مقایسه مدلهای شبکه عصبی موجک، ماشین بردار پشتیبان و برنامه ریزی بیان ژن در تخمین میزان اکسیژن محلول در اب رودخانه ها

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار گروه مهندسی آب، دانشگاه لرستان

2 دانشجو

چکیده

اکسیژن محلول در آب از موثرترین پارامترها در تعیین کیفیت آب رودخانه ها بوده و کنترل آن در رودخانه ها از مهم ترین عوامل توسعه منابع آب هر منطقه است. به همین دلیل در این پژوهش عملکرد مدلهای شبکه عصبی موجک، ماشین بردار پشتیبان و برنامه ریزی بیان ژن را جهت تخمین اکسیژن محلول در آب رودخانه کامبرلند واقع در ایالت تنسی مورد بررسی قرار گرفت. برای این منظور سری زمانی ماهانه شاخص DO رودخانه کامبرلند در طی یک دوره 10 ساله (2006-2016) با استفاده از پارامترهای دبی جریان و دما شبیه سازی شد. معیارهای ضریب همبستگی، ریشه میانگین مربعات خطا و میانگین قدر مطلق خطا برای ارزیابی و عملکرد مدلها مورد استفاده قرار گرفت. نتایج نشان داد ساختارهای ترکیبی در هر سه مدل عملکرد بهتری نسبت به سایر ساختارها ارائه می دهد. همچنین نتایج حاصل از معیارهای ارزیابی نشان داد از بین مدلهای بکار رفته، مدل شبکه عصبی موجک با بیشترین ضریب همبستگی (960/0)، کمترین جذر میانگین مربعات خطا (668/0) و نیز کمترین میانگین قدرمطلق خطا (519/0) را در مرحله صحت سنجی دارا می باشد. در مجموع نتایج نشان داد به لحاظ توانایی بالای شبکه عصبی موجک و حذف نویزهای سری های زمانی در تخمین پارامترهای کیفی آب رودخانه، این مدل می‌تواند، راهکاری مناسب و سریع در مدیریت کیفیت منابع آب و اطمینان از نتایج پایش کیفی و کاهش هزینه های آن مطرح شود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Comparison of wavelet neural network models, support vector machine and gene expression programming in estimating the amount of oxygen dissolved in rivers

نویسنده [English]

  • babak shahinejad 1
1 Assistant Professor   Department of Water Engineering
چکیده [English]

Water-soluble oxygen is one of the most effective parameters in determining the water quality of rivers and its control in the rivers is one of the most important factors for the development of water resources in each region. For this reason, in this study, the performance of wavelet neural network models, support vector machines and gene expression scheduling was investigated to estimate the oxygen dissolved in the water of the Cumberland River in Tennessee. For this purpose, the monthly time series DO of the Cumberland River index were simulated using flow and temperature flow parameters over a 10-year period (2006-2016). The correlation coefficient, root mean square error and mean absolute error value were used for evaluation and performance of the models. The results showed that hybrid structures in all three models offer better performance than other structures. Also, the results of the evaluation criteria showed that the wavelet neural network model with the highest correlation coefficient (0.960), the lowest root mean square error (0.668), and the lowest mean error of error (0.519) in the verification stage were among the applied models. In total, the results showed that in terms of the high ability of wavelet neural network and the elimination of time series noise in the estimation of river water quality parameters, this model could be a suitable and fast way to manage the quality of water resources and ensure the results of quality monitoring and cost reduction.

کلیدواژه‌ها [English]

  • Dissolved oxygen
  • Gene expression programming
  • Wavelet Neural Network
  • Water Quality
  • Support Vector Machine
Alizadeh MJ, Kavianpour MR (2015) Development of wavelet-ANN models to predict water quality parameters in Hilo Bay, Pacific Ocean. Marine Pollution Bulletin 98(1–2):171-8

Banejad H, Kamali M, Amir Moradi K, Olyaei A (2013) Forecasting some of the qualitative parameters of rivers using Wavelet Artificial Neural Network Hybrid (W-ANN) model (case of study: Jajroud river of Tehran and Gharaso river of Kermanshah). Iranian journal of Health and Environment 6(3):277-294 (In Persian)

Chapman D (1992) Water Quality Assessments. Chapman and Hall Ltd, London, UK

Chu HB, Lu WX, Zhang L (2013) Application of artificial neural network in environmental water quality assessment. Journal of Agricultural Science and Technology 15(2):343-356

Dehghani R, Ghorbani MA, Teshnehlab M, Rikhtegar A, Asadi A (2015) Comparison and evalution of Bayesian neural network, gene gramming, support vector machine and multiple expression prolinear regression in river discharge estimation (case study: Sufi Chay Basin). Iranian journal of Irrigation and Water 20(5):66-85 (In Persian)

Dogan E, Lent Sengorur  B, Koklu R (2009) Modeling biological oxygen demand of the Melen River in Turkey using an artificial neural network technique. Journal of Environmental Management 90:1219-35

Eskandari A, Nouri R, Meragi H, Kiaghaderi A (2012) Developing an appropriate model based on artificial neural network and support vector machine for prediction of timely 5 day biochemical oxygen demand. Journal of Ecology 38(1):71-82 (In Persian)

Ferreira C (2001) Gene expression programming: a new adaptive algorithm for solving problems. Complex Systems 13(2):87–129

Ghorbani  MA, Dehghani R (2017) Comparison of Bayesian neural network, artificial neural network gene expression programming in river water quality (case study: Belkhviachay river). Watershed Management Research 8(15):13-24 (In Persian)

Ghorbani MA, Ahmadzadeh  H, Isazadeh M, Terzi  O (2016) A comparative study of artificial neural network (MLP, RBF) and support vector machine models for river flow prediction. Environmental Earth Sciences 75(476):3-14

Ghorbani MA, Azani A, Mahmoudi S (2015) Rainfall-Runoff modeling using hybrid intelligent models. Iran-Water Resources Research 11(2):146-150 (In Persian)

Ghorbani MA, Khatibi R, Asadi H, Yousefi P (2012) Inter-comparison of an evolutionary programming model of suspended sediment time-series whit other local model. INTECH.doi. org/10.5772/47801: 255-282

Ghorbani MA, Salehi A (2011) Use of gene expression planning to study the variation of groundwater quality data with fluctuations in the water level in Isfahan plain. Sixth National Congress on Civil Engineering (In Persain)

Hamel  L (2009) Knowledge discovery with support vector machines. Hoboken, N.J. John Wiley

Khatibi  R, Naghipour L, Ghorbani MA, Aalami MT (2012) Predictability of relative humidity by two artificial intelligence techniques using noisy data from two Californian gauging stations. Neural Computing and Application 23(7):643-941

Kisi O, Karahan M, Sen Z (2006) River suspended sediment modeling using fuzzy logic approach . Hydrol Process 20:4351-4362

Lin JY, Cheng CT, Chau KW (2006) Using support vector machines for long-term discharge prediction. Hydrolog Sci J 51(3):599–612

Liong SY,  Sivapragasam C (2002)  Flood stage forecasting with support vector machines. J Am Water Resour  38(4):173–186

Lopes JF, Dias JM, Cardoso AC, Silva CIV (2005) The water quality of the Ria de Aveiro lagoon, Portugal: from the observations to the implementation of a numerical model. Mar Environ Res 60:594-628

Nagy  H, Watanabe K, Hirano M  (2002)  Prediction of sediment load concentration in rivers using artificial neural network model. Journal of Hydraulics Engineering 128:558-559

Nourani  V,  Kisi  Ö,  Komasi  M (2011)  Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology 402(3): 41–59

Nozari H, Tavakoli F (2017) Evaluation of the efficiency of conventional and computerized methods for reconstruction of monthly flow time series in hydrometric stations. Iran-Water Resources Research 13(4):174-178 (In Persian)

Radmanesh F, Pourhaghi A, Solgi A (2016) Improvement of artificial neural network modeling using wavelet transformation and PCA method for modeling and predicting biosphere oxygen (BOD). Journal of Ecohydrology 3(4):569-585 (In Persian)

Radwan M, Willems P, El-Sadek A, Berlamont J (2003) Modelling of dissolved oxygen and biochemical oxygen demand in river water using a detailed and simplified model. Int J River Basin Manage 1(2):97-103

Raheli B, Alami MT, El-Shafie A, Deo R (2017) Uncertainty assessment of the Multilayer Perceptron (MLP) neural network model with implementation of the novel hybrid MLP-FFA method for prediction of biochemical oxygen demand and dissolved oxygen: a case study of Langat River. Environmental Earth Sciences 76(503):3-16

Shin S, Kyung D, Lee S, Taik & Kim  J, Hyun J (2005) An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications 28(4):127-135

Solgi A, Pourhaghi A, Zarei H, Ansari H (2017) Modeling and forecast biological oxygen demand (BOD) using combination support vector machine with wavelet transform. Journal of Water and Soil 31(1):86-100 (In Persian)

Vapnik  V, Chervonenkis A (1991)  The necessary and sufficient conditions for consistency in the empirical risk minimization method. Pattern Recognition and Image Analysis 1(3):283-305

Vapnik  VN (1995) The Nature of Statistical Learning Theory. Springer, New York

Vapnik  VN (1998) Statistical learning theory. Wiley, New York

Wang D, Safavi AA, Romagnoli JA  (2000)  Wavelet-based adaptive robust M-estimator for non-linear system identification. AIChE Journal 46(4):1607-1615

Yoon H, Jun  SC, Hyun Y, Bae  GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396(4):128–138