با همکاری انجمن آبخیزداری ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

استادیار، پژوهشکده حفاظت خاک و آبخیزداری، سازمان تحقیقات، آموزش و ترویج کشاورزی، تهران، ایران

چکیده

روابط بین پارامترهای کیفی آب رودخانه و فرایندهای فیزیکی، ژئوشیمیائی و بیولوژیکی انجام­شده بین منابع حوضه (خاک، پوشش‌گیاهی، زمین‌شناسی، کاربری‌ اراضی و غیره)، متغیرهای هواشناسی (دما، بارش، ذوب‌ برف و غیره)، متغیر هیدرولوژیکی رودخانه (دبی) و همچنین دخالت‌های انسانی، اغلب بسیار پیچیده، غیر‌قطعی و غیرخطی بوده به­نحوی که درک کامل آن‌ها را غیرممکن می‌سازد. در این شرایط، استفاده از هوش محاسباتی (نظیر شبکه‌های عصبی مصنوعی) ابزار مناسبی در شبیه‌سازی و برآورد متغیرهای کیفی آب رودخانه نظیر بار رسوب معلق محسوب می‌­شود. در پژوهش حاضر، با تلفیق کتابخانه‌های متن باز GIS و مدل‌های شبکه عصبی مصنوعی (با ناظر و بدون ناظر)، سامانه مکانی هوشمندی، طراحی و کدنویسی شده است که می‌تواند در شرایط تک­متغیره یا چند­متغیره، رسوب معلق روزانه را برآورد کند. نتایج گرفته­شده از به­کارگیری این سامانه در حوزه آبخیز رودخانه مزلقان در محل ایستگاه هیدرومتری رازین نشان داد که این سامانه قادر است با کارائی و صحت‌سنجی مناسب (با ریشه میانگین مربعات خطا برابر 1033 تن در روز، میانگین قدر مطلق خطا 455 تن در روز و شاخص نش-ساتکلیف برابر 89/0 با داده‌های آزمون)، رسوب معلق ایستگاه مورد مطالعه را شبیه‌سازی کند. در مجموع، این سامانه می‌تواند به­عنوان یک زیر­ساخت نرم­افزاری در مقیاس ملی، در شبیه‌سازی و مدیریت رسوب معلق کلیه ایستگاه‌های هیدرومتری کشور مورد استفاده سازمان‌های ذی­ربط قرار گیرد.

کلیدواژه‌ها

عنوان مقاله [English]

Simulation of the suspended sediment of the country rivers using the technology of intelligent models and open source GIS system, case study: Razin Hydrometric Station, Mozlanghan Watershed, Markazi Province

نویسندگان [English]

  • Mahmoudreza Tabatabaei
  • Amin Salehpour Jam

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

چکیده [English]

Relationships between river water quality parameters and physical, geochemical and biological processes carried between basin resources (soil, vegetation, geology, land use, etc.), meteorological variables (temperature, precipitation, snowmelt, etc.), River hydrological variables (flow discharge), as well as human interventions are often very complex, nonlinear and non–deterministic in a way that makes their complete understanding impossible. In this situation, the use of computational intelligence (such as artificial neural networks) is a useful tool in simulating and estimating river water quality variables such as suspended sediment load. In the present study, by combining open source GIS libraries and neural network models (with and without supervisor), an intelligent GIS system has been designed and coded that can estimate daily suspended sediment load under univariate or multivariate conditions. The results of applying this system to Mazaljan River Watershed at Razin hydrometric station showed that this system is able to simulate suspended sediment load with proper performance and validation  (with root mean square error of 1033 tonday-1, mean absolute error of 455 tonday-1 and Nash-Sutcliffe efficiency of 0.89 for the test data set). In general, this system can be used as a national infrastructure in the simulation and management of suspended sediment in all hydrometric stations in the country by relevant organizations.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Data clustering
  • Prediction
  • Self-organizing map
  • Suspended sediment
  • Validation
  1. Banejad, H., K.W. Chau and A.M. Melesse. A comparison of various artificial intelligence approaches performance for estimating suspended sediment load of river systems, a case study in United States. Environmental Monitoring and Assessment, 187(4): 189-204.
  2. Bowden, G.J., H.R. Maier and G.C. Dandy. 2002. Optimal division of data for neural network models in water resources applications. Water Resources Research, 38(2): 2-11.
  3. Buyukyildiz, M. and S.Y. Kumcu. 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, 31(4): 1343-1359.
  4. Chen, X.Y. and K.W. Chau. 2016. A hybrid double feedforward neural network for suspended sediment load estimation. Water Resources Management, 30: 2179-2194.
  5. Demirci, M. and A. Baltaci. 2012. Prediction of suspended sediment in river using fuzzy logic and multilinear regression approaches. Neural Computing and Applications, 23(1): 145-151.
  6. Hornik, K., M. Stinchcombe and H. White. 1989. Multilayer feedforward networks are universal approximators. Neural Networks, 2(5): 359-366.
  7. Joshi, R., K. Kumar and V.P.S. Adhikari. 2016. Modelling suspended sediment concentration using artificial neural networks for Gangotri glacier. Hydrology Process, 30(9): 1354–1366.
  8. Kakaei Lafdani, E., A. Moghaddamnia and A. Ahmadi. 2013. Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology, 478: 50–62.
  9. Khan, M.Y.A., F. Tian, F. Hasan and G.J. Chakrapani. 2019. Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India. International Journal of Sediment Research, 34(2): 95-107.
  10. Kisi, O. and C. Ozkan. 2017. A new approach for modeling sediment-discharge relationship: local weighted linear regression. Water Resources Management, 30(2): 1-23.
  11. Kisi, O. and O. Shiri. 2012. River suspended sediment estimation by climatic variables implication: comparative study among soft computing technique. Computers and Geosciences, 43: 73-82.
  12. Kohonen, T. 1998. The self-organizing map. Neurocomputing, 21(1): 1-6.
  13. Li, X., M.H. Nour, D.W. Smith and A.A. Prepasc. 2010. Neural networks modeling of nitrogen export: model development and application to unmonitored boreal forest watersheds. Environmental Technology, 31(5): 495–510.
  14. Malik, A., A. Kumar and J. Piri. 2017. Daily suspended sediment concentration simulation using hydrological data of Pranhita River Basin, India. Computers and Electronics in Agriculture, 138: 20-28.
  15. Mansourfar, K. 2009. Advanced statistical methods using applied software. University of Tehran Press, 459 pages (in Persian).
  16. May, R.J., H.R. Maier and G.C. Dandy. 2010. Data splitting for artificial neural networks using SOM-based stratified sampling. Neural Networks, 23: 283-294.
  17. Melesse, A.M., S. Ahmad, M.E. McClain, X. Wang and Y.H. Lim. 2011. Suspended sediment load prediction of river systems: an artificial neural network approach. Agricultural Water Management, 98(5): 855-866.
  18. Mustafa, M.R., R.B. Rezaur, S. Saiedi and M.H. Isa. 2012. River suspended sediment prediction using various multilayer perceptron neural network training algorithms, a case study in Malaysia. Water Resources Management, 26(7): 1879-1897.
  19. Nour, M.H., D.W. Smith, M. Gamal El-Din and E.E. Prepas. 2006. Neural networks modelling of streamflow, phosphorus, and suspended solids: application to the Canadian Boreal Forest. Water Science and Technology, 53(10): 91-99.
  20. Olyaie, E., H. Banejad, K.W. Chau and A.M. Melesse. 2015. A comparison of various artificial intelligence approaches performance for estimating suspended sediment load of river systems, a case study in United States. Environmental Monitoring and Assessment, 187(4): 189-202.
  21. Tabatabaei, M., K. Solaimani, M.H. Roshan and A. Kavian. 2015. Estimation of daily suspended sediment concentration using artificial neural networks and data clustering by self-organizing. Journal of Watershed Management Research, 5(10): 98-116 (in Persian).
  22. Tabatabaei, M., A. Salehpour Jam and S.A. Hosseini. 2019a. Presenting a new approach to increase the efficiency of the sediment rating curve model in estimating suspended sediment load in watersheds, case study: Mahabad-Chai River, Lake Urmia Basin, West Azarbayejan Province, Iran. Journal of Watershed Management Research, 10(19): 181-193 (in Persian).
  23. Tabatabaei, M., A. Salehpour Jam and S.A. Hosseini. 2019b. Suspended sediment load prediction using non-dominated sorting genetic algorithm II. International Soil and Water Conservation Research, 7(20): 119-129.
  24. Tabatabaei, M., A. Salehpour Jam and J. Mossafaei. 2020. Improvement of the efficiency of artificial neural network model in suspended sediment simulation using particle swarm optimization algorithm. DOI: 10.22092/ijwmse.2019.125871.1638 (in Persian).
  25. Tayfur, G. 2012. Soft computing in water resources engineering: artificial neural networks, fuzzy logic and genetic algorithms. WIT Press, Dorset, 267 pages.
  26. Tfwala, S.S. and Y.M. Wang. 2016. Estimating sediment discharge using sediment rating curves and artificial neural networks in the Shiwen River, Taiwan. Water, 8(53): 1-15.
  27. Ulke, A., G. Tayfur and S. Ozkul. 2009. Predicting suspended sediment loads and missing data for Gediz River, Turkey. Journal of Hydrologic Engineering, 14(9): 954-965.