با همکاری انجمن آبخیزداری ایران

نوع مقاله : مقاله پژوهشی

نویسنده

استادیار پژوهشی، بخش تحقیقات حفاظت خاک و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان کرمانشاه، سازمان تحقیقات آموزش و ترویج کشاورزی، کرمانشاه، ایران

چکیده

مقدمه
انتقال رسوبات معلق یکی از چالش‌های بنیادین در مهندسی منابع آب است که موجب کاهش ظرفیت مخازن، تخریب کیفیت آب و آسیب به زیرساخت‌های هیدرولیکی می‌شود. روش‌های متداول منحنی سنجه رسوب (SRC) بر فروض ساده‌سازی ‌شده‌ای استوارند که اغلب در بازنمایی روابط غیرخطی و دینامیک جریان-رسوب ناکارآمدند. پیشرفت‌های اخیر در رویکردهای داده‌محور، به‌ویژه شبکه‌های عصبی مصنوعی (ANN) و سامانه‌های استنتاج عصبی-فازی تطبیقی، توانمندی قابل‌توجهی در مدلسازی این فرایندهای پیچیده هیدرولوژیکی نشان داده‌اند. این پژوهش چارچوب ترکیبی نوینی را توسعه و ارزیابی می‌کند که منحنی‌های سنجه تجربی را با سامانه استنتاج عصبی-فازی همکارانه (CANFIS) تلفیق می‌نماید تا دقت پیش‌بینی و استحکام مدل را در ایستگاه هیدرومتری گلینک واقع در حوزه آبخیز طالقان ارتقا بخشد.
 
مواد و روش‌ها
این تحقیق بر پایه 800 مشاهده همزمان دبی جریان و دبی رسوب معلق جمع‌آوری‌شده از ایستگاه گلینک طی دوره 1402-1350 انجام شد. پیش‌پردازش داده‌ها شامل شناسایی داده‌های پرت، آزمون همگنی با روش نرمال استاندارد و نرمال‌سازی بود. شش روش تجربی منحنی سنجه رسوب واسنجی و ارزیابی شدند: رگرسیون لگاریتمی-خطی، رگرسیون چندبخشی، روش میانگین بار لگاریتمی در دسته‌های دبی (LMLWDC)، ضریب اصلاحی فائو، ضریب اصلاحی پارامتری و ضریب اصلاحی ناپارامتری. ارزیابی عملکرد با استفاده از ضریب تعیین (R2)، ضریب کارایی ناش-ساتکلیف (NSE) و میانگین خطای نسبی (RME) صورت گرفت. همزمان، شش معماری شبکه عصبی-پرسپترون چندلایه (MLP)، شبکه پیش‌خور تعمیم‌یافته (GFF)، تابع پایه شعاعی (RBF)، ماشین بردار پشتیبان (SVM)، نقشه خودسازمان‌ده (SOFM) و CANFIS با تقسیم 75 درصد آموزش و 25 درصد آزمون آموزش داده شدند. سنجش مدل‌ها با معیارهای خطای مربعات میانگین نرمال‌شده (NMSE)، میانگین قدرمطلق خطا (MAE) و ضریب همبستگی پیرسون (R) انجام شد. دو پیکربندی ترکیبی بررسی شدند: مدل ترکیبی 1 که تنها از خروجی بهینه SRC به‌عنوان ورودی CANFIS استفاده کرد و مدل ترکیبی 2 که هم خروجی SRC و هم داده‌های دبی جریان را درنظر گرفت.
 
نتایج و بحث
واکاوی یافته‌های پژوهش در ایستگاه گلینک مبین آن است که مدل‌های متداول هیدرولوژیک به‌دلیل پراکندگی افراطی داده‌ها با ضریب تغییرات بالا (206.75 درصد)، در برآورد دقیق بار رسوبی با محدودیت‌های ساختاری جدی مواجه هستند. نوسانات شدید دبی رسوب و وجود توزیع آماری چوله به راست و دم‌کلفت، در کنار شناسایی 12.88 درصد داده پرت، منجر به کاهش شاخص کارایی NSE در این ایستگاه شده است. از منظر فیزیکی، نوسان 3700 برابری نسبت دبی رسوب به جریان، وقوع پدیده هیستروسیس را تأیید می‌کند که نشان‌دهنده وابستگی بار رسوبی به شرایط پیشین حوضه نظیر رطوبت خاک است. در این میان، مدل ترکیبی 1 (حد وسط دسته‌ها- CANFIS) با کسب شاخص NSE معادل 0.63، برتری قاطعی نسبت به مدل‌های منفرد نشان داد. موفقیت این الگو ریشه در تلفیق هوشمندانه دانش تجربی سنجه رسوب با قدرت یادگیری سیستم استنتاج عصبی‌فازی دارد که توانسته است با مدیریت عدم‌قطعیت‌ها، توازن منطقی میان پیش‌بینی‌های عددی و واقعیت‌های هیدرومورفولوژیک برقرار سازد.
 
نتیجه‌گیری
یافته‌های این پژوهش به روشنی اثبات می‌کند که تلفیق هم‌افزایانه رویکردهای تجربی و هوش مصنوعی، چارچوبی استوار و کارآمد برای غلبه بر چالش‌های مدلسازی در حوضه‌هایی با چولگی بالا و فراوانی داده‌های پرت فراهم می‌آورد. بر این اساس، معماری CANFIS با بهره‌گیری هوشمندانه از منطق فازی، ظرفیت پردازش روابط غیرخطی پیچیده و تحلیل دقیق پدیده Hysteresis را به‌طور معنی‌داری ارتقا بخشیده و مزایای متمایزی نسبت به ساختارهای کلاسیک محاسباتی ارائه کرده است. با توجه به نقش حیاتی و راهبردی رخدادهای سیلابی در مدیریت منابع آب واکاوی داده‌های پرت امری اجتناب‌ناپذیر تلقی می‌شود. در این راستا، مدل ترکیبی تدوین‌شده توانسته است با دقت قابل‌قبولی این ناهنجاری‌های آماری را پوشش داده و تحلیل نماید. به‌منظور ارتقای کارایی و غنای علمی در مطالعات آتی، توسعه بانک‌های اطلاعاتی جامع با تمرکز ویژه بر ثبت دقیق دبی‌های سیلابی و گنجاندن متغیرهای کمکی نظیر شدت بارندگی و وضعیت پوشش گیاهی اکیداً توصیه می‌شود. شایان ذکر است که به‌کارگیری الگوریتم‌های پیشرفته‌ای همچون یادگیری عمیق در قالب مدل‌های LSTM و استفاده از تکنیک‌های پیش‌پردازش مقاوم مانند رگرسیون کوانتیل، می‌تواند منجر به کاهش چشمگیر خطاهای سیستماتیک و افزایش ضریب اطمینان مدل‌ها در مدیریت یکپارچه حوزه‌های آبخیز شود.

کلیدواژه‌ها

عنوان مقاله [English]

Simulation of suspended sediment using a hybrid intelligent approach based on sediment rating curve and CANFIS network, case study: Taleghan Glinak Station

نویسنده [English]

  • Golaleh Ghaffari

Assistant Professor, Soil Conservation and Watershed Management Research Department, Kermanshah Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Kermanshah, Iran

چکیده [English]

Introduction
Suspended sediment transport constitutes a critical challenge in water resources engineering, causing reservoir capacity reduction, water quality degradation, and hydraulic infrastructure damage. Conventional sediment rating curve (SRC) methods rely on simplifying assumptions that frequently fail to capture nonlinear and transient flow-sediment dynamics. Recent advances in data-driven approaches, particularly artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems, have demonstrated substantial potential for modeling such complex hydrological processes. This study develops and rigorously evaluates a hybrid framework that integrates empirical SRCs with a Coactive Neuro-Fuzzy Inference System (CANFIS) to enhance predictive accuracy and model robustness at the Glinak hydrometric station in the Taleghan watershed.
 
Materials and methods
The analysis utilized 800 paired observations of streamflow and suspended sediment discharge collected from Glinak station between 1971 and 2023. Data preprocessing involved outlier removal, homogeneity assessment using the standard normal homogeneity test, and normalization. Six empirical SRC methods were calibrated and evaluated: logarithmic-linear regression, multi-segment regression, Logged Mean Load within Discharge Classes Method (LMLWDC), modified FAO correction factor, parametric correction factor, and non-parametric correction factor. Performance evaluation employed the coefficient of determination (R²), Nash-Sutcliffe efficiency (NSE), and relative mean error (RME). In parallel, six ANN architectures—Multilayer Perceptron (MLP), General Feed-Forward (GFF), Radial Basis Function (RBF), Support Vector Machine (SVM), Self-Organizing Feature Map (SOFM), and CANFIS—were trained using a 75%-25% train-test split. Model assessment utilized normalized mean squared error (NMSE), mean absolute error (MAE), and Pearson's correlation coefficient (R). Two hybrid configurations were examined: Hybrid Model 1 used the optimal SRC output as the sole input to CANFIS, whereas Hybrid Model 2 incorporated both SRC output and streamflow as inputs.
 
Results and discussion
A detailed interrogation of the findings at the Glinak hydrometric station reveals that conventional hydrological models encounter substantive structural constraints when estimating suspended sediment load under conditions of extreme data dispersion, as evidenced by a coefficient of variation of 206.75%. Pronounced fluctuations in sediment discharge, coupled with a right-skewed and heavy-tailed statistical distribution and the identification of 12.88% outliers, collectively suppressed the Nash–Sutcliffe efficiency (NSE) at this station. From a process-based perspective, the 3,700-fold variability in the sediment-to-flow discharge ratio corroborates the occurrence of hysteresis, underscoring the dependence of sediment yield on antecedent catchment states, particularly soil moisture conditions. Against this backdrop, Hybrid Model 1 (LMLWDC –CANFIS) achieved superior performance, attaining an NSE of 0.63 and markedly outperforming standalone empirical sediment rating curve (SRC) and artificial intelligence architectures. The robustness of this configuration stems from the strategic integration of empirically derived sediment rating-curve knowledge with the adaptive learning capacity of the Coactive Neuro-Fuzzy Inference System (CANFIS). By explicitly accommodating uncertainty and nonlinearity inherent in flow-sediment dynamics, the model establishes a coherent balance between numerical prediction and hydromorphological realism, thereby enhancing predictive reliability under highly variable sediment transport regimes.
 
Conclusion
The results unequivocally demonstrate that the synergistic integration of empirical hydrological reasoning and artificial intelligence provides a resilient and efficient modeling framework for watersheds characterized by pronounced skewness and a high prevalence of anomalous observations. In this context, the CANFIS architecture, leveraging fuzzy logic to resolve complex nonlinear interactions, substantially improves the representation of hysteretic sediment dynamics and offers clear advantages over conventional computational structures, including multilayer perceptron (MLP), general feed-forward (GFF), radial basis function (RBF), support vector machine (SVM), and self-organizing feature map (SOFM) networks. Given the strategic significance of flood events in water resources engineering, the rigorous interrogation of outlier behavior is not optional but imperative. The proposed hybrid framework effectively captures and interprets these statistical anomalies with acceptable precision, thereby reinforcing its applicability in suspended sediment transport management under extreme hydrological conditions. To advance methodological robustness and scientific depth in future investigations, the establishment of comprehensive, high-resolution databases—particularly those documenting peak flood discharges—is strongly recommended. Incorporating auxiliary predictors such as antecedent soil moisture, rainfall intensity, and vegetation cover indices would further strengthen process representation and address hysteresis phenomena. Moreover, deploying advanced machine-learning paradigms, including Long Short-Term Memory (LSTM) networks, alongside robust preprocessing techniques such as quantile regression and outlier treatment methods, has strong potential to attenuate systematic error and enhance model confidence in integrated watershed management applications. Additionally, ensemble methods combining multiple model outputs and uncertainty quantification frameworks  are recommended to improve predictive reliability and decision-making support in sediment yield estimation.
 

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Hybrid Model
  • Sediment Rating Curve
  • Suspended Sediment
  • Taleghan Watershed
Adnan, R.M., Wang, M., Masood, A., Kisi, O., Shahid, S., Zounemat-Kermani, M., 2025. Applications of advanced optimized neuro fuzzy models for enhancing daily suspended sediment load prediction. Comput. Model. Eng. Sci. 143(1), 1249–1272. https://doi.org/10.32604/cmes.2025.062339
Ahmadi, M., 2012. Estimating sediment of rivers by RBF and MLP. 11th Hydraulic Conf. in Iran, Urmia Uni. Iran (in Persian).
Ahmer, M., Qaiser, K., Muhammad, A., 2019. Prediction of suspended sediment load using ANN, SVM and M5Tree machine learning models. Water 11(11), 2315.
Arabkhedri, M., Lai, F.S., Ibrahim, N.A., Mohamad-Kasim, M.R., 2010. Effect of adaptive cluster sampling design on accuracy of sediment rating curve estimation. J. Hydrol. Eng. 15(2), 142–151. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000171
Arabkhedri, M., Lai, F.S., Noor-Akma, I., Mohamad-Roslan, M.K., 2010. An application of adaptive cluster sampling for estimating total suspended sediment load. Hydrol. Res. 41(1), 63–73. https://doi.org/10.2166/nh.2010.113
Asfandiar-Darabad, F., Gharachorloo, M., 2022. Regional estimation of sediment yield using monthly sediment rating curves, case study: Ghareh-Soo Watershed. Appl. Res. Geogr. Sci. 23(69), 33–52 (in Persian).
Asselman, N.E.M., 2000. Fitting and interpretation of sediment rating curves. J. Hydrol. 234(3–4), 228–248. https://doi.org/10.1016/S0022-1694(00)00253-5
Azamathulla, H.M., Ghani, A.A., Fei, S.Y., 2012. ANFIS-based approach for predicting sediment transport in clean sewer. Appl. Soft Comput. 12(3), 1227–1230. https://doi.org/10.1016/j.asoc.2011.08.009
Biranvand, N., Sepehvand, A., Haghi-Zadeh, A., 2021. Evaluation of the sediment rating curve method for estimating suspended sediment load, case study: Khorramabad, Alishtar and Beyranshahr Watersheds. Hydrol. Eng. Res. (in Persian).
Chai, T., Draxler, R.R., 2014. Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7(3), 1247–1250. https://doi.org/10.5194/gmd-7-1247-2014
Choubin, B., Darabi, H., Rahmati, O., Sajedi-Hosseini, F., Kløve, B., 2018. River suspended sediment modelling using the CART model: A comparative study of machine learning techniques. Sci. Total Environ. 615, 272–281. https://doi.org/10.1016/j.scitotenv.2017.09.249
Doroudi, S., Sharafati, A., 2024. A newly developed multi-objective evolutionary paradigm for predicting suspended sediment load. J. Hydrol. 634, 131090. https://doi.org/10.1016/j.jhydrol.2024.131090
Eilderemi, A.R., Mohamadpanah-Moghadam, M., 2021. Optimization of a suitable model for estimating suspended sediment load in river basins. J. Hydrol. Hydromech. 69(4), 345–357.
Ferguson, R.I., 1986. River loads underestimated by rating curves. Water Resour. Res. 22(1), 74–76. https://doi.org/10.1029/WR022i001p00074
Ghafari, G., 2025. Prediction of suspended sediments using a hybrid model of sediment rating curve and artificial neural network at the Narvan Afjeh station. Watershed Manage. Res. 38(1), 128–146 (in Persian).
Glysson, G.D., 1987. Sediment-transport curves (No. 87-218). U.S. Geol. Surv. https://pubs.usgs.gov/of/1987/0218/report.pdf
Gupta, H.V., Sorooshian, S., Yapo, P.O., 1999. Status of automatic calibration for hydrologic models: Comparison with multilevel expert calibration. J. Hydrol. Engin. 4(2), 135–143. https://doi.org/10.1061/(ASCE)1084-0699(1999)4:2(135
Issazadeh, L., Govay, B., 2014. Reservoir sediment prediction in Duhok Dam using artificial neural network and conventional methods. Indian J. Fundam. Appl. Life Sci. 4, 56–67.
Jansson, M.B., 1996. Estimating a sediment rating curve of the Reventazón River at Palomo using logged mean loads within discharge classes. J. Hydrol. 183(3–4), 227–241. https://doi.org/10.1016/0022-1694(95)02988-5
Janus, R., Volna, E., 2013. Feed-forward neural networks training speedup by using generalized activation function. Int. J. Math. Models Methods Appl. Sci. 7(8), 768–777.
Karami, G., Moradi, H., Bahrami, M.R., 2014. Feasibility of predicting suspended sediments using a combination of sediment rating curve and artificial neural network. Mar. Sci. Technol. 13(48), 1–12 (in Persian).
Karami, H., Farzin, S., Sadrabadi, M.T., Moazami, S., 2020. Simulation of water quality parameters using artificial intelligence-based models. Water Supply 20(5), 1863–1881. https://doi.org/10.2166/ws.2020.103
Khazaeepoul, A., Talebi, A., 2013. Feasibility of predicting suspended sediment using a combination of sediment rating curve and artificial neural network, case study: Ghotourchai River, Yazdekan Bridge. Environ. Erosion Res. 3(1), 73–82 (in Persian).
Kisi, O., Ay, M., 2012. Comparison of ANN and ANFIS techniques in modeling dissolved oxygen. Proc. 16th Int. Water Technol. Conf. (IWTC16), 7–10, Istanbul, Turkey.
Koch, R.W., Smillie, G.M., 1986. Bias in hydrologic prediction using log-transformed regression models. J. Am. Water Resour. Assoc. 22(5), 717–723. https://doi.org/10.1111/j.1752-1688.1986.tb00744.x
Kumar, A., Ahmad, S., Verma, A.K., 2020. Prediction of daily suspended sediments using particle swarm optimization-based artificial neural network models – A case study of Ganga River. Environ. Monit. Assess. 192(10), 1–16.
Lee, B., Yun, T., Choi, J., Jeon, J., Kim, D., 2021. An advanced hybrid artificial neural network–sediment rating curve model for suspended sediment prediction in rivers. Water 13(11), 1552.
Legates, D.R., McCabe, G.J., 1999. Evaluating the use of "goodness-of-fit" measures in hydrologic and hydroclimatic model validation. Water Resour. Res. 35(1), 233–241. https://doi.org/10.1029/1998WR900018
Lohani, A.K., Goel, N.K., Bhatia, K.K.S., 2006. Improving real time flood forecasting using fuzzy inference system. Water Resour. Manage. 20(4), 513–529. https://doi.org/10.1007/s11269-005-9007-3
Mahdavi-Meymand, A., Sulisz, W., 2023. Development of clustered machine learning technique for the modeling of scour profile/suspended-sediment related applications. Ocean Engin. 288, 115915. https://doi.org/10.1016/j.oceaneng.2023.115915
Maier, H.R., Dandy, G.C., 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environ. Model. Softw. 15(1), 101–124. https://doi.org/10.1016/S1364-8152(99)00007-9
Malik, A., Kumar, A., Piri, J., 2017. Daily suspended sediment concentration simulation using hydrological data of Pranhita River Basin, India. Comput. Electron. Agric. 138, 20–28. https://doi.org/10.1016/j.compag.2017.04.005
Mardoukhpour, A., Jamasebi, H., Alipour, O., 2019. Evaluation of sediment estimation using the sediment rating method compared with regression and neural network methods, case study: Babolrud River, Mazandaran Province. Environ. Sci. Technol. 21(11), 79–91 (in Persian).
Miller, C.R., 1951. Analysis of flow-duration sediment rating curve method of computing sediment yield. U.S. Bureau of Reclamation.
Moradi, H., Haghizadeh, A., Ghaemi, A., 2021. Predicting daily suspended sediment load using a novel hybrid artificial recurrent neural network model. Environ. Monit. Assess. 193(1), 1–16.
Moriasi, D.N., Arnold, J.G., Van Liew, M.W., Bingner, R.L., Harmel, R.D., Veith, T.L., 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Trans. ASABE 50(3), 885–900. https://doi.org/10.13031/2013.23153
Mostafa, R.R., Kisi, O., Adnan, R.M., Sadeghifar, T., Kuriqi, A., 2024. Modeling potential evapotranspiration by improved machine learning methods using limited climatic data. Water 15(3), 486. https://doi.org/10.3390/w15030486
Najafinejhad, A., Babaei, A., Saniei, E., Mahmoodi, O., 2010. Comparison of monthly and seasonal suspended load rating curves in several Golestan province rivers. 4th Natl. Seminar on Erosion and Sediment, Noor, Iran, 6p (in Persian).
Nash, J.E., Sutcliffe, J.V., 1970. River flow forecasting through conceptual models part I—A discussion of principles. J. Hydrol. 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Niha, K., Kumar, S., Yadav, S., 2023. Streamflow prediction using machine learning models. J. Hydrol. Hydromech. 71(1), 84–96. https://doi.org/10.2478/johh-2022-0039
Noor, H., Vafakhah, M., Maghdesi, M., 2016. Decision support tool for optimal spatial planning of watershed management measures, case study: Taleghan Dam Watershed. Water. Manage. Res. 113, 71–80 (in Persian).
Ren, Y., Zi, F., Xiong, L., Yu, G., Zhang, B., 2023. Improved hybrid model for sediment concentration prediction using advanced optimization and machine learning algorithms. J. Hydrol. 617, 128865. https://doi.org/10.1016/j.jhydrol.2022.128865
Rishab, M., Kumar, A., Singh, R., 2024. Prediction of sediment transport using neural networks. Water Resour. Manage. 38(2), 567–584. https://doi.org/10.1007/s11269-023-03712-5
Sepehvand, A., Biranvand, N., 2022. Evaluation of sediment rating curve method for estimating suspended sediment in karst rivers, case study: Hydrometric stations of Khorramabad, Alishtar and Beyranshahr Watersheds. 17th Natl. Conf. Watershed Sci. Engin. Iran (in Persian).
Shahidi, K., Manavi-Amri, S.M., Mahmoudi, N., 2022. Spatial and temporal analysis of suspended sediment variations in the Nekaroud watershed, Mazandaran Province. Spatial Anal. Environ. Hazards 9(2), 195–208 (in Persian).
Shiri, J., Kisi, O., 2012. Estimation of daily suspended sediment load by using wavelet conjunction models. J. Hydrol. 472–473, 302–317. https://doi.org/10.1016/j.jhydrol.2012.09.051
Singh, J., Knapp, H.V., Arnold, J.G., Demissie, M., 2004. Hydrologic modeling of the Iroquois River watershed using HSPF and SWAT. J. Am. Water Resour. Assoc. 41(2), 343–360. https://doi.org/10.1111/j.1752-1688.2005.tb03740.x
Srilatha, K., Sudha, T., 2024. Radial basis function neural networks for water quality prediction. Environ. Monit. Assess. 196(1), 45. https://doi.org/10.1007/s10661-023-12245-8
Tamrabet, Z., Marouf, N., Remini, B., 2022. Modeling of suspended sediment concentrations by artificial neural network and adaptive neuro-fuzzy inference system method–study of five largest basins in Eastern Algeria. Water Pract. Technol. 17(5), 1058–1081. https://doi.org/10.2166/wpt.2022.050
Thomas, R.B., 1985. Estimating total suspended sediment yield with probability sampling. Water Resour. Res. 21(9), 1381–1388. https://doi.org/10.1029/WR021i009p01381
Wang, Y., Ding, J., 2021. A review of sediment prediction methods based on sediment rating curves. J. Hydrol. 601, 126543. https://doi.org/10.1016/j.jhydrol.2021.126543
Willmott, C.J., Matsuura, K., 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim. Res. 30(1), 79–82. https://doi.org/10.3354/cr030079
Yadav, A., Chithaluru, P., Singh, A., Albahar, M.A., Jurcut, A., Álvarez, R.M., Mojjada, R.K., Joshi, D., 2022. Suspended sediment yield forecasting with single and multi-objective optimization using hybrid artificial intelligence models. Mathematic. 10(22), 4263. https://doi.org/10.3390/math10224263
Yousefi, M., Barzegar, F., 2015. Determining the best sediment rating method and comparison with artificial neural network to estimate suspended sediments, case study: Lorestan Province. Range Water. Manage. Summer 2015 (in Persian).
Zare, M., Bayat, M., 2013. Application of CANFIS for groundwater level forecasting. J. Hydrol. Hydromech. 61(4), 341–348. https://doi.org/10.2478/johh-2013-0043
Zhang, H., 2023. Prediction of suspended sediment concentration by artificial neural networks at the Vu Gia–Thu Bon Catchment, Vietnam. Environ. Sci. Eng. 77–84.
Zhang, J., Govindaraju, R.S., 2011. Modeling subsurface flow using an adaptive neuro-fuzzy inference system. J. Hydrol. Eng. 16(12), 1013–1019. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000392