Hibrit Parçacık Sürüsü Optimizasyonu ile Geçitli Tekrarlayan Birim Modeli Kullanılarak Nehir Akım Tahmini: Ceyhan Havzası Örneği

Öz

Su kaynaklarının verimli bir şekilde kullanılmasının en önemli yöntemlerinden biri havza bazlı yönetimin etkin bir şekilde gerçekleştirilmesidir. Su kaynaklarının sürdürülebilir olması, nehir akım tahminlerinin önemini ortaya koymaktadır. Bu çalışmada, nehir akım tahminine yardımcı olabilecek hibrit model kullanılmıştır. Derin öğrenme modellerinden olan kapılı tekrarlayan birim ve (GRU) ve parçacık sürüsü algoritması (PSO) hibritlenmiştir. Çalışmada Ceyhan Havzasının farklı kolları üzerinde yer alan Fırnız Deresi ve Aksu Çayı akım gözlem istasyonlara ait 2001-2010 yıllarına ait günlük akış verileri kullanılmıştır. İstasyon verileri kıyaslama modeli (GRU) hibrit model (PSO-GRU) ve klasik yöntemlerden olan lineer regresyon (LR) ile kıyaslanmıştır. Sonuçlar karşılaştırıldığında hibrit modelin kıyaslama ve lineer regresyon modellerine göre daha başarılı sonuçlar verdiği gözlemlenmiştir. Ayrıca değerlendirme kriterlerinden olan RMSE, MAE, MAPE, SD ve R2 değerlerine göre de hibrit model bu başarıyı doğrulamıştır

Anahtar Kelimeler

• parçacık sürüsü algoritması
• nehir akımı
• kapılı tekrarlayan birim

River Flow Forecasting Using the Gated Recurrent Unit Model with Hybrid Particle Swarm Optimization: The Case Study of Ceyhan Basin

Abstract

One of the most important methods of efficient use of water resources is the effective implementation of watershed-based management. The sustainability of water resources reveals the importance of stream flow estimations. In this study, a hybrid model was proposed to river flow estimation. Deep learning methods named, gated recurrent unit (GRU) and particle swarm algorithm (PSO), are hybridized. In the study, daily flow data of the Fırnız River and Aksu River, flow measurement stations, which are located on different branches of the Ceyhan Basin, were used with the timespan of 2001-2010. Benchmark model (GRU) was compared with hybrid model (PSO-GRU) and linear regression (LR) which is one of the classical methods. Once the results were compared, it was observed that the hybrid model was more successful than the comparison and linear regression models. In addition, the hybrid model confirmed this success according to the RMSE, MAE, MAPE, SD and R2 values, which are among the evaluation criteria.

Keywords

• Particle swarm optimization
• stream flow
• gated recurrent unit
• hybrid model

Kaynakça

1. Zhou, S.; Song, C.; Zhang, J.; Chang, W.; Hou, W.; Yang, L. A Hybrid Prediction Framework for Water Quality with Integrated W-ARIMA-GRU and LightGBM Methods. Water 2022, 14, 1322. https://doi.org/10.3390/w14091322 Akdeğirmen, Ö. (2019). SCS Curve Number ve Soil Moisture Accounting Yöntemleriyle HEC-HMS Havza Modellemesi: Alaşehir Havzası Örneği. Yüksek lisans Tezi. İzmir, Türkiye: İzmir Yüksek Teknoloji Üniversitesi.
2. Xu, Z., Zhou, J., Mo, L., Jia, B., Yang, Y., Fang, W., Qin, Z. (2021). A Novel Runoff Forecasting Model Based on the Decomposition-IntegrationPrediction Framework. Water, 13, 3390. https://doi.org/10.3390/ w13233390
3. Bittelli, M., Tomei, F., Pistocchi, A., Flury, M., Boll, J., Brooks, E.S., Antolini, G. (2010). Development and testing of a physically based, three-dimensional model of surface and subsurface hydrology. Adv. Water Resour. 33, 106–122. https://doi.org/10.1016/j.advwatres.2009.10.013
4. Kilinc, H.C.; Haznedar, B. (2022). Hybrid Model for Streamflow Forecasting in the Basin of Euphrates. Water, 14, 80. https://doi.org/10.3390/w14010080
5. Chen, L.; Sun, N.; Zhou, C.; Zhou, J.; Zhou, Y.; Zhang, J.; Zhou, Q. (2018). Flood Forecasting Based on an Improved Extreme Learning Machine Model Combined with the Backtracking Search Optimization Algorithm. Water, 10, 1362. https://doi.org/10.3390/w10101362
6. Sun, N., Zhang, S., Peng, T., Zhang, N., Zhou, J., Zhang, H. (2022). Multi-Variables-Driven Model Based on Random Forest and Gaussian Process Regression for Monthly Streamflow Forecasting. Water, 14, 1828. https://doi.org/10.3390/ w14111828
7. Mosavi, A., Ozturk, P., Chau, K. W. (2018). Flood Prediction Using Machine Learning Models: Literature Review. Water, 10, 1536. https://doi.org/10.3390/w10111536 B. Bunday, Basic Optimization Methods, London: Edward Arnold Ltd, 1984.
8. Çelik, Y., Yıldız, İ., Karadeniz, A. T. (2019). Son Üç Yılda Geliştirilen Metasezgisel Algoritmalar Hakkında Kısa Bir İnceleme, Avrupa Bilim ve Teknoloji Dergisi, 463-477. https://doi.org/10.31590/ejosat.638431

9. Samanataray, S., Sahoo, A. (2021). A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches. KSCE Journal of Civil Engineering, 25(10), 4032–4043. https://doi:10.1007/s12205-021-2223-y Chaudhury, S., Samantaray, S., Sahoo, A., Bhagat, B., Biswakalyani, C., Satapathy, D.P. (2022). Hybrid ANFIS-PSO Model For Monthly Precipitation Forecasting. In: Bhateja, V., Tang, J., Satapathy, S.C., Peer, P., Das, R. (eds) Evolution in Computational Intelligence. Smart Innovation, Systems and Technologies, vol 267. Springer, Singapore. https://doi.org/10.1007/978-981-16-6616-2_33
10. Kırtıl, H. S. (2022). Mobil Lokalizasyon Problemine Uygulanan Yeni Bir Hibrit Metasezgisel Algoritma. Yüksek lisans Tezi. İstanbul, Türkiye: İstanbul Sabahattin Zaim Üniversitesi.
11. Zhang, D., Lindholm, G., Ratnaw, E., R. H. (2018). Use long short-term memory to enhance Internet of Things for combined sewer overflow monitoring. Journal of Hydrology 556: 409-418.
12. Stergiou, K., Karakasidis, T. E. (2021) Application of deep learning and chaos theory for load forecasting in Greece. Neural Computing and Applications.
13. Abdolrasol, M. G. M., M. A. Hannan, S. M. S. Hussain, and T. S. Ustun. (2022). Optimal PI controller based PSO optimization for PV inverter using SPWM techniques. Energy Reports, 8, 1003–1011.
14. Alzerkani, L. A. R. (2022). Control The Maxımum Power Poınt (MPP) During Rapidly Change of Irradıatıon in Partially Shaded Photovoltaic System Using Particle Swarm Optımızation (PSO). Yüksek lisans Tezi. İstanbul, Türkiye: Altınbaş Üniversitesi.
15. Achite, M., Banadkooki, F.B., Ehteram, M. et al. Exploring Bayesian model averaging with multiple ANNs for meteorological drought forecasts. Stoch Environ Res Risk Assess (2022). https://doi.org/10.1007/s00477-021-02150-6
16. Barutçu, İ. Ç. & Erduman, A. (2022). Analysis of the Uncertainty Effect in Power System Losses: Uncertainties of Renewable Energy and Load. Avrupa Bilim ve Teknoloji Dergisi, (35), 62-71. DOI: 10.31590/ejosat.1051410
17. Muhammad, A.U., Li, X., Feng, J. (2019). Using LSTM GRU and Hybrid Models for Streamflow Forecasting. In: Zhai, X., Chen, B., Zhu, K. (eds) Machine Learning and Intelligent Communications. MLICOM 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 294. Springer, Cham. https://doi.org/10.1007/978-3-030-32388-2_44
18. Ahmed, A.A.M., Deo, R.C., Feng, Q. et al. Hybrid deep learning method for a week-ahead evapotranspiration forecasting. Stoch Environ Res Risk Assess 36, 831–849 (2022). https://doi.org/10.1007/s00477-021-02078-x
19. Singh, U.K., Kumar, B., Gantayet, N.K., Sahoo, A., Samantaray, S., Mohanta, N.R. (2022). A Hybrid SVM–ABC Model for Monthly Stream Flow Forecasting. In: Chakravarthy, V.V.S.S.S., Flores-Fuentes, W., Bhateja, V., Biswal, B. (eds) Advances in Micro-Electronics, Embedded Systems and IoT. Lecture Notes in Electrical Engineering, vol 838. Springer, Singapore. https://doi.org/10.1007/978-981-16-8550-7_30
20. Cho, K.; van Merrienboer, B.; Gulcehre, C.; Bahdanau, D.; Bougares, F.; Schwenk, H.; Bengio, Y. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, 25–29 October 2014; 1724–1734.
21. Zhao, X.; Lv, H.; Wei, Y.; Lv, S.; Zhu, X. Streamflow Forecasting via Two Types of Predictive Structure-Based Gated Recurrent Unit Models. Water 2021, 13, 91.
22. Wegayehu, E.B., Muluneh, F. B. Short-Term Daily Univariate Streamflow Forecasting Using Deep Learning Models, Advances in Meteorology, 2022, 1860460, 21.
23. Zhou, S.; Song, C.; Zhang, J.; Chang, W.; Hou, W.; Yang, L. A Hybrid Prediction Framework for Water Quality with Integrated W-ARIMA-GRU and LightGBM Methods. Water 2022, 14, 1322.
24. Kennedy, J.; Eberhart, R. Particle swarm optimization. In Proceedings of the ICNN’95-International Conference on Neural Networks, Perth, WA, Australia, 27 November–1 December 1995; IEEE: Piscataway, NJ, USA, 1995; Volume 4, pp. 1942–1948.
25. Roshanravan, B.; Aghajani, H.; Yousefi, M.; Kreuzer, O. Particle Swarm Optimization Algorithm for Neuro-Fuzzy Prospectivity Analysis Using Continuously Weighted Spatial Exploration Data. Nonrenew. Resour. 2018, 28, 309–325.
26. Chi, S.; Ni, S.; Liu, Z. Back Analysis of the Permeability Coefficient of a High Core Rockfill Dam Based on a RBF Neural Network Optimized Using the PSO Algorithm. Math. Probl. Eng. 2015, 2015, 1–15.
27. Eldem, H. (2014). Karınca koloni optimizasyonu (KKO) ve parçacık sürüsü optimizasyonu (PSO) Algoritmaları Temelli Bir Hiyerarşik Yaklaşım Geliştirilmesi. Yüksek lisans Tezi. Konya, Türkiye: Selçuk Üniversitesi Fen Bilimleri Enstitüsü. Abyaneh, H.Z.; Nia, A.M.; Varkeshi, M.B.; Marofi, S.; Kisi, O. Performance Evaluation of ANN and ANFIS Models for Estimating Garlic Crop Evapotranspiration. J. Irrig. Drain. Eng. 2011, 137, 280–286.
28. Arslan, N.; Sekertekin, A. Application of Long Short-Term Memory neural network model for the reconstruction of MODIS Land Surface Temperature images. J. Atmos. Sol. Terr. Phys. 2019, 194, 105100.
29. Çuhadar, M., Atiş, E. (2019). Drought Analysis in Ceyhan Basin Using Standardized Precipitation Index. Journal of the Institute of Science and Technology, 9, 2303-2312.
30. Tanrıverdi, Ç., Alp, A., Demirkıran, A. R., Üçkardeş, F. (2009). Assessment of surface water quality of the Ceyhan River basin, Turkey. Environmental Monitoring and Assessment, 167(1-4), 175–184. https://doi:10.1007/s10661-009-1040-4 Çuhadar, M. (2019). Mobil Lokalizasyon Problemine Uygulanan Yeni Bir Hibrit Metasezgisel Algoritma. Yüksek lisans Tezi. İstanbul, Türkiye: İstanbul Sabahattin Zaim Üniversitesi. Doktora Tezi. İzmir, Türkiye: Ege Üniversitesi.
31. Koç, K. O. (2019). Phyton Üzerinden Derin Öğrenme Algoritmaları Kullanılarak Deri Görüntüsünden Cilt Hastalıklarının Tespit Edilmesi. Yüksek lisans Tezi. Bolu, Türkiye: Bolu Abant İzeet Baysal Üniversitesi.