Suda bulanıklık tahmini için genetik programlama: saatlik ve aylık senaryolar

Öz

Bu çalışmada, içme suyu dağıtım şebekelerinde bulanıklık tahmini için klasik genetik programlama (GP) ve gen ekspresyon programlama (GEP) olmak üzere iki GP yönteminin kalibrasyonu ve değerlendirilmesi sunulmaktadır. İlk yöntem olan Klasik GP, Bihać kentinin (Bosna Hersek) ana su kaynağındaki bulanıklığı modellemek için kullanılmıştır. İkinci yöntem olan GEP, Türkiye’de bulunan Antalya ili su izleme istasyonlarından birinde bulanıklık modellemesi için kullanılmıştır. Birincisinde, 2006-2018 döneminde kaydedilen ortalama aylık bulanıklık ölçümlerine dayanarak çeşitli tahmin modelleri oluşturuldu. İkincisinde ise, düşük bulanıklık dönemindeki Antalya-Gürkavak İstasyonu'ndaki saatlik ölçümler kullanılmıştır. Sonuçlar, bulanıklık modellemesinin, özellikle optimum gecikme süreleri ve girdi parametrelerinin belirlenmesi bağlamında, dikkatli veri analizi gerektiren zorlu bir görev olduğunu göstermiştir. Antalya su temin hattında debi ve bulanıklık arasında anlamlı bir ilişki bulunamamıştır. Bulunan sonuçlar ayrıca sunulan algoritmalara dayanan tahmin modellerinin geleneksel regresyon yaklaşımına kıyasla daha doğru tahminler sağlayabileceğini göstermiştir. Bulgular, yüksek kalitede su temininin hedeflendiği sürdürülebilir kentsel su yönetimi için kullanışlıdır.

Anahtar Kelimeler

• Genetik programlama,Gen ekspresyon programlama,Bulanıklık,İçme suyu

Genetic programming for turbidity prediction: hourly and monthly scenarios

Abstract

This paper presents the calibration and evaluation of two genetic programming (GP) methods, namely classis GP and gene expression programming (GEP) for turbidity prediction at drinking water distribution networks. Classic GP first method was used to model turbidity at the main water source of Bihac town (Bosnia and Herzegovina) and GEP second method was used to model turbidity at one of the water monitoring stations of city of Antalya, Turkey. The former various predictive models were built based on the mean monthly turbidity measurements recorded during 2006-2018. Moreover, hourly measurements at Gürkavak Station during low turbidity period were used. The results showed that the modelling of turbidity is a challenging task which required careful data analysis especially in the context of determining the optimum lag times/input parameters. No meaningful relation between discharge and turbidity was found at Antalya water supply pipeline. The results also indicated that the predictive models based on the presented algorithms may provide more accurate estimations in comparison to the traditional regression approach. The findings are useful for sustainable urban water management whereby a high quality water supply is aimed.

Keywords

• Genetic programming,Gene expression programming,Turbidity,Drinking water

References

1. Nebbache S, Feeny V, Poudevigne I, Alarda D. “Turbidity and nitrate transfer in karstic aquifers in rural areas: the brionne basin case-study”. Journal of Environmental Management, 62(4), 389-98, 2001.
2. Najah A, Elshafie A, Karim, OA, Jaffar O. “Prediction of Johor River water quality parameters using artificial neural networks”. European Journal of Scientific Research, 28(3), 422-435, 2009.
3. Makić H, Koričić A, Hrnjica B. “Development of a model of predicting the sweetness level by using genetic programming”. International Conference SVAROG, Banja Luka, Bosnia and Herzegovina, 22-23 May 2015.
4. Makić H, Ibrahimpašić J, Hrnjica B. “Modeling and forecasting of some una water quality parameters by genetic programming”. 11th International Scientific Conference RIM, Dubrovnik, Croatia, 2-5 October 2015.
5. Danandeh Mehr A, Nourani V. “A pareto-optimal moving average-multigene genetic programming model for rainfall-runoff modelling”. Environmental Modelling and Software, 92, 239-51, 2017.
6. Olyaie E, Abyaneh HZ, Danandeh Mehr A. “A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in delaware river”. Geoscience Frontiers, 8(3), 517-27 2016.
7. Mulia IE, Harold T, Roopsekhar K, Pavel T. “Hybrid ANN-GA model for predicting turbidity and chlorophyll-a concentrations”. Journal of Hydro-Environment Research, 7(4), 279-99, 2013.
8. Ogston SA, Field EM. “Predictions of turbidity due to enhanced sediment resuspension resulting from sea-level rise on a fringing coral reef: evidence from Molokai, Hawaii”. Journal of Coastal Research, 26, 1027-37, 2010.

9. Nakao K, Hajime N, Shuichi T. “Inverse analysis to reconstruct hydraulic conditions of non-steady turbidity currents based on multiple grain-size classes: application to an ancient turbidite of the kiyosumi formation of the Awa Group, Boso Peninsula, and Central Japan”. JPGU-AGU Joint Meeting, Mkuhary Messe, Japan, 20-25 May 2017.
10. Wang Y, Wang P, Bai Y, Tian Z, Li J, Shao X, Mustavich LF, Li BL. “Assessment of surface water quality via multivariate statistical techniques: a case study of the songhua river harbin region, China”. Journal of Hydro-Environment Research, 7(1), 30-40, 2013.
11. Iglesias C, Martínez Torres J, García Nieto PJ, Alonso Fernández JR, Díaz Muñiz C, Piñeiro JI, Taboada J. “Turbidity prediction in a river basin by using artificial neural networks: a case study in northern Spain”. Water Resources Management, 28(2), 319-31, 2014.
12. Huang M, Tian D, Liu H, Zhang C, Yi X, Cai J, Ying, G. “A hybrid fuzzy wavelet neural network model with self-adapted fuzzy c -means clustering and genetic algorithm for water quality prediction in rivers”. Complexity, 8241342, 1-11, 2018.
13. Kazemi E, Mounce S, Husband S, Boxall J. “Predicting turbidity in water distribution trunk mains using nonlinear autoregressive exogenous artificial neural networks”. 13th International Conference on Hydroinformatics, Palermo, Italy, 16 July 2018.
14. Koven W, Gisbert E, Nixon O, Solovyev MM, Gaon, A, Allon G, Rosenfeld H. “The effect of algal turbidity on larval performance and the ontogeny of digestive enzymes in the grey mullet (Mugil cephalus)”. Comparative Biochemistry and Physiology -Part A : Molecular and Integrative Physiology, 228, 71-80, 2019.
15. Savary M, Johannet A, Massei N, Dupont JP, Hauchard E. Limits in Using Multiresolution Analysis to Forecast Turbidity by Neural Networks. Case Study on the Yport Basin, Normandie-France. In: Bertrand C, Denimal S, Steinmann M, Renard P. (Eds) Eurokarst 2018, Besançon. Advances in Karst Science. Springer, Cham, 2019.
16. Wang JD, Li PY, Zhang YM, Qi, WG. “River water turbidity forecasting based on phase space reconstruction and support vector regression”. 2010 International Conference on Intelligent Computation Technology and Automation, ICICTA, Changsha, China, 11-12 May 2010.
17. Danandeh Mehr A, Nourani V, Kahya E, Hrnjica B, Sattar A M, Yaseen ZM. “Genetic programming in water resources engineering: a state-of-the-art review”. Journal of Hydrology, 566, 643-667, 2018.
18. Hrnjica B, Danandeh Mehr A. Optimized Genetic Programming Applications: Emerging Research and Opportunities. Hershey, USA, IGI Global, 2019.
19. Ferreira C. “Gene expression programming: a new adaptive algorithm for solving problems”. Complex Systems, 13(2), 87-129, 2001.
20. Danandeh Mehr A, Nourani V, Hrnjica B, Molajou A. “A binary genetic programing model for teleconnection identification between global sea surface temperature and local maximum monthly rainfall events”. Journal of Hydrology, 555, 397-406, 2017.