2012. MissForest: Non parametric missing value imputation for mixed type data. Bioinformatics, 28(1):112–118. https://doi.org/10.1093/bioinformatics/btr597
  14. Sutthichaimethee, P., Ariyasajjakorn, D. 2017. Forecasting energy consumption in short-term and long-term periods by using the ARIMAX model in the construction and materials sector in Thailand. Journal of Ecological Engineering, 18(4):52-59. https://doi.org/10.12911/22998993/74396
  15. Valipour, M. 2012. Number of required observation data for rainfall forecasting according to the climate conditions. American Journal of Scientific Research, 74:79–86.
  16. Valipour, M. 2015. Long-term runoff study using SARIMA and ARIMA models in the United States. Meteorological Applications, 22:592–598. https://doi.org/10.1002/met.1491
  17. Wangwongchai, A., Waqas, M., Dechpichai, P., Hlaing, PT., Ahmad, S., Humphries, U. W. 2023. Imputation of missing daily rainfall data: A comparison between artificial intelligence and statistical techniques. MethodsX, 11, 102459. https://doi.org/10.1016/j.mex.2023.102459
  18. Vincent, P., Larochelle, H., Bengio, Y., Manzagol, PA. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th International Conference on Machine Learning, s. 1096–1103. ACM.
  19. Wang, J., Du, Y H., Zhang, XT. 2008. Theory and application with seasonal time series (1st ed.). Nankai: Nankai University Press.
  20. Waqas, M., Humphries, UW., Hlaing, PT., Wangwongchai, A., Dechpichai, P. 2024. Advancements in daily precipitation forecasting: A deep dive into daily precipitation forecasting hybrid methods in the tropical climate of Thailand. MethodsX, 12, 102757. https://doi.org/10.1016/j.mex.2024.102757
  21. Zhang, G. P. 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50:159–175.
  22. Bentéjac, C., Csörgo, A., Martínez-Muñoz, G. 2021. A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54. https://doi.org/10.xxxx
  23. Waqas, M., Humphries, UW., Hlaing, PT., Wangwongchai, A., Dechpichai, P. 2024. Advancements in daily precipitation forecasting: A deep dive into daily precipitation forecasting hybrid methods in the tropical climate of Thailand. MethodsX, 12, 102757. https://doi.org/10.1016/j.mex.2024.102757