Akıllı Sulamayı Desteklemek İçin Uydu Tabanlı Makine Öğrenmesi Yaklaşımlarıyla Yağış Tahmini: Ankara ve Samsun Örneği

Öz

Tarım, su yönetimi ve afet hazırlığı açısından doğru yağış tahminleri kritik öneme sahiptir ve artan iklim belirsizliği bu gereksinimi daha da güçlendirmektedir. Geleneksel yöntemler, yağışın doğrusal olmayan ve yüksek değişkenlik gösteren yapısını, özellikle yerel ölçekte, yeterince temsil edememektedir. Bu çalışma, akıllı sulama sistemlerini desteklemek amacıyla Türkiye’de Ankara ve Samsun şehirleri için günlük yağış tahmininde makine öğrenmesi tekniklerinin etkinliğini incelemektedir. PERSIANN uydu verisi (2020–2024) kullanılarak oluşturulan zaman serileri; gecikmeli değerler, hareketli istatistikler, kurak dönem indeksleri ve mevsimsel kodlamalar ile zenginleştirilmiştir. Doğrusal regresyon, Rastgele Orman, SVR, Gradyan Artırma ve XGBoost modelleri karşılaştırmalı olarak değerlendirilmiştir. Bulgular, model performansının hem seçilen algoritmaya hem de iklim koşullarına bağlı olarak değiştiğini göstermektedir. SVR en düşük ortalama mutlak hatayı üretirken, aşırı koşullarda kararsız kalmıştır. XGBoost ise büyüklük ve gerçekleşme tahminlerinde daha dengeli sonuçlar sağlamıştır. Hiçbir modelin tüm senaryolarda üstün olmadığı görülmüş, bu durum ensemble ve hibrit yaklaşımların gerekliliğini ortaya koymuştur. Çalışma, Türkiye’de şehir ölçeğinde ML tabanlı yağış tahminine sistematik bir katkı sunmakta ve uydu verileri ile uygulama odaklı modelleri bütünleştirmektedir. Ancak nadir olayların modellenmesi, yorumlanabilirlik ve hesaplama verimliliği önemli açık problemler olarak devam etmektedir.

Anahtar Kelimeler

• Yağış tahmini
• makine öğrenmesi
• akıllı sulama
• PERSIANN veri seti
• şehir ölçeğinde tahmin

Satellite-Driven Machine Learning Approaches for Rainfall Forecasting in Support of Smart Irrigation: The Case of Ankara and Samsun

Öz

Accurate rainfall forecasting is essential for agriculture, water management, and disaster preparedness, and its importance is further amplified by increasing climate variability. Traditional approaches often fail to adequately capture the nonlinear and highly variable nature of rainfall, particularly at the local scale. This study investigates the effectiveness of machine learning techniques for daily rainfall prediction in Ankara and Samsun, Türkiye, to support smart irrigation systems. Rainfall time series derived from the PERSIANN satellite dataset (2020–2024) were enriched with lagged values, rolling statistics, dry-spell indices, and seasonal encodings. Multiple models, including Linear Regression, Random Forest, Support Vector Regression (SVR), Gradient Boosting, and XGBoost, were comparatively evaluated. The findings indicate that model performance varies depending on both the selected algorithm and climatic conditions. SVR achieved the lowest mean absolute error but exhibited instability under extreme conditions, whereas XGBoost provided more balanced performance in both magnitude and occurrence prediction. No single model consistently outperformed others, highlighting the necessity of ensemble and hybrid approaches. This study presents a systematic city-scale evaluation of ML-based rainfall forecasting in Türkiye, integrating satellite-derived data with application-oriented modeling. However, challenges remain in modeling rare events, improving interpretability, and ensuring computational efficiency for real-time applications.

Anahtar Kelimeler

• Rainfall forecasting
• machine learning
• smart irrigation
• PERSIANN dataset
• city-scale forecasting

Kaynakça

1. C. Liyew, H.A. Melese, Machine learning techniques to predict daily rainfall amount, J. Big Data 8 (2021). https://doi.org/10.1186/s40537-021-00545-4.
2. V. Kumar, N. Kedam, K.V. Sharma, K. Khedher, A.E. Alluqmani, A Comparison of Machine Learning Models for Predicting Rainfall in Urban Metropolitan Cities, Sustainability (2023). https://doi.org/10.3390/su151813724.
3. K. Bartwal, N. Pathak, J. Alexander, M. Aeri, S. Dhondiyal, S. Awasthi, Rainfall Prediction Using Machine Learning, 2024 2nd Int. Conf. Disruptive Technol. (2024) 582–588. https://doi.org/10.1109/ICDT61202.2024.10489249.
4. M. Hassan, M. Rony, M.A.R. Khan, M.M. Hassan, F. Yasmin, A. Nag, T.H. Zarin, A.K. Bairagi, S. Alshathri, W. El-Shafai, Machine Learning-Based Rainfall Prediction: Unveiling Insights and Forecasting for Improved Preparedness, IEEE Access 11 (2023) 132196–132222. https://doi.org/10.1109/ACCESS.2023.3333876.
5. M. Taware, S. Navale, Rainfall Prediction using Machine learning For University/Institute, INTERANTIONAL J. Sci. Res. Eng. Manag. (2025). https://doi.org/10.55041/ijsrem43428.
6. O. Wani, S.S. Mahdi, M. Yeasin, S. Kumar, A. Gagnon, F. Danish, N. Al-Ansari, S. El-Hendawy, M. Mattar, Predicting rainfall using machine learning, deep learning, and time series models across an altitudinal gradient in the North-Western Himalayas, Sci. Rep. 14 (2024). https://doi.org/10.1038/s41598-024-77687-x.
7. S. Sreenivasu, S. Rafi, V.V.A.S. Lakshmi, S. Rao, C. Rajani, Rainfall Prediction Using Machine Learning, 2024 2nd Int. Conf. Recent Trends Microelectron. Autom. Comput. Commun. Syst. (2024) 140–149. https://doi.org/10.1109/ICMACC62921.2024.10894486.
8. S. Latif, N.A.B. Hazrin, C.H. Koo, J.L. Ng, B. Chaplot, Y.F. Huang, A. El-Shafie, A.N. Ahmed, Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches, Alexandria Eng. J. (2023). https://doi.org/10.1016/j.aej.2023.09.060.

9. S. Cramer, M. Kampouridis, A. Freitas, A. Alexandridis, An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives, Expert Syst. Appl. 85 (2017) 169–181. https://doi.org/10.1016/j.eswa.2017.05.029.
10. J. Díez-Sierra, M. Del Jesus, Long-term rainfall prediction using atmospheric synoptic patterns in semi-arid climates with statistical and machine learning methods, J. Hydrol. 586 (2020) 124789. https://doi.org/10.1016/j.jhydrol.2020.124789.
11. D.A. Sachindra, K. Ahmed, M.M. Rashid, S. Shahid, B.J.C. Perera, Statistical downscaling of precipitation using machine learning techniques, Atmos. Res. 212 (2018) 240–258. https://doi.org/10.1016/J.ATMOSRES.2018.05.022.
12. S. Makridakis, E. Spiliotis, V. Assimakopoulos, Statistical and Machine Learning forecasting methods: Concerns and ways forward, PLoS One 13 (2018). https://doi.org/10.1371/journal.pone.0194889.
13. W. Ridwan, M. Sapitang, A. Aziz, K.F. Kushiar, A. Ahmed, A. El-Shafie, Rainfall forecasting model using machine learning methods: Case study Terengganu, Malaysia, Ain Shams Eng. J. (2020). https://doi.org/10.1016/j.asej.2020.09.011.
14. J. Diez-Sierra, M. del Jesus, Long-term rainfall prediction using atmospheric synoptic patterns in semi-arid climates with statistical and machine learning methods, J. Hydrol. 586 (2020) 124789. https://doi.org/https://doi.org/10.1016/j.jhydrol.2020.124789.
15. J. Wang, R. Wong, M. Jun, C. Schumacher, R. Saravanan, C. Sun, Rainfall prediction: A, Environ. Res. Commun. 3 (2021). https://doi.org/10.1088/2515-7620/ac371f.
16. A.Y. Barrera-Animas, L.O. Oyedele, M. Bilal, T.D. Akinosho, J.M.D. Delgado, L. Àkànbí, L.A. Akanbi, Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting, Mach. Learn. with Appl. 7 (2022) 100204. https://doi.org/10.1016/j.mlwa.2021.100204.
17. A.U. Rahman, S. Abbas, M. Gollapalli, R. Ahmed, S. Aftab, M. Ahmad, M.A. Khan, A. Mosavi, Rainfall Prediction System Using Machine Learning Fusion for Smart Cities, Sensors 22 (2022) 1–15. https://doi.org/10.3390/s22093504.
18. F.R. Aderyani, S. Jamshid Mousavi, F. Jafari, Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR, LSTM and CNN, J. Hydrol. 614 (2022) 128463. https://doi.org/https://doi.org/10.1016/j.jhydrol.2022.128463.
19. S.D. Latif, N. Alyaa Binti Hazrin, C. Hoon Koo, J. Lin Ng, B. Chaplot, Y. Feng Huang, A. El-Shafie, A. Najah Ahmed, Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches, Alexandria Eng. J. 82 (2023) 16–25. https://doi.org/https://doi.org/10.1016/j.aej.2023.09.060.
20. V. Kumar, N. Kedam, O. Kisi, S. Alsulamy, K. Khedher, M.A. Salem, A Comparative Study of Machine Learning Models for Daily and Weekly Rainfall Forecasting, Water Resour. Manag. (2024). https://doi.org/10.1007/s11269-024-03969-8.
21. A. Rahman, S. Abbas, M. Gollapalli, R. Ahmed, S. Aftab, M. Ahmad, M.A. Khan, A. Mosavi, Rainfall Prediction System Using Machine Learning Fusion for Smart Cities, Sensors 22 (2022). https://doi.org/10.3390/s22093504.
22. K. Hsu, X. Gao, S. Sorooshian, H. V Gupta, Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks, J. Appl. Meteorol. 36 (1997) 1176–1190. https://doi.org/https://doi.org/10.1175/1520-0450(1997)036<1176:PEFRSI>2.0.CO;2.
23. H. Ashouri, K.-L. Hsu, S. Sorooshian, D.K. Braithwaite, K.R. Knapp, L.D. Cecil, B.R. Nelson, O.P. Prat, PERSIANN-CDR: Daily Precipitation Climate Data Record from Multisatellite Observations for Hydrological and Climate Studies, Bull. Am. Meteorol. Soc. 96 (2015) 69–83. https://doi.org/https://doi.org/10.1175/BAMS-D-13-00068.1.
24. D. Mehr, B. Vaheddoost, Identification of the trends associated with the SPI and SPEI indices across Ankara, Turkey, Theor. Appl. Climatol. 139 (2019) 1531–1542. https://doi.org/10.1007/s00704-019-03071-9.
25. M. Abbasnia, H. Toros, Trend analysis of weather extremes across the coastal and non-coastal areas (case study: Turkey), J. Earth Syst. Sci. 129 (2020) 1–13. https://doi.org/10.1007/s12040-020-1359-3.
26. M. Karabulut, M. Gürbüz, H. Korkmaz, Precipitation and Temperature Trend Analyses in Samsun, (2008). https://consensus.app/papers/precipitation-and-temperature-trend-analyses-in-samsun-karabulut-gürbüz/ebacd0cb90c45f7295a561cd6fd454df/.
27. F. Sarış, D. Hannah, W. Eastwood, Spatial variability of precipitation regimes over Turkey, Hydrol. Sci. J. 55 (2010) 234–249. https://doi.org/10.1080/02626660903546142.
28. E.C.L. De Oliveira, E.C. De Carvalho, E. Jesus, R. De Lima Rocha, H.M. Arruda, R.C. De Oliveira Alves, R.G. Tedeschi, A statistical and machine learning approach for monthly precipitation forecasting in an Amazon city, Front. Earth Sci. (2025). https://doi.org/10.3389/feart.2025.1589753.
29. R. Nirranjana, R. Aishwarya, S. Tejshree, K.S. Gayathri, S. Natarajan, P. Thirunavukkarasu, Rainfall Forecasting Model for Amaravathi Basin Using Machine Learning Approach, J. Inst. Eng. Ser. A (2025). https://doi.org/10.1007/s40030-025-00914-9.
30. E. Vivas, L.B. De Guenni, H. Allende-Cid, R. Salas, Deep Lagged-Wavelet for monthly rainfall forecasting in a tropical region, Stoch. Environ. Res. Risk Assess. 37 (2022) 831–848. https://doi.org/10.1007/s00477-022-02323-x.
31. A. Agrawal, A. Adke, V. Hood, R. Bambale, P. Shelke, Forecasting Rainfall Utilizing Simple Linear Regression, 2024 ASU Int. Conf. Emerg. Technol. Sustain. Intell. Syst. (2024) 1348–1352. https://doi.org/10.1109/ICETSIS61505.2024.10459620.
32. D.Ganesh, Mrs.Pasupuleti, V. Ramana, V. Ramakrishna, M.J. Reddy, M.V. Ubbala, T.Reena, Application of Multi Linear Regression Model for Predicting Heavy Rainfall, 2024 Int. Conf. Commun. Comput. Energy Effic. Technol. (2024) 273–278. https://doi.org/10.1109/I3CEET61722.2024.10993556.
33. S. Sarkar, A. Srivastava, E.A. Kaur, Prediction Rainfall with Regression Analysis, Int. J. Res. Appl. Sci. Eng. Technol. (2023). https://doi.org/10.22214/ijraset.2023.49852.
34. R. Grover, S. Sharma, Impact of Climate Change on Rainfall Pattern by using Ridge Regression Analysis, 2024 Int. Conf. Comput. Intell. Comput. Appl. 1 (2024) 558–563. https://doi.org/10.1109/ICCICA60014.2024.10585166.
35. T. Lee, Y. Kong, V. Singh, The more the better or the less the better: LASSO versus random forest in forecasting seasonal precipitation for drought management, Mach. Learn. Sci. Technol. 6 (2025). https://doi.org/10.1088/2632-2153/adbe24.
36. T. Lee, Y. Kong, J.-H. Lee, H.-C. Yoon, Spring precipitation forecasting with exhaustive searching and LASSO using climate teleconnection for drought management, Clim. Dyn. (2023). https://doi.org/10.1007/s00382-023-06983-5.
37. P. Jinashree, R. PoojaD, M. Meghana, P. AishwaryaG, K. SiddharthB, Rainfall Prediction Using LASSO Regression, J. Emerg. Technol. Innov. Res. 8 (2021). https://consensus.app/papers/rainfall-prediction-using-lasso-regression-jinashree-siddharthb/09a92d6ed8a4586eb4346cbb05b5b36a/.
38. D. Sharma, P. Rattan, Rainfall Prediction using Random Forest and XGBoost-A comparative study, 2024 5th Int. Conf. Data Intell. Cogn. Informatics (2024) 1348–1353. https://doi.org/10.1109/ICDICI62993.2024.10810907.
39. A. Siswadi, H. Suprapto, P. Musa, T.D.S. Margianto, B. Wardijono, E.P. Wibowo, Evaluating Rainfall Prediction Models: A Comprehensive Analysis of Linear Regression, Gradient Boosting, and Random Forest in Multi-Location Data Sets, 2024 Ninth Int. Conf. Informatics Comput. (2024) 1–7. https://doi.org/10.1109/ICIC64337.2024.10957037.
40. A. Rahimi, N.K. Yashooa, A.N. Ahmed, M. Sherif, A. El-Shafie, Different Time-Increment Rainfall Prediction Models: a Machine Learning Approach Using Various Input Scenarios, Water Resour. Manag. (2024). https://doi.org/10.1007/s11269-024-04040-2.
41. J.-G. Dong, W. Zeng, L. Wu, J.-S. Huang, T. Gaiser, A. Srivastava, Enhancing short-term forecasting of daily precipitation using numerical weather prediction bias correcting with XGBoost in different regions of China, Eng. Appl. Artif. Intell. 117 (2023) 105579. https://doi.org/10.1016/j.engappai.2022.105579.
42. R.P. Permata, R. Ni’mah, A.T.R. Dani, Daily Rainfall Forecasting with ARIMA Exogenous Variables and Support Vector Regression, J. Varian (2024). https://doi.org/10.30812/varian.v7i2.3202.
43. L.C. Velasco, J.M. Aca-Ac, J.J. Cajes, N.J. Lactuan, S. Chit, Rainfall Forecasting using Support Vector Regression Machines, Int. J. Adv. Comput. Sci. Appl. (2022). https://doi.org/10.14569/ijacsa.2022.0130329.
44. N. Singh, A.S. Tomar, P. Rajput, R. Bhatt, P. Chand, M.W. De Oliveira, D. De Freitas Santos, A machine learning based approach for Rainfall Prediction, Obs. LA Econ. Latinoam. (2025). https://doi.org/10.55905/oelv23n3-033.
45. S. Sikarwar, S. Pandey, S. Kumar, P. Kumar, D. Of, P. Kumar, B. Singh, Optimizing Crop Yield Predictions Using K-Nearest Neighbors Regression: An Analysis of Temperature, Rainfall and Soil pH Influences, 2024 1st Int. Conf. Adv. Comput. Commun. Netw. (2024) 1336–1341. https://doi.org/10.1109/ICAC2N63387.2024.10894947.
46. N. Yu, T. Haskins, Bagging Machine Learning Algorithms: A Generic Computing Framework Based on Machine-Learning Methods for Regional Rainfall Forecasting in Upstate New York, Informatics 8 (2021) 47. https://doi.org/10.3390/INFORMATICS8030047.
47. H. Salehi, M. Sadeghi, S. Golian, P. Nguyen, C. Murphy, S. Sorooshian, The Application of PERSIANN Family Datasets for Hydrological Modeling, Remote Sens. 14 (2022). https://doi.org/10.3390/rs14153675.
48. F. Baig, M. Abrar, H. Chen, M. Sherif, Evaluation of Precipitation Estimates from Remote Sensing and Artificial Neural Network Based Products (PERSIANN) Family in an Arid Region, Remote Sens. 15 (2023). https://doi.org/10.3390/rs15041078.
49. N. Sapkota, K. Khattri, D. Aryal, Modeling Precipitation: A Statistical and Machine Learning Approach, Int. J. Eng. Technol. (2025). https://doi.org/10.3126/injet.v2i2.78616.
50. R. Tedeschi, E.C. De Carvalho, A.N. Neto, C.P.W. Da Costa, J.C.G. De Freitas, R. De Lima Rocha, R.C. De Oliveira Alves, E.C.L. De Oliveira, Multivariable modelling based on statistical and machine learning techniques for monthly precipitation forecasting in the eastern Amazon, Front. Earth Sci. (2025). https://doi.org/10.3389/feart.2025.1576377.
51. K. Jha, P. Kumar, Comparing Different Machine Learning and Deep Learning Models for Daily Rainfall Prediction at Kerala Point Location, 2025 3rd Int. Conf. Device Intell. Comput. Commun. Technol. (2025) 490–495. https://doi.org/10.1109/dicct64131.2025.10986746.