A comparative study of artificial intelligence models for predicting monthly river suspended sediment load

• Autorzy: Rezaei Khalil , Vadiati Meysam

Identyfikatory

DOI

10.24425/jwld.2020.133052

• Języki publikacji: EN

Abstrakty

EN

When high precision modelling is required, for example, with the estimation of suspended sediment load (SSL), data-driven models are preferred over physically-based numerical models for their real-time, short-horizon prediction ability. The investigation of SSL, as an important index in engineering practices assessment, like design and operation of the hydraulic structures not only shows the hydrological behaviour of the river, but also illustrates the valuable information about the water quality deterioration, surface-groundwater interaction and land-use changes of the watershed. The following data-driven methods were compared in order to predict SSL at the Seyra gauging station on the Karaj River in Iran: Fuzzy logic (FL), two adaptive neuro-fuzzy inference systems (i.e., ANFIS-GP and ANFIS-FCM models), an artificial neural network (ANN), and least squares support vector machine (LSSVM). Monthly average river flow and SSL data for 50 years were obtained from the Tehran Regional Water Authority (TRWA). The data was first divided into training, validation and test sets and the SSL was then predicted using the ANN, FL, ANFIS, and LSSVM models. The reliability of the applied models was evaluated by the correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE). The results showed that the ANFIS models outperformed the ANN, FL, and LSSVM models for predicting SSL using the given input and output data. Overall, the performances of the artificial intelligence models used in the present study were satisfactory in predicting the non-linear behaviour of the SSL.

Słowa kluczowe

EN

artificial intelligence; data-driven methods; Karaj dam; suspended sediment load; Karaj River

• Wydawca: Wydawnictwo ITP
• Czasopismo: Journal of Water and Land Development
• Rocznik: 2020
• Tom: no. 45
• Strony: 107--118
• Opis fizyczny: Bibliogr. 47 poz., rys., tab.

Twórcy

autor

Rezaei Khalil

• Kharazmi University, Faculty of Earth Sciences, Applied Geology Department, No. 43, Mofatteh, 15719-14911, Tehran, Iran

autor

Vadiati Meysam

• Kharazmi University, Faculty of Earth Sciences, Applied Geology Department, No. 43, Mofatteh, 15719-14911, Tehran, Iran

Bibliografia

• ABRAHAM A., KÖPPEN M., FRANKE K. (eds). 2003. Design and application of hybrid intelligent systems. Amsterdam. IOS Press. ISBN 978-1-58603-394-1 pp. 1154.
• ALP M., CIGIZOGLU H.K. 2007. Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environmental Modeling and Software. Vol. 22. Iss. 1 p. 2–13. DOI 10.1016/j.envsoft.2005.09.009.
• BASAK D., PAL S., PATRANABIS D.C. 2007. Support vector regression. Neural Information Processing-Letters and Reviews. Vol. 11. Iss. 10 p. 203–224.
• BEZDEK J.C., EHRLICH R., FULL W. 1984. FCM: The fuzzy c-means clustering algorithm. Computers and Geosciences. Vol. 10. Iss. 2–3 p. 191–203. DOI 10.1016/0098-3004 (84)90020-7.
• BUYUKYILDIZ M., KUMCU S.Y. 2017. An Estimation of the Suspended Sediment Load Using Adaptive Network Based Fuzzy Inference System, Support Vector Machine and Artificial Neural Network Models. Water Resources Management. Vol. 31. Iss. 4 p. 1343–1359. DOI 10.1007/s11269-017-1581-1.
• CHANG Q., CHEN Q., WANG X. 2005. Scaling Gaussian RBF kernel width to improve SVM classification. In: Neural Networks and Brain, 2005 ICNNB'05 International Conference on. (Vol. 1 p. 19–22) IEEE. DOI 10.1109/ICNNB.2005. 1614559.
• CHANG C.C., LIN C.J. 2011. LIBSVM: A library for support vector machines [online]. ACM Transactions on Intelligent Systems and Technology. Vol. 2. Iss. 3 p. 1–27. [Access 6.04.2019]. Available at: https://www.csie.ntu.edu.tw/~cjlin/ libsvm/
• CORTES C., VAPNIK V. 1995. Support-vector networks. Machine Learning. Vol. 20. Iss. 3 p. 273–297. DOI 10.1007/ BF00994018.
• EL-SHAFIE A., TAHA M.R., NOURELDIN A. 2007. A neuro-fuzzy model for inflow forecasting of the Nile River at Aswan high dam. Water Resources Management. Vol. 21. Iss. 3 p. 533–556. DOI 10.1007/s11269-006-9027-1.
• GOYAL M.K. 2014. Modeling of sediment yield prediction using M5 model tree algorithm and wavelet regression. Water Resources Management. Vol. 28. Iss. 7 p. 1991–2003. DOI 10.1007/s11269-014-0590-6.
• GRANDE J.A., ANDÚJAR J.M., AROBA J., BELTRÁN R., DE LA TORRE M.L., CERÓN J.C., GÓMEZ T. 2010. Fuzzy modeling of the spatial evolution of the chemistry in the Tinto River (SW Spain). Water Resources Management. Vol. 24. Iss. 12 p. 3219–3235. DOI 10.1007/s11269-010-9603-2.
• HASSAN M., SHAMIM M.A., SIKANDAR A.,MEHMOOD I., AHMED I., ASHIQ S.Z., KHITAB A 2015. Development of sediment load estimation models by using artificial neural networking techniques. Environmental monitoring and assessment. Vol. 187. Iss. 11. DOI 10.1007/s10661-015-4866-y.
• HEIDARNEJAD M., GOLMAEE S.H., MOSAEDI A., AHMADI M.Z. 2006. Estimation of sediment volume in Karaj Dam Reservoir (Iran) by hydrometry method and a comparison with hydrography method. Lake and Reservoir Management. Vol. 22. Iss. 3 p. 233–239. DOI 10.1080/07438140609353900.
• HU Y.C. 2007. Sugeno fuzzy integral for finding fuzzy if–then classification rules. Applied mathematics and computation. Vol. 185. Iss. 1 p. 72–83. DOI 10.1016/j.amc.2006.07.010.
• JAIN A.K., DUBES R.C. 1988. Algorithms for clustering data. Englewood Cliffs, NJ. Prentice Hall, Inc. ISBN 978-0-13-022278-7 pp. 320.
• JANG J.S.R., SUN C.T., MIZUTANI E. 1997. Neuro-fuzzy and soft computing: A computational approach to learning and machine intelligence. Upper Saddle River, NJ. Prentice Hall. ISBN 0132610663 pp. 648.
• JHA S.K., BOMBARDELLI F.A. 2011. Theoretical/numerical model for the transport of non-uniform suspended sediment in open channels. Advances in water resources. Vol. 34. Iss. 5 p. 577–591. DOI 10.1016/j.advwatres.2011.02.001.
• JIE L.C., YU S.T. 2011. Suspended sediment load estimate using support vector machines in Kaoping River basin. In International Conference on Consumer Electronics Communications and Networks (IEEE). XianNing, China p. 16–18.
• KHALIL B., BRODA S., ADAMOWSKI J., OZGA-ZIELINSKI B., DONOHOE A. 2015. Short-term forecasting of groundwater levels under conditions of mine-tailings recharge using wavelet ensemble neural network models. Hydrogeology Journal. Vol. 23. Iss. 1 p. 121–141. DOI 10.1007/s10040-014-1204-3.
• KISI O. 2005. Suspended sediment estimation using neuro-fuzzy and neural network approaches/Estimation des matières en suspension par des approches neurofloues et à base de réseau de neurones. Hydrological Sciences Journal. Vol. 50. Iss. 4. DOI 10.1623/hysj.2005.50.4.683.
• KISI Ö. 2008. Constructing neural network sediment estimation models using a data-driven algorithm. Mathematics and Computers in Simulation. Vol. 79. Iss. 1 p. 94–103. DOI 10.1016/j.matcom.2007.10.005.
• KISI O., YASEEN Z.M. 2019. The potential of hybrid evolutionary fuzzy intelligence model for suspended sediment concentration prediction. Catena. Vol. 174 p. 11–23. DOI 10.1016/ j.catena.2018.10.047.
• KISI O., ZOUNEMAT-KERMANI M. 2016. Suspended sediment modeling using neuro-fuzzy embedded fuzzy c-means clustering technique. Water Resources Management. Vol. 30. Iss. 11 p. 3979–3994. DOI 10.1007/s11269-016-1405-8.
• KLIR G.J., FOLGER T.A. 1988. Fuzzy sets, uncertainty, and information. Prentice Hall. ISBN 978-0133459845 pp. 355.
• LENDASSE A., JI Y., REYHANI N., VERLEYSEN M. 2005. LS-SVM hyper parameter selection with a nonparametric noise estimator. In Artificial Neural Networks: Formal Models and Their Applications–ICANN 2005 p. 625–630. Springer Berlin Hei-delberg. DOI http://dx.doi.org/10.1007/ 11550907_163.
• MAIER H.R., DANDY G.C. 2001. Neural network based modeling of environmental variables: a systematic approach. Mathematical and Computer Modeling. Vol. 33. Iss. 6 p. 669–682. DOI 10.1016/S0895-7177(00)00271-5.
• MAMDANI E.H., ASSILIAN S. 1975. An experiment in linguistic synthesis with a fuzzy logic controller. International journal of man-machine studies. Vol. 7. Iss. 1 p. 1–13. DOI 10.1016/S0020-7373(75)80002-2.
• MathWorks. 2014. MATLAB and Fuzzy Logic Toolbox Release 2014a. MathWorks, Natick, Massachusetts.
• NOORI H., SIADATMOUSAVI S.M.,MOJARADI B. 2016. Assessment of sediment yield using RS and GIS at two sub-basins of Dez Watershed, Iran. International Soil and Water Conservation Research. Vol. 4. Iss. 3 p. 199–206. DOI 10.1016/j.iswcr. 2016.06.001.
• NOURANI V., ALIZADEH F., ROUSHANGAR K. 2016. Evaluation of a two-stage SVM and spatial statistics methods for modeling monthly river suspended sediment load. Water Resources Management. Vol. 30. Iss. 1 p. 393–407. DOI 10.1007/ s11269-015-1168-7.
• NOURANI V., BAGHANAM A.H., ADAMOWSKI J., GEBREMICHAEL M. 2013. Using self-organizing maps and wavelet transforms for space–time pre-processing of satellite precipitation and runoff data in neural network based rainfall–runoff modeling. Journal of Hydrology. Vol. 476 p. 228–243. DOI 10.1016/ j.jhydrol.2012.10.054
• NOURANI V., KALANTARI O., BAGHANAM A.H. 2012. Two semidistributed ANN-based models for estimation of suspended sediment load. Journal of Hydrologic Engineering. Vol. 17. Iss. 12 p. 1368–1380. DOI 10.1061/(ASCE)HE. 1943-5584.0000587.
• PLATT J.C. 1999. Fast training of support vector machines using sequential minimal optimization In: Advances in Kernel Methods–Support Vector Learning MIT Press. Eds. B. Schokopf, C.J.C. Burges, A.J. Smolar. Cambridge, Massachusetts, USA p. 185–208.
• RAGHAVENDRA N.S., DEKA P.C. 2014. Support vector machine applications in the field of hydrology: a review. Applied Soft Computing. Vol. 19 p. 372–386. DOI 10.1016/j.asoc.2014. 02.002.
• REZAEI K.H. 2015. Environmental pollutant enrichment in soil, surface sediments and water resources by mining activities, a case study, Zarshuran mine, Iran. International Conference on Science and Engineering. 1 Dec 2015, Dubai-UAE.
• REZAEI K.H., FRIEDRICH A., GUEST B., FAYAZI F., NAKHAEI M., FATEMI AGHDA S.M., BEITOLLAHI A. 2009. Feed forward Neural Network and Interpolation function models to predict the distribution of soil and subsurface sediments in Bam, Iran, Acta Geophysica. Vol. 57 p. 271–293. DOI: 10.2478/s11600-008-0073-3.
• SANIKHANI H., KISI O. 2012. River flow estimation and forecast-ing by using two different adaptive neuro-fuzzy approaches. Water Resources Management. Vol. 26. Iss. 6 p. 1715–1729. DOI: 10.1007/s11269-012-9982-7.
• SARI V., DOS REIS CASTRO N.M., PEDROLLO O.C. 2017. Estimate of suspended sediment concentration from monitored data of turbidity and water level using artificial neural networks. Water Resources Management. Vol. 31. Iss. 15 p. 4909–4923. DOI 10.1007/s11269-017-1785-4.
• SHAMAEI E., KAEDI M. 2016. Suspended sediment concentration estimation by stacking the genetic programming and neuro-fuzzy predictions. Applied Soft Computing. Vol. 45 p. 187–196. DOI 10.1016/j.asoc.2016.03.009.
• SHEVADE S.K., KEERTHI S.S., BHATTACHARYYA C., MURTHY K.R.K. 2000. Improvements to the SMO algorithm for SVM regression. Neural Networks, IEEE Transactions on. Vol. 11. Iss. 5 p. 1188–1193.
• SHIRI J., KIŞI Ö. 2011. Comparison of genetic programming with neuro-fuzzy systems for predicting short-term water table depth fluctuations. Computers and Geosciences. Vol. 37. Iss. 10 p. 1692–1701.
• VADIATI M., NAKHAEI M., AMIRI A.V., MIRARABI A. 2013. An assessment of the Karoon River’s water quality using the fuzzy inference model. Water Engineering. Vol. 6. Iss. 18 p. 39–48.
• VADIATI M., NALLEY D., ADAMOWSKI J., NAKHAEI M., ASGHARI-MOGHADDAM A. 2019. A comparative study of fuzzy logic-based models for groundwater quality evaluation based on irrigation indices. Journal of Water and Land Development. Vol. 43 p. 158–170. DOI 10.2478/jwld-2019-0074.
• VAFAKHAH M. 2013. Comparison of cokriging and adaptive neuro-fuzzy inference system models for suspended sediment load forecasting. Arabian Journal of Geosciences. Vol. 6. Iss. 8 p. 3003–3018. DOI 10.1007/s12517-012-0550-5.
• VAPNIK V. 2013. The nature of statistical learning theory. Springer Science Business Media. ISBN 1475724403 pp. 188. DOI 10.1007/978-1-4757-2440-0.
• ZADEH L.A. 1965. Fuzzy sets, information and controls. Vol. 8. Iss. 3 p. 353–383.
• ZOUNEMAT-KERMANI M., KIŞI Ö., ADAMOWSKI J., RAMEZANI-CHARMAHINEH A. 2016. Evaluation of data driven models for river suspended sediment concentration modeling. Journal of Hydrology. Vol. 535 p. 457–472. DOI 10.1016/j.jhydrol. 2016.02.012.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).