نوع مقاله : مقاله پژوهشی

نویسندگان

• امیر مرادی نژاد ¹
• عباس پارسائی ²
• سعید خسروبیگی ³
• احمد حسینی ⁴
• محمودرضا طباطبایی ⁵

¹ استادیار بخش حفاظت خاک و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان مرکزی، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران.

² استادیار، گروه سازه های آبی، دانشکده مهندسی آب و محیط زیست، دانشگاه شهید چمران اهواز، اهواز ایران

³ دکتری آبخیزداری و رئیس بخش فنی و مهندسی اداره کل منابع طبیعی استان مرکزی.

⁴ استادیار بخش مهندسی رودخانه و سواحل، پژوهشکده حفاظت خاک و آبخیزداری کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران ایران.

⁵ استادیار پژوهشی، پژوهشکده حفاظت خاک و آبخیزداری کشور، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران ایران.

چکیده

برآورد مقدار رسوب رودخانه در طراحی و اجرای سازه­های آبی و ساماندهی رودخانه اهمیت به­سزایی دارد. شبیه­سازی و ارزیابی رسوب رودخانه از مسائل مهم و کاربردی در مدیریت منابع آب است. بنابراین دست یافتن به شیوه ­های نوین و خلاقانه که بتواند در این راستا موثر واقع گردد دارای اهمیت زیادی است. هدف از این پژوهش ارزیابی و مقایسة مدل­های فازی- عصبی تطبیقی (ANFIS)، ماشین بردار پشتیبان (SVM) و برنامه­ریزی بیان ژن (GEP) در برآورد بار رسوب ایستگاه باقرآباد رودخانه­ قمرود استان مرکزی است. بدین منظور عملکرد سه نوع مدل ماشین بردار پشتیبان (SVM)، سیستم عصبی فازی-تطبیقی (ANFIS) و برنامه­ریزی بیان ژن (GEP) در شبیه ­سازی بار رسوبی رودخانه ­ها بررسی و نتایج به­دست آمده از این سه روش با یکدیگر و با نتایج منحنی سنجه مقایسه شد. نتایج بیانگر عملکرد قابل قبول مدل ­ها نسبت به منحنی سنجه است. برتری مدل (GEP) با بیشترین ضریب تعیین R² با مقدار 0/99 و کمترین ریشه میانگین مربعات خطا RMSE بر حسب تن در روز با مقدار 0/010 نشان داده شد. در این خصوص کارآیی مدلSVR با R² با مقدار 0/95 و RMSE برابر  1/49 تا حدی بهتر از مدل ANFIS با R² با مقدار 0/91 و RMSE برابر 7/94 بود.  نتایج به ­دست آمده همچنین نشان داد هر سه روش داده ­کاوی بررسی شده نسبت به منحنی سنجة رسوب، نتایج به­مراتب بهتری  ارائه می­ کننند.

کلیدواژه‌ها

• برنامه‌ریزی بیان ژن
• شبکه عصبی
• رسوب
• ماشین بردار پشتیبان

20.1001.1.24764000.1401.23.88.6.8

موضوعات

• مهندسی رودخانه

عنوان مقاله [English]

Modeling based on computational intelligence in river suspended load estimation (Baqorabad Station of the Qamroud River)

نویسندگان [English]

• amir moradinejad ¹
• Abbas Parsaie ²
• saeid khosrobeghi ³
• Seyed Ahmad Hosseini ⁴
• Mahmodreza Tabatabaei ⁵

¹ Assistant Prof., Soil Conservation and Watershed Management Research Department, Markazi Agricultural and Natural Resources Research and Education Center, Arak, Agricultural Research Education & Extention Organization (AREEO). Tehran, Iran.

² Assistant Professor, Department of Hydraulic Structures, Faculty of Water and Environmental Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran

³ PhD in Watershed Management and Head of Technical and Engineering Department of the General Department of Natural Resources of Markazi Province

⁴ Assistant Professor, Soil Conservation and Watershed Management Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran.

⁵ Assistant Professor, Soil Conservation and Watershed Management Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran.

چکیده [English]

Extended Abstract
Introduction
Estimating the sediment load of rivers is one of the important and practical issues in the studies and design of water engineering projects, such as the design and development of irrigation and drainage networks, water extraction from rivers, etc. Sediment concentration can be calculated by direct or indirect methods, which are usually expensive and time-consuming direct methods. Various factors affect this phenomenon, which makes their analysis difficult. Statistical and regression models are the most common methods of analysis, which often provide erroneous results due to the linear solution of these phenomena. Therefore, they cannot model the sedimentation phenomenon with acceptable accuracy. Hydraulic models cannot always be trusted due to the need for a lot of data, the unavailability of the required data, and the inaccuracy of the data due to human error in simulating sediments. Due to their ability to solve complex and nonlinear phenomena, intelligent fuzzy and neural conductor systems have found many applications in various water engineering problems, including sedimentation. This research aims to evaluate and compare adaptive neural fuzzy models (ANFIS), machine Support vector (SVM), and GEP gene expression programming in estimating the sediment load of selected rivers in Central Province. For this purpose, the performance of three types of support vector machine (SVM), adaptive neural system (ANFIS), and GEP gene expression programming in the simulation of the sediment load of rivers was studied.
Methodology
In this research, first, the long-term daily statistics of temperature, rainfall, average flow rate, and sediment concentration of Bagharabad Abad hydrometric station and sediment measuring station located on the main branch of the of Qamroud River were collected. Then, the data sufficiency test for analysis, checking the correlation between parameters of river discharge, precipitation, temperature with sediment discharge, and determining the long-term average of suspended sediment in the studied stations were performed. In the next step, a suitable combination of input variables was selected. The design of input parameter pattern can be based on the relationship between flow and sediment flow parameters, rainfall, temperature, flow, and sediment flow. Determining the most appropriate time delay of input parameters in flow and sediment modeling. Estimation of sediment discharge using support vector machine (SVM), gene expression programming (GEP), and fuzzy-adaptive neural system (Anfis), comparing three data mining methods with each other as well as with gauge curve and observational data. The appropriate design of the structure of soft calculation models is used, in this research, the number of data required for training (usually more than 70 percent), research data as training, and also determining the required data (usually between 20 and 30 percent) is used for validation and testing.
Results and Discussion
In this research, the best performance of the GEP model has been obtained for pattern number 13. In this model, the R² explanatory coefficient and the RMSE error obtained from the model are 0.97 and 0.033, respectively. The coefficient of explanation R² and the RMSE error of the models in predicting suspended sediment values in the test phase were obtained as 0.53, 3.18 for the ANFIS model, and 0.70, 15.16 for the SVR model, respectively. Comparing the results of ANFIS and GEP models with the SVR model indicates the superiority of the GEP model, in predicting the amount of suspended sediment according to Verdi model number 13. According to the obtained results, it can be seen that the performance of GEP model was better compared to other models. SVR and ANFIS models are ranked second and third. According to the obtained results, it can be said that the GEP model as a powerful and high-speed model, can be used to model the suspended sediment in the Qomroud catchment area of Bagherabad station.
Conclusions
The results show the acceptable performance of the models compared to the gauge curve. Also, the results showed the superiority of the GEP model with the highest coefficient of determination R² with a value of 0.99 and the lowest root mean square error RMSE in terms of tons per day with a value of 0.010. In this regard, the efficiency of the SVR model was somewhat better than the ANFIS model. The results showed that all three investigated data mining methods provide far better results than the sediment gauge curve.

کلیدواژه‌ها [English]

• Gene expression programming
• neural network
• sedimentation
• support vector machine