Akım ve Sediment Yük Öngörümü İçin Doğrusal Genetik Programlamanın Uygulanması
Nehirlerin morfolojisini, ekosistemi ve özellikle taşkın olaylarını etkileyen iki ana değişken askıdaki sediment ve günlük akımlardır. Yapay sinir ağları (YSA), bu değişkenleri modellemek ve tahmin etmek için yakın zamanda yapılmış çalışmalarda başarıyla kullanılmıştır. Bununla birlikte, bunlar kapalı yöntemlerdir ve pratik uygulamalarda kolaylıkla kullanılamazlar. Bu makalede, İran'daki iki nehirde bu değişkenleri tahmin etmek üzere açık modeller geliştirmek için doğrusal genetik programlama (DGP) yaklaşımı önerilmiştir. DGP tarafından geliştirilen açık ilişkiler (tahmin kuralları), fiziksel tutarlılığı açısından kontrol edilebilen denklemler veya program kodları şeklindedir. Sonuçlar, global maksimum ve minimum akımları elde etme noktasında, DGP’nin YSA’ya göre daha başarılı olduğunu gerek kalibrasyon gerekse doğrulama aşamalarında hataların karelerinin ortalamasının karekökünün en düşük, verimlilik katsayısının ise daha yüksek olmasını sağlayarak göstermiştir.
STREAMFLOW AND SEDIMENT LOAD PREDICTION USING LINEAR GENETIC PROGRAMMING
Daily flow and suspended sediment discharge are two major hydrological variables that affectrivers’ morphology and ecosystem, particularly during flood events. Artificial neural networks (ANNs)have been successfully used to model and predict these variables in recent studies. However, these areimplicit and cannot be simply used in practice. In this paper, linear genetic programming (LGP) approachhas been suggested to develop explicit models to predict these variables in two rivers in Iran. The explicitrelationships (prediction rules) evolved by LGP take the form of equations or program codes, which canbe checked for its physical consistency. The results showed that the LGP outperforms ANNs to get globalmaximum and minimum discharges providing lowest root mean squared error and higher coefficient ofefficiency both for training and validation periods.
___
- Abrahart, R.J., Anctil, F., Coulibaly, P., et al., (2012) Two decades of anarchy? Emerging
themes and outstanding challenges for neural network modelling of surface hydrology.
Progresses in Physical Geography 36(4), 480-513. doi: 10.1177/0309133312444943
- Aytek, A., and Kisi, O. (2008) A genetic programming approach to suspended sediment
modeling, Journal of Hydrology, 351, 288-298. doi: 10.1016/j.jhydrol.2007.12.005
- Babovic, V., Keijzer, M. (2002) Declarative and preferential bias in GP-based scientific
discovery. Genetic Programming and Evolvable Machines, 3(1), 41-79. Retrieved from
https://link.springer.com/article/10.1023/A:1014596120381
- Danandeh Mehr, A., Kahya, E. (2017) A Pareto-optimal moving average multigene genetic
programming model for daily streamflow prediction, Journal of Hydrology,549, 603-615.
doi: 10.1016/j.jhydrol.2017.04.045
- Danandeh Mehr, A., Nourani, V. (2017) A Pareto-optimal moving average-multigene
genetic programming model for rainfall-runoff modelling. Environmental Modelling &
Software, 92, 239-251. doi: 10.1016/j.envsoft.2017.03.004
- Danandeh Mehr, A., Demirel, M.C. (2016) On the calibration of multi-gene genetic
programming to simulate low flows in the Moselle River. Uludağ University Journal of the
Faculty of Engineering, 21 (2), 365-376. doi: 10.17482/uumfd.278107
- Danandeh Mehr, A., Kahya E., Şahin, A. and Nazemosadat M.J. (2015) Successive-station
monthly streamflow prediction using different ANN algorithms. International Journal of
Environmental Science and Technology, 12 (7): 2191-2200. doi: 10.1007/s13762-014-0613-
0
- Danandeh Mehr, A., Kahya, E. and Yerdelen, C. (2014) Linear genetic programming
application for successive-station monthly streamflow prediction. Computers &
Geosciences, 70, 63-72.16(6), 1318-1330. doi: 10.1016/j.cageo.2014.04.015
- Danandeh Mehr, A., Kahya E. and Olyaie E. (2013) Streamflow prediction using linear
genetic programming in comparison with a neuro-wavelet technique. Journal of Hydrology,
505:240–249. doi: 10.1016/j.jhydrol.2013.10.003
- Francone, D.F. (2001) DiscipulusTM Software Owner’s Manual, Version 3.0 Register
Machine Learning Technologies, Inc., Littleton, Colorado. Retrieved from
https://www.cs.bham.ac.uk/~wbl/biblio/gp-html/francone_manual.html
- Giustolisi, O. (2004) Using genetic programming to determine chezy resistance coefficient
in corrugated channels, Journal of Hydroinformatics, 157-173. doi:
10.2166/hydro.2004.0013
- Guven A, Aytek A, Yuce M. I . and Aksoy H. (2008) Genetic programming-based empirical
model for daily reference evapotranspiration estimation. Clean-Soil AirWater, 36(10-11)
905-912. doi: 10.1002/clen.200800009
- Guven, A. (2009). Linear genetic programming for time-series modeling of daily flow rate,
Journal of Earth System and Science. 118, No. 2, 157-173. doi: 10.1007/s12040-009-0022-9
- Hrnjica, B. and Danandeh Mehr, A. (2019) Optimized Genetic Programming Applications:
Emerging Research and Opportunities, (pp. 1-310). Hershey, PA: IGI Global.
doi:10.4018/978-1-5225-6005-0
- Kisi, O. and Cigizoglu H. K. (2007) Comparision of different ANN techniques in river flow
prediction, Civil engineering and environmental system. vol 24(3), 211-231. doi:
10.1080/10286600600888565
- Koza, J.R., 1992. Genetic Programming: on the Programming of Computers by Means of
Natural Selection. MIT Press, Cambridge, MA, USA.
- Olyaie, E. Zare Abyaneh, H. and Danandeh Mehr, A. (2017). A comparative analysis
among computational intelligence techniques for dissolved oxygen prediction in Delaware
River. doi: 10.1016/j.gsf.2016.04.007
- Ravansalar, M., Rajaee, T., & Kisi, O. (2017). Wavelet-linear genetic programming: A new
approach for modeling monthly streamflow. Journal of Hydrology, 549, 461-475. doi:
10.1016/j.jhydrol.2017.04.018
- Roushangar, K., & Homayounfar, F. (2015). Prediction of Flow Friction Coefficient using
GEP and ANN Methods. International Journal of Artificial Intelligence and Mechatronics,
4(2), 65-68. Retrieved from http://www.ijaim.org/volissues.html?view=publication&task=show&id=140
- Sajikumar, N., & Thandaveswara, B. S. (1999). A non-linear rainfall–runoff model using an
artificial neural network. Journal of hydrology, 216(1-2), 32-55. doi: 10.1016/S0022-
1694(98)00273-X
- Tofiq F.A., Guven, .A (2014) Prediction of design flood discharge by statistical
downscaling and General Circulation Models. Journal of Hydrology, 517, 1145-1153. doi:
10.1016/j.jhydrol.2014.06.028
- Uyumaz, A., Danandeh Mehr A., Kahya E. and Erdem H. (2014) Rectangular side weirs
discharge coefficient estimation in circular channels using linear genetic programming
approach, Journal of Hydroinformatics, 16(6), 1318-1330. doi: 10.2166/hydro.2014.112