Derin Öğrenme, Makine Öğrenmesi ve İstatistiksel Modellerin Yağış ve Sıcaklık Tahmin Performanslarının Karşılaştırılması: Hakkâri İli Örneği

Öz

Bu çalışma, Türkiye'nin güneydoğusundaki Hakkâri bölgesinde aylık ortalama sıcaklık ve toplam yağış tahmini için derin öğrenme (LSTM), makine öğrenmesi (Random Forest) ve istatistiksel (Prophet) modellerin karşılaştırmalı performansını değerlendirmektedir. 1940–2025 dönemine ait ERA5 reanaliz verileri kullanılmış; model doğruluğu hata kareler ortalamasının karekökü (RMSE), ortalama mutlak hata (MAE), belirtme katsayısı (R²), Nash–Sutcliffe verimliliği (NSE) ve Kling–Gupta verimliliği (KGE) olmak üzere beş metrikle karşılaştırılmıştır. 85 yıllık tarihsel iklim kaydının zamansal analizi, tüm mevsimlerde istatistiksel olarak anlamlı ısınma eğilimleri (0,221°C/10 yıl, p < 0,001) ortaya koymaktadır; ilkbahar ısınması 1,578°C/10 yıl (p < 0,001) ile en belirgin mevsimsel eğilimi oluşturmaktadır. Toplam yağıştaki uzun dönemli değişim ihmal edilebilir düzeydedir (+0,60 mm/10 yıl). Kar örtüsü ve evapotranspirasyon doğrudan modellenmediğinden, kar-yağmur faz geçişi ve kuraklık riskine ilişkin yorumlar ampirik sonuç değil, fiziksel olarak olası hidrolojik çıkarımlar olarak sunulmaktadır. Sızıntı önleyici değerlendirme çerçevesinde sıcaklık tahmininde Prophet en yüksek doğruluğu sağlamıştır (RMSE = 1,51°C, MAE = 1,15°C, R² = 0,976, NSE = 0,976, KGE = 0,952). Random Forest ikinci sıradadır (RMSE = 1,96°C, MAE = 1,59°C, R² = 0,960, NSE = 0,960, KGE = 0,839); LSTM daha düşük performans göstermiştir (RMSE = 2,52°C, MAE = 2,08°C, R² = 0,933, NSE = 0,933, KGE = 0,791). Yağış tahmini, sıcaklık tahminine göre belirgin biçimde daha zorlu kalmıştır. Prophet yağışta en iyi performansı sergilemiştir (RMSE = 50,15 mm, MAE = 33,88 mm, R² = 0,601, NSE = 0,601, KGE = 0,681). Random Forest (RMSE = 52,26 mm, MAE = 35,56 mm, R² = 0,567, NSE = 0,567, KGE = 0,672) ve LSTM (RMSE = 53,80 mm, MAE = 36,80 mm, R² = 0,542, NSE = 0,542, KGE = 0,680) benzer ve sınırlı tahmin becerisi göstermiştir. Bu bulgular, sıcaklık gibi güçlü mevsimsellik gösteren değişkenlerin farklı modelleme yaklaşımlarıyla tahmin edilebilirliğini koruduğunu; buna karşılık aylık yağışın, aynı ay bilgisi dışlandığında ve gecikmeli öngörücüler kullanıldığında, sızıntı önleyici koşullar altında yalnızca orta düzeyde tahmin edilebilirlik sergilediğini göstermektedir. Gelecekteki çalışmalar, ek mekânsal öngörücüler, karla ilişkili değişkenler ve hidrometeorolojik göstergelerin dâhil edilmesinden ve ayrıca hibrit derin öğrenme ile topluluk öğrenmesi mimarilerinin test edilmesinden yarar sağlayabilir.

Anahtar Kelimeler

• İklim modelleme
• ERA5 yeniden analiz
• Zaman serisi analizi
• Makine öğrenimi

Destekleyen Kurum

Hakkari Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü

Etik Beyan

Hazırlanan makalede herhangi bir kişi veya kurumla çıkar çatışması bulunmamaktadır.” “Yazarlar, hazırlanan makaleyle ilgili olarak herhangi bir kişi veya kurumla çıkar çatışması bulunmadığını beyan ederler.” “Bu makalenin hazırlanması sırasında, “Google” tarafından geliştirilen “Gemini” adlı yapay zeka aracı, yalnızca dilbilimsel düzeltmeler amacıyla sınırlı ölçüde kullanılmıştır. Bilimsel içerik, analizler ve sonuçlar tamamen yazar(lar)ın sorumluluğundadır.

Teşekkür

Bu çalışma, Hakkari Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından desteklenmiştir (Proje No: FM19BAP).

Comparison of Deep Learning, Machine Learning, and Statistical Models for Precipitation and Temperature Forecasting Performance: A Case Study of Hakkari Province

Öz

This study compares three forecasting approaches for monthly mean temperature and total precipitation over Hakkari, southeastern Turkey: LSTM (deep learning), Random Forest (machine learning), and Prophet (statistical). ERA5 reanalysis data spanning 1940–2025 served as input, and model performance was evaluated using five metrics (RMSE, MAE, R², NSE, and KGE). Analysis of the 85-year ERA5 record reveals statistically significant warming across all seasons (0.221°C/10 years, p < 0.001), with spring warming being the strongest (1.578°C/10 years, p < 0.001). Long-term precipitation change remains negligible (+0.60 mm/10 years). Because snow cover and evapotranspiration were not directly modeled, interpretations related to snow-rain phase shifts and drought risk are treated as physically plausible implications rather than direct empirical conclusions. Under the leakage-safe evaluation, Prophet produced the best temperature performance (RMSE = 1.51°C, MAE = 1.15°C, R2 = 0.976, NSE = 0.976, KGE = 0.952), followed by Random Forest (RMSE = 1.96°C, MAE = 1.59°C, R2 = 0.960, NSE = 0.960, KGE = 0.839) and LSTM (RMSE = 2.52°C, MAE = 2.08°C, R² = 0.933, NSE = 0.933, KGE = 0.791). Precipitation forecasting was consistently more demanding than temperature forecasting. Prophet achieved the best precipitation performance (RMSE = 50.15 mm, MAE = 33.88 mm, R² = 0.601, NSE = 0.601, KGE = 0.681), while Random Forest (RMSE = 52.26 mm, MAE = 35.56 mm, R² = 0.567, NSE = 0.567, KGE = 0.672) and LSTM (RMSE = 53.80 mm, MAE = 36.80 mm, R² = 0.542, NSE = 0.542, KGE = 0.680) showed similar limited skill. These findings suggest that strongly seasonal variables such as temperature remain tractable across modeling frameworks, whereas monthly precipitation exhibits only moderate predictability under leakage-safe conditions when same-month information is excluded and lagged predictors are used. Future studies may benefit from incorporating additional spatial predictors, snow-related variables, and hydrometeorological indicators, as well as testing hybrid deep learning and ensemble learning architectures.

Anahtar Kelimeler

• Climate forecasting
• ERA5 reanalysis
• Time-series analysis
• Machine learning.

Destekleyen Kurum

Hakkari University Scientific Research Projects Coordination Office

Etik Beyan

“There is no conflict of interest with any individual or organisation in relation to this article.” “The authors declare that there is no conflict of interest with any individual or organisation in relation to this article.” “During the preparation of this article, the artificial intelligence tool ‘Gemini’, developed by ‘Google’, was used to a limited extent solely for linguistic corrections. The scientific content, analyses and results are entirely the responsibility of the author(s).

Teşekkür

This study was supported by the Scientific Research Projects Coordination Office of Hakkari University, Türkiye (Project No: FM19BAP).

Kaynakça

1. J. Cifuentes, G. Marulanda, A. Bello, and J. Reneses, “Air Temperature Forecasting Using Machine Learning Techniques: A Review,” Energies, vol. 13, p. 4215, 2020.
2. F. Shah and A. Sharifi, “Climate Models for Predicting Precipitation and Temperature Trends in Cities: A Systematic Review,” Sustain. Cities Soc., vol. 120, p. 106171, 2025.
3. V. S. Yavuz, “Forecasting Monthly Rainfall and Temperature Patterns in Van Province, Türkiye, Using ARIMA and SARIMA Models: A Long-Term Climate Analysis,” J. Water Clim. Change, vol. 16, pp. 800–818, 2025.
4. L. Adil, D. Eckstein, V. Künzel, and L. Schäfer, Climate Risk Index: Who Suffers Most from Extreme Weather Events? Bonn, Germany: Germanwatch, 2025, p. 72.
5. International Water Management Institute (IWMI), IWMI Annual Report 2023. Colombo, Sri Lanka: IWMI, 2024.
6. M. Manucharyan, “Climate Change Impacts on Sustainable Agriculture: Evidence from Armenia,” Unconv. Resour., vol. 6, p. 100159, 2025.
7. OECD, Climate Change, Water and Agriculture: Towards Resilient Systems, OECD Studies on Water. Paris, France: OECD Publishing, 2014.
8. M. M. Raghuwanshi, Y. Katre, A. Sahu, D. Sharma, A. Udapure, and C. Lonarkar, “Weather Prediction with Machine Learning,” Int. J. Innov. Sci. Res. Technol., pp. 3271–3275, 2024.

9. P. Fan, J. Yang, Z. Zhang, N. Zang, Y. Li, and G. Feng, “Summer Precipitation Prediction in Eastern China Based on Machine Learning,” Clim. Dyn., vol. 60, pp. 2645–2663, 2023.
10. S. Gui, Z. Yang, H. Wu, R. Yang, Z. Dong, Y. Yang, and Y. Lian, “Improving the Hindcast of Late Spring-Early Summer Heatwaves in Southeast Asia with Machine Learning Models,” Clim. Dyn., vol. 63, p. 302, 2025.
11. D. Kumar, S. Shekhar, and T. Tewary, “Editorial: AI and Data Analytics for Climate Data Management,” Front. Environ. Sci., vol. 13, 2025.
12. V. Ramachandra, Artificial Intelligence in Climate Science: A State-of-the-Art Review (2020–2025), 2025.
13. R. Sha and T. Guha, “Climate Time Series Prediction with Deep Learning and LSTM,” in Proc. 4th Int. Conf. Smart Electron. Commun. (ICOSEC), Sep. 2023, pp. 1631–1637.
14. K. E. Fahim, L. C. De Silva, and H. Yassin, “Time Series Forecasting of Active Power Using ARIMA, SARIMA and Hybrid Models,” in Proc. Smart Sustain. Develop. Conf. (SSD 2025), S. Singh, B. Dowdeswell, J. Sun, I. Ardekani, F. Mehdipour, and W. Hewage, Eds. Dordrecht, Netherlands: Atlantis Press Int. BV, 2025, vol. 2, pp. 203–219.
15. S. Kumari and P. Muthulakshmi, “SARIMA Model: An Efficient Machine Learning Technique for Weather Forecasting,” Procedia Comput. Sci., vol. 235, pp. 656–670, 2024.
16. Y. Sabzevari and S. Eslamian, “Climate Warming Prediction Using Time Series Analysis: Case Study, Western Iran,” AUT J. Civ. Eng., 2024.
17. T. Balasubramaniam, W. A. Mohotti, K. Sabir, and R. Nayak, “Feature Engineering on Climate Data with Machine Learning to Understand Time-Lagging Effects in Pasture Yield Prediction,” Ecol. Inform., vol. 86, p. 103011, 2025.
18. Y.-J. Kim, S.-J. Lee, H.-S. Jin, I.-A. Suh, and S.-Y. Song, “Comparison of Linear and Nonlinear Statistical Models for Analyzing Determinants of Residential Energy Consumption,” Energy Build., vol. 223, p. 110226, 2020.
19. R. Yang, J. Hu, Z. Li, J. Mu, T. Yu, J. Xia, X. Li, A. Dasgupta, and H. Xiong, “Interpretable Machine Learning for Weather and Climate Prediction: A Review,” Atmos. Environ., vol. 338, p. 120797, 2024.
20. X. Cui, Y. Xu, L. Sun, and T. Yao, “Machine Learning Models for Predicting Rural Residential Carbon Emissions and Optimising Spatial Forms,” Sci. Rep., vol. 15, p. 33111, 2025.
21. T. Hovorushchenko, V. Alekseiko, and V. Levashenko, “Machine Learning Methods’ Comparison for Land Surface Temperatures Forecasting Due to Climate Classification,” in Proc. 1st Int. Workshop Adv. Appl. Inf. Technol. (AdvAIT 2024), CEUR Workshop Proc., Zilina, Slovakia, 2024, vol. 3899, pp. 66–72.
22. S. Saiful and N. B. Wibisono, “Crop Yield Prediction Using Random Forest Algorithm and XGBoost Machine Learning Model,” Int. J. Res. Innov. Soc. Sci., vol. IX, pp. 1983–1994, 2025.
23. Q. Guo, Z. He, and Z. Wang, “Monthly Climate Prediction Using Deep Convolutional Neural Network and Long Short-Term Memory,” Sci. Rep., vol. 14, p. 17748, 2024.
24. Q. Liu, M. Yang, K. Mohammadi, D. Song, J. Bi, and G. Wang, “Machine Learning Crop Yield Models Based on Meteorological Features and Comparison with a Process-Based Model,” Artif. Intell. Earth Syst., vol. 1, 2022.
25. M. Waqas and U. W. Humphries, “A Critical Review of RNN and LSTM Variants in Hydrological Time Series Predictions,” MethodsX, vol. 13, p. 102946, 2024.
26. S. N. H. Bukhari and K. A. Ogudo, “Forecasting Temperature and Rainfall Using Deep Learning for the Challenging Climates of Northern India,” PeerJ Comput. Sci., vol. 11, p. e3012, 2025.
27. F. Z. Che Rose, N. A. K. Rosili, and M. F. Marsani, “Comparison of Machine Learning Model Performance for Predicting the Climate Variables in Johor Bahru, Malaysia,” Sci. Rep., vol. 15, p. 23465, 2025.
28. C. O. De Burgh-Day and T. Leeuwenburg, “Machine Learning for Numerical Weather and Climate Modelling: A Review,” Geosci. Model Dev., vol. 16, pp. 6433–6477, 2023.
29. R. Ranjan and A. Shrivastava, “Evaluating Deep Learning Models for Predicting Climate Change Trends: A Review,” Int. J. Innov. Res. Technol., vol. 11, pp. 2326–2329, 2025.
30. S. Khatri, “Advanced Weather Forecasting with Machine Learning: Leveraging Meteorological Data for Improved Predictions,” Commun. Appl. Nonlinear Anal., vol. 32, pp. 1–16, 2025.
31. H. Hersbach, B. Bell, P. Berrisford, S. Hirahara, A. Horányi, J. Muñoz-Sabater, J. Nicolas, C. Peubey, R. Radu, D. Schepers, et al., “The ERA5 Global Reanalysis,” Q. J. R. Meteorol. Soc., vol. 146, pp. 1999–2049, 2020.
32. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, pp. 1735–1780, 1997.
33. F. Farhangi, A. Sadeghi-Niaraki, J. Safari Bazargani, S. V. Razavi-Termeh, D. Hussain, and S.-M. Choi, “Time-Series Hourly Sea Surface Temperature Prediction Using Deep Neural Network Models,” J. Mar. Sci. Eng., vol. 11, p. 1136, 2023.
34. X. Zhang, Q. Zhang, G. Zhang, Z. Nie, Z. Gui, and H. Que, “A Novel Hybrid Data-Driven Model for Daily Land Surface Temperature Forecasting Using Long Short-Term Memory Neural Network Based on Ensemble Empirical Mode Decomposition,” Int. J. Environ. Res. Public Health, vol. 15, p. 1032, 2018.
35. F. Aksan, Y. Li, V. Suresh, and P. Janik, “CNN-LSTM vs. LSTM-CNN to Predict Power Flow Direction: A Case Study of the High-Voltage Subnet of Northeast Germany,” Sensors, vol. 23, p. 901, 2023.
36. F. Shafiq, A. Zafar, M. U. Ghani Khan, S. Iqbal, A. S. Albesher, and M. N. Asghar, “Extreme Heat Prediction through Deep Learning and Explainable AI,” PLoS One, vol. 20, p. e0316367, 2025.
37. L. Breiman, “Random Forests,” Mach. Learn., vol. 45, pp. 5–32, 2001.
38. G. Ali and W. Robert, “Machine Learning for Temperature Analysis in Ouagadougou: A Random Forest Perspective,” EDRAAK, vol. 2024, pp. 101–105, 2024.
39. Y. He, J. Li, F. Bi, Y. Mao, B. Li, C. Chen, and Y. Chu, “Prediction of Near-Surface Air Temperature at Glacier Region Using ERA5 Data Based on Random Forest Regression Method,” in Proc. 3rd Int. Conf. Geol., Mapping Remote Sens. (ICGMRS), Zhoushan, China, Apr. 2022, pp. 179–182.
40. Q. Ji, X. Jia, L. Jiang, M. Xie, Z. Meng, Y. Wang, and X. Lin, “Contribution of Atmospheric Factors in Predicting Sea Surface Temperature in the East China Sea Using the Random Forest and SA-ConvLSTM Model,” Atmosphere, vol. 15, p. 670, 2024.
41. T. Magesh, C. Sai Pratap, A. Vishal, T. Naveen Kumar, M. Karthikeyan, and S. Iniyan, “Enhanced Accuracy of Weather Forecasting Using Hybrid LSTM and Random Forest Models,” in Proc. Int. Conf. Power, Energy, Control Transm. Syst. (ICPECTS), Oct. 2024, pp. 1–5.
42. W. Zhang, Z. Li, Y. Tian, and L. Liu, “Research on Temperature Prediction Based on RF-LSTM Modeling,” in Proc. 6th Int. Acad. Exchange Conf. Sci. Technol. Innov. (IAECST), Dec. 2024, pp. 873–876.
43. M. G. S. Kenyi and K. Yamamoto, “A Hybrid SARIMA-Prophet Model for Predicting Historical Streamflow Time-Series of the Sobat River in South Sudan,” Discov. Appl. Sci., vol. 6, p. 457, 2024.
44. M. J. A. Shohan, M. O. Faruque, and S. Y. Foo, “Forecasting of Electric Load Using a Hybrid LSTM-Neural Prophet Model,” Energies, vol. 15, p. 2158, 2022.
45. J. Tang, L. Xu, C. Fan, C. Xu, and Y. Ning, “A Short-Term Prediction of Ionospheric TEC Using the RF-Prophet Model for GNSS Stations in China,” Adv. Space Res., vol. 76, pp. 3654–3669, 2025.
46. C. B. Aditya Satrio, W. Darmawan, B. U. Nadia, and N. Hanafiah, “Time Series Analysis and Forecasting of Coronavirus Disease in Indonesia Using ARIMA Model and PROPHET,” Procedia Comput. Sci., vol. 179, pp. 524–532, 2021.
47. J. Tang, Y. Li, D. Yang, and M. Ding, “An Approach for Predicting Global Ionospheric TEC Using Machine Learning,” Remote Sens., vol. 14, p. 1585, 2022.
48. G. Codeluppi, A. Cilfone, L. Davoli, and G. Ferrari, “AI at the Edge: A Smart Gateway for Greenhouse Air Temperature Forecasting,” in Proc. IEEE Int. Workshop Metrol. Agric. Forestry (MetroAgriFor), Nov. 2020, pp. 348–353.
49. Y.-S. Lin, S.-L. Fang, L. Kang, C.-C. Chen, M.-H. Yao, and B.-J. Kuo, “Combining Recurrent Neural Network and Sigmoid Growth Models for Short-Term Temperature Forecasting and Tomato Growth Prediction in a Plastic Greenhouse,” Horticulturae, vol. 10, p. 230, 2024.
50. Y. Dong and H. Ding, “Bayesian Optimization of Hybrid Quantum LSTM in a Mixed Model for Precipitation Forecasting,” Mach. Learn. Sci. Technol., vol. 6, p. 015065, 2025.
51. Y. Li and S. Dev, “Short-Term Precipitation Forecasting Based on BU-LSTM Model in Dublin City, Ireland,” in Proc. 17th Int. Congr. Image Signal Process., BioMed. Eng. Informatics (CISP-BMEI), Oct. 2024, pp. 1–6.
52. A. H. Saputra, I. M. A. Satya, F. P. Sari, and A. Mulya, “Spatial Rain Probabilistic Prediction Performance Using Cost-Sensitive Learning Algorithm,” E3S Web Conf., vol. 464, p. 19001, 2023.
53. Y. Wang and L. Zhang, “Using Long Short-Term Memory (LSTM) to Merge Precipitation Data over Mountainous Area in Sierra Nevada,” 2024.
54. C. J. Gamboa-Villafruela, J. C. Fernández-Alvarez, M. Márquez-Mijares, A. Pérez-Alarcón, and A. J. Batista-Leyva, “Convolutional LSTM Architecture for Precipitation Nowcasting Using Satellite Data,” in Proc. 4th Int. Electron. Conf. Atmos. Sci., Jun. 2021, p. 33.
55. S. Salma, “Hybrid CNN-LSTM Model: Rainfall Analysis and Prediction for Karnataka Region,” 2022.
56. Y. Wang, P. Jia, Z. Shu, K. Liu, and A. R. M. Shariff, “Multidimensional Precipitation Index Prediction Based on CNN-LSTM Hybrid Framework,” 2025.
57. M. Fan, O. Imran, A. Singh, and S. A. Ajila, “Using CNN-LSTM Model for Weather Forecasting,” in Proc. IEEE Int. Conf. Big Data, Dec. 2022, pp. 4120–4125.
58. W. Liu, Y. Wang, D. Zhong, S. Xie, and J. Xu, “ConvLSTM Network-Based Rainfall Nowcasting Method with Combined Reflectance and Radar-Retrieved Wind Field as Inputs,” Atmosphere, vol. 13, p. 411, 2022.
59. Y. Ding, B. Wang, Q. Yang, S. Ren, F. Yang, and L. Sun, “High-Resolution Climate Prediction in Mountainous Terrain Using a ConvLSTM-XGBoost Hybrid Model with Dynamic Bayesian Weighting,” Sci. Rep., vol. 15, p. 36923, 2025.
60. M. S. Islam, M. Shafiuzzaman, G. Mahmud, N. Nowshin, P. Reza, J. Hasan, M. F. Ahamed, M. Nahiduzzaman, M. A. Ayari, and A. Khandakar, “Explainable Deep Learning for Rainfall Prediction: A CNN-XGBoost Hybrid Approach in the Northern Region of Bangladesh,” Neural Comput. Appl., vol. 37, pp. 28125–28160, 2025.
61. V. Khettar, N. Kitratporn, S. Lerk-u-suke, J. Chaiwongsai, P. Jeefoo, and C. Sukawattanavijit, “Indices for Extreme Rainfall Risk Mapping in Thailand Using XGBoost,” 2025.
62. S. A. Putri, G. Darmawan, R. Arisanti, and C. C. Clorinda, “Extreme Gradient Boosting Method Forecasting Rainfall in Lembang District, West Java Province,” Indo-MathEdu Intellect. J., vol. 4, pp. 1959–1972, 2023.
63. T. Tang, D. Jiao, T. Chen, and G. Gui, “Medium- and Long-Term Precipitation Forecasting Method Based on Data Augmentation and Machine Learning Algorithms,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 1000–1011, 2022.
64. X. Lin, J. Fan, Z. J. Hou, and J. Wang, “Machine Learning of Key Variables Impacting Extreme Precipitation in Various Regions of the Contiguous United States,” J. Adv. Model. Earth Syst., vol. 15, p. e2022MS003334, 2023.
65. D. S. Chadha, R. Chauhan, and N. Gupta, “Flood Prediction and Rainfall Analysis Using Light Gradient Boosted Machine,” NeuroQuantology, vol. 20, 2022.
66. L. Pang, Q. Fan, H. Zhang, B. Gong, H. Ye, J. He, J. Wu, H. Li, Q. Zhang, and H. Zhang, “Research on Rainfall and Temperature Forecasting and Correction Technology in Mountainous Microterrain,” in Proc. 13th Annu. Int. Conf. Mater. Sci. Environ. Eng. (MSEE 2025), SPIE, Sep. 2025, vol. 13811, pp. 304–312.
67. T. Tang, Y. Wu, Y. Li, L. Xu, X. Shi, H. Zhao, and G. Gui, “Advanced Machine Learning Ensembles for Improved Precipitation Forecasting: The Modified Stacking Ensemble Strategy in China,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 18, pp. 4242–4254, 2025.
68. H. Zhuang, F. Lehner, and A. T. DeGaetano, “Improved Diagnosis of Precipitation Type with LightGBM Machine Learning,” J. Appl. Meteorol. Climatol., vol. 63, pp. 437–453, 2024.
69. T. Babu, R. R. Nair, and P. K, “Optimized Rainfall Prediction Model Using Optune CatBoost: An Innovative Approach,” in Proc. 3rd Odisha Int. Conf. Electr. Power Eng., Commun. Comput. Technol. (ODICON), Nov. 2024, pp. 1–6.
70. R. Szczepanek, “Daily Streamflow Forecasting in Mountainous Catchment Using XGBoost, LightGBM and CatBoost,” Hydrology, vol. 9, p. 226, 2022.
71. V. Prashanthi, S. Kanakala, D. Borgaonkar, and D. S. Babu, “Rainfall Prediction Using CatBoost Machine Learning Algorithm,” in Proc. Int. Conf. Netw., Multimedia Inf. Technol. (NMITCON), Sep. 2023, pp. 1–5.
72. D. Niu, L. Diao, Z. Zang, H. Che, T. Zhang, and X. Chen, “A Machine-Learning Approach Combining Wavelet Packet Denoising with CatBoost for Weather Forecasting,” Atmosphere, vol. 12, p. 1618, 2021.