Sıcaklık ve güneşlenme süresine dayalı günlük yağış tahmini: Antalya ilinde istasyon bazlı bir modelleme yaklaşımı

Öz

Sıcaklıkta yaşanan pozitif anomaliler son yıllara iklim değişikliğine bağlı önemli bir araştırma sorusu olmuştur. Sıcaklık değişimleri doğrudan ve dolaylı pek çok etkiye sahiptir. Bu çalışma günlük maksimum sıcaklık ve günlük toplam güneşlenme süresi parametrelerinin günlük yağış üzerindeki etkisini araştırmayı amaçlamaktadır. Bu doğrultuda çalışmada Granger nedensellik analizi yapılarak meteorolojik parametrelerin yağış üzerindeki etkisi araştırılmıştır. Güneşlenme süresi ve günlük maksimum sıcaklık değişkenleri için p istatistik değeri <0.05 olarak belirlenmiş olup iki değişkenin de yağış üzerinde etkin olduğu görülmüştür. Çalışmada parametrelerde çeşitli gün gecikmeleri kullanılarak optimum girdi modelleri oluşturulmuş, Yapay Sinir Ağları (YSA) ve Sınıflandırma ve Regresyon Ağacı (SRA) yöntemleri kullanılarak ilişki düzeyleri araştırılmıştır. Çalışma sonucunda SRA yöntemi ile geliştirilen tahmin modellerinin YSA modellerine göre üstün başarısı (NSE:0.65-0.79) görülmüştür.

Anahtar Kelimeler

• Yağış Tahmini
• Makine Öğrenmesi
• Granger Nedensellik Analizi
• Güneşlenme Süresi

Daily rainfall prediction based on temperature and sunshine duration: A station-based modelling approach in Antalya province

Abstract

Positive anomalies in temperature have been an important research question related to climate change in recent years. Temperature changes have many direct and indirect effects. This study aims to investigate the effect of daily maximum temperature and total daily sunlight duration parameters on daily rainfall. In this perspective, Granger causality analysis was conducted to investigate the effect of meteorological parameters on rainfall. The p statistic value of the sunshine duration and daily maximum temperature variables was determined as <0.05 and both variables were found to be effective on rainfall. In the study, optimum input models were created using various day lags for the parameters and the relationship levels were investigated using Artificial Neural Networks (ANN) and Classification and Regression Tree (CART) methods. As a result of the study, the prediction models developed with the CART method outperformed the ANN models (NSE: 0.65-0.79).

Keywords

• Rainfall Prediction
• Machine Learning
• Granger Casuality Test
• Sunshine Duration

Kaynakça

1. A. Keskin ve Z. Kanat, Dünyada iklim değişikliği üzerine yapılan çalışmalar ve Türkiye’de mevcut durum. Atatürk University Journal of Agricultural Faculty, 49(1), 2018.
2.    M. Röthlisberger ve L. Papritz, Quantifying the physical processes leading to atmospheric hot extremes at a global scale. Nature Geoscience, 16, 210–216, 2023. https://doi.org/10.1038/s41561-023-01126-1
3.    K.-H. Kim ve B.-M. Lee, Effects of climate change and drought tolerance on maize growth. Plants, 12(20), 3548, 2023.https://doi.org/10.3390/plants12203548
4.    T. Vansteenkiste, M. Tavakoli, V. Ntegeka, P. Willems, F. De Smedt ve O. Batelaan, Climate change impact on river flows and catchment hydrology: a comparison of two spatially distributed models. Hydrological Processes, 27(25), 3649–3662, 2013. https://doi.org/10.1002/hyp.9480.
5.    M. Donat, A. Lowry, L. Alexander, P. A. O’Gorman, N. Maher, More extreme precipitation in the world’s dry and wet regions. Nature Climate Change, 6, 508–513, 2016. https://doi.org/10.1038/nclimate2941.
6.    H. Serkendiz, H. Tatlı, A. Kılıç, vd., Analysis of drought intensity, frequency and trends using the SPEI in Turkey. Theoretical and Applied Climatology, 155, 2997–3012, 2024. https://doi.org/10.1007/s00704-023-04772-y
7.    M. A. Çelik, H. Bayram ve S. Özüpekçe, An assessment on climatological, meteorological and hydrological disasters that occurred in Turkey in the last 30 years (1987–2017). International Journal of Geography and Geography Education, 38, 295–310, 2018. https://doi.org/10.32003/iggei.424675
8.    T. Pilevneli, G. Capar ve C. Sánchez-Cerdà, Investigation of climate change impacts on agricultural production in Turkey using volumetric water footprint approach. Sustainable Production and Consumption, 35, 605–623, 2023. https://doi.org/10.1016/j.spc.2022.12.013.

9.    M. Turkes, Climate and drought in Turkey. In N. Harmancioglu ve D. Altinbilek (Eds.), Water Resources of Turkey, World Water Resources, vol. 2, Springer, Cham, pp. 57–87, 2020. https://doi.org/10.1007/978-3-030-11729-0_4
10. Q. Zhang, J. Li, V. P. Singh ve M. Xiao, Spatio-temporal relations between temperature and precipitation regimes: Implications for temperature-induced changes in the hydrological cycle. Global and Planetary Change, 111, 57–76, 2013. https://doi.org/10.1016/j.gloplacha.2013.08.012.
11. H. T. Babacan, İklim değişikliği etkisi altında kıyı bölgelerinde aylık yağış rejimi değişimi ve gelecek yağış-akış tepkisinin araştırılması: Rize ve Antalya çalışması. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(2), 1020–1035, 2025. https://doi.org/10.17780/ksujes.1657507
12. M. Riazi, S. M. Bateni, C. Jun, vd., Enhancing rainfall-runoff simulation in data-poor watersheds: Integrating remote sensing and hybrid decomposition for hydrologic modelling. Water Resources Management, 2025. https://doi.org/10.1007/s11269-025-04215-5
13. H. Guzel, Estimation of rainfall-runoff relationship using soft computing techniques. Applied Ecology & Environmental Research, 23(2), 2025.
14. T. D. Duong, V. N. Tran ve T. V. Nguyen, Evaluating rainfall-runoff generation mechanisms of deep learning models using a process-based rainfall-runoff model. Water Resources Management, 2025. https://doi.org/10.1007/s11269-025-04231-5
15. M. Valipour, Temperature analysis of reference evapotranspiration models. Meteorological Applications, 22(3), 385–394, 2015. https://doi.org/10.1002/met.1465
16. K. A. Coskuner, Doğu Karadeniz orman yangınlarının uzun dönem meteorolojik parametrelerle değerlendirilmesi. Doğal Afetler ve Çevre Dergisi, 7(2), 374–381, 2021.
17. S. D. Lindsey ve R. K. Farnsworth, Sources of solar radiation estimates and their effect on daily potential evaporation for use in streamflow modeling. Journal of Hydrology, 201(1–4), 348–366, 1997. https://doi.org/10.1016/S0022-1694(97)00046-2
18. V. Kaleris ve A. Langousis, Comparison of two rainfall–runoff models: Effects of conceptualization on water budget components. Hydrological Sciences Journal, 62(5), 729–748, 2016. https://doi.org/10.1080/02626667.2016.1250899
19. Y. Zhang, Y. Chao, R. Fan, F. Ren, B. Qi, K. Ji ve B. Xu, Spatial-temporal trends of rainfall erosivity and its implication for sustainable agriculture in the Wei River Basin of China. Agricultural Water Management, 245, 106557, 2021. https://doi.org/ 10.1016/j.agwat.2020.106557
20. P. Guhathakurta ve E. Saji, Detecting changes in rainfall pattern and seasonality index vis-à-vis increasing water scarcity in Maharashtra. Journal of Earth System Science, 122, 639–649, 2013. https://doi.org/10.1007/s12040-013-0294-y
21. T. Cheng, Z. Xu, H. Yang, S. Hong ve J. P. Leitao, Analysis of effect of rainfall patterns on urban flood process by coupled hydrological and hydrodynamic modeling. Journal of Hydrologic Engineering, 25(1), 04019061, 2020. https://doi.org/10.1061/(ASCE)HE.19435584.0001867
22. A. Y. Barrera-Animas, L. O. Oyedele, M. Bilal, T. D. Akinosho, J. M. D. Delgado ve L. A. Akanbi, Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting. Machine Learning with Applications, 7, 100204, 2022. https://doi.org/10.1016/j.mlwa.2021.100204
23. S. D. Latif, N. A. B. Hazrin, C. H. Koo, J. L. Ng, B. Chaplot, Y. F. Huang, vd., Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches. Alexandria Engineering Journal, 82, 16–25, 2023. https://doi.org/10.1016/j.aej.2023.09.060
24. H. I. Erdal ve O. Karakurt, Advancing monthly streamflow prediction accuracy of CART models using ensemble learning paradigms. Journal of Hydrology, 477, 119–128, 2013.https://doi.org/ 10.1016/j.jhydrol.2012.11.015
25. D. Patil, S. Badarpura, A. Jain ve A. Gupta, Rainfall prediction using linear approach & neural networks and crop recommendation based on decision tree. International Journal of Engineering Research & Technology (IJERT), 2020.
26. H. T. Babacan ve Ö. Yüksek, Investigation of climate change impacts on daily streamflow extremes in Eastern Black Sea Basin, Turkey. Physics and Chemistry of the Earth, 134, 103599, 2024.https://doi.org/10.1016/j.pce.2024.103 599
27. J. L. Ng, H. C. Aik, J. C. L. Jin, N. I. F. M. Noh, M. Abdulkareem, D. Syamsunur, vd., Machine learning-based approach for filling gaps in streamflow data. Semarak International Journal of Machine Learning, 5(1), 46–63, 2025. https://doi.org/ 10.37934/sijml.5.1.4663a
28. H. T. Babacan, Examining streamflow in lower and upper basins due to climate change and the effects of forest fires: The Manavgat basin, Türkiye. Hydrological Sciences Journal, 70(5), 818–832, 2025. https://doi.org/10.1080/02626667.2025.2461081
29. C. W. Granger, Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37(3), 424–438, 1969. https://doi.org/10.2307/19127911969
30. B. Bergougui ve M. A. Zambrano-Monserrate, Assessing the relevance of the Granger non-causality test for energy policymaking: Theoretical and empirical insights. Energy Strategy Reviews, 59, 101743, 2025. https://doi.org/10.1016/j.esr.2025.101743
31. D. A. Dickey ve W. A. Fuller, Distribution of the estimators for autoregressive time series with a unit root. Journal of the American Statistical Association, 74(366a), 427–431, 1979. https://doi.org/10.1080/01621459.1979.10482531
32. W. Wang, P. H. A. J. M. Van Gelder ve J. K. Vrijling, Trend and stationarity analysis for streamflow processes of rivers in western Europe in the 20th century. Proceedings: IWA International Conference on Water Economics, Statistics, and Finance, 810, 2005.
33. Ö. Yüksek, H. T. Babacan ve F. Saka, Yağış-akış modellemesinde optimum yapay sinir ağı yapısının araştırılması. Türk Hidrolik Dergisi, 2(1), 31–37, 2018.
34. M. J. Bahmani, Z. Kayhomayoon, S. G. Milan, F. Hassani, M. Malekpoor ve R. Berndtsson, Development of a new hybrid model to enhance streamflow estimation using artificial neural network and reptile search algorithm. Scientific Reports, 15, 6098, 2025.https://doi.org/10.1038/s41598-025-90550-x
35. R. S. Oyarzabal, L. B. L. Santos, C. Cunningham, vd., Forecasting drought using machine learning: A systematic literature review. Natural Hazards, 121, 9823–9851, 2025. https://doi.org/10.1007/s11069-025-07195-2
36. J. J. More, The Levenberg–Marquardt algorithm: Implementation and theory. In Numerical Analysis: Proceedings of the Biennial Conference held at Dundee, June 28–July 1, 1977 (pp. 105–116). Springer, Berlin, Heidelberg, 2006.
37. A. Yadav, P. Chithaluru, A. Singh, D. Joshi, D. H. Elkamchouchi, C. M. Pérez-Oleaga ve D. Anand, An enhanced feed-forward back propagation Levenberg–Marquardt algorithm for suspended sediment yield modeling. Water, 14(22), 3714, 2022. https://doi.org/10.3390/w14223714
38. L. Latifoğlu ve M. Özger, A novel approach for high-performance estimation of SPI data in drought prediction. Sustainability, 15(19), 14046, 2023. https://doi.org/10.3390/su151914046
39. J. Drisya, D. S. Kumar ve T. Roshni, Hydrological drought assessment through streamflow forecasting using wavelet enabled artificial neural networks. Environment, Development and Sustainability, 23, 3653–3672, 2021.https://doi.org/10.1007/s10668-020-00737-7
40. L. Breiman, J. Friedman, R. A. Olshen ve C. J. Stone, Classification and Regression Trees. Routledge, 2017.https://doi.org/10.1201/9781315139470
41. D. P. Adeke ve S. N. Mugume, A methodology for development of flood-depth-velocity damage functions for improved estimation of pluvial flood risk in cities. Journal of Hydrology, 132736, 2025. https://doi.org/10.1016/j.jhydrol.2025.132736
42. H. T. Babacan, Ö. Yüksek ve F. Saka, Investigation of impact of vapor pressure on hybrid streamflow prediction modeling. KSCE Journal of Civil Engineering, 27, 890–902, 2023. https://doi.org/10.1007/s12205-022-0488-4
43. E. E. Başakın, Ö. Ekmekcioğlu, H. Çıtakoğlu, vd., A new insight to the wind speed forecasting: Robust multi-stage ensemble soft computing approach based on pre-processing uncertainty assessment. Neural Computing and Applications, 34, 783–812, 2022. https://doi.org/10.1007/s00521-021-06424-6
44. H. Citakoğlu ve Ö. Coşkun, Comparison of hybrid machine learning methods for the prediction of short-term meteorological droughts of Sakarya Meteorological Station in Turkey. Environmental Science and Pollution Research, 29, 75487–75511, 2022. https://doi.org/10.1007/s11356-022-21083-3
45. H. Citakoğlu, Comparison of artificial intelligence techniques for prediction of soil temperatures in Turkey. Theoretical and Applied Climatology, 130, 545–556, 2017. https://doi.org/10.1007/s00704-016-1914-7
46. C. R. Brydges, Effect size guidelines, sample size calculations, and statistical power in gerontology. Innovation in Aging, 3(4), igz036, 2019., https://doi.org/10.1093/geroni/igz036