بررسی نقش متغیر بارندگی در عملکرد مدل‌سازی بار رسوب معلق روزانه (مطالعه موردی: حوزه‌ آبخیز سعید آباد چای)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم خاک، دانشگاه زنجان، زنجان، ایران

2 گروه خاکشناسی- بخش فیزیک و حفاظت خاک-دانشگاه زنجان

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

چکیده

آگاهی از مقدار دقیق بار رسوب معلق روزانه می‌تواند در شناخت وضعیت فرسایش و رسوب حوزه های آبخیز مورد استفاده قرار گیرد. در این تحقیق از مدل‌های هوشمند شبکه عصبی مصنوعی و برنامه‌ریزی بیان ژن برای برآورد بار رسوب معلق روزانه استفاده شد. همچنین با توجه به اهمیت پاسخ حوزه به متغیرهای ورودی به مدل‌ها، علاوه بر متغیر دبی، متغیر دینامیک بارندگی به‌دلیل نقش تأثیرگذار در ایجاد فرسایش و تولید رسوب نیز برای ورود به مدل‌ها انتخاب شد. نتایج حاصل از این تحقیق نشان داد که تمام مدل‌هایی که از متغیر بارندگی به همراه دبی استفاده کردند، دارای مقدار آماره‌های NSE و R2 بیشتر و مقدار آماره‌های RMSE و MAE کمتر در مقایسه با مدل‌هایی بودند که تنها از متغیر دبی برای برآورد بار رسوب معلق استفاده کردند. همچنین مدل GEP با ترکیب متغیر ورودی دبی لحظه‌ای، دبی متوسط روزانه، دبی متوسط روزانه تا سه روز قبل، بارندگی متوسط روزانه و بارندگی متوسط روزانه تا سه روز قبل، کارآمدترین مدل در برآورد صحیح بار رسوب معلق روزانه با بیشترین مقدار آماره‌های NSE برابر 90/0 و R2 برابر 92/0و کمترین مقدار آماره‌های RMSE برابر 42/2282 (ton/day) و MAE برابر 38/750 (ton/day) در مقایسه با مدل‌های شبکه عصبی مصنوعی بود. به-طور کلی نتایج این تحقیق نشان داد که متغیر دبی به تنهایی نتوانست واریانس رسوب رودخانه را به درستی تبیین نماید و استفاده از متغیر بارندگی به‌عنوان متغیر ورودی به مدل‌های هوشمند، نقش تأثیرگذار در افزایش دقت برآورد بار رسوب معلق داشت و استفاده از متغیر بارندگی به همراه متغیر دبی در طی فرآیند مدل‌سازی، کارآیی مدل‌ها را افزایش داد.

کلیدواژه‌ها

عنوان مقاله [English]

Investigating the role of precipitation variable in the performance of daily suspended sediment load modeling (case study: Saied Abad Chai watershed (

نویسندگان [English]

  • Adele Alijanpour Shalmani 1
  • Ali Reza Vaezi 2
  • MahmoudReza Tabatabaei 3
1 Soil Science. Department, University of Zanjan, Zanjan, Iran
2 Soil Sci. Dept, Univ. of Zanjan
3 Soil Conservation and Watershed Management Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran
چکیده [English]

Knowledge of the exact amount of daily suspended sediment loads can be used to identify the erosion and sedimentation status of the watersheds. In this research, intelligent artificial neural network and Gene Expression Programming was models used to estimate the daily suspended sediment load. Also, due to the importance of the watershed response to the input variables of the models, in addition to the flow discharge variable, the dynamic precipitation variable was also selected for entering the models due to its influential role in creating erosion and sediment production. The results of this study showed that all the models that used the precipitation variable along with the flow discharge had higher NSE and R2 statistic and lower RMSE and MAE statistics compared to the models that only the flow discharge variable to estimate the suspended sediment load. Also, GEP model with input variable combinations including instantaneous flow, average, average daily flow discharge with a delay time of three days, average daily precipitation and average daily precipitation with a delay time of three days, the most efficient model for estimating the daily suspended sediment load with the highest amount of statistics NSE was 0.90 and R2 was 0.92 and the lowest value of RMSE was 2282.42 (ton/day) and MAE was 750.38 (ton/day) compared to artificial neural network models. In general, the results of this research showed that the flow discharge variable, alone could not properly explain the variance of river sediment. Using precipitation variable as input variable to intelligent models played a significant role in increasing the precision of estimation of suspended sediment load and using precipitation variables In addition to the flow discharge variable, during the modeling process, the efficiency of the models was increased.

کلیدواژه‌ها [English]

  • Artificial neural network
  • Gene Expression Programming
  • Self-organizing map
  • Precipitation

مراجع

ASCE. 2000. artificial neural networks in hydrology, I: Preliminary concepts. Journal of Hydrologic Engineering, ASCE. 5. 2: 115–123.
Azamathulla, H.M., Cuan, Y.C., Ghani, A.A and Chang, C.K. 2013. Suspended sediment load prediction of river systems: GEP approach. Arabian Journal of Geosciences. 6. 9: 3469-3480.
Bowden, G.J., Maier, H.R and Dandy, G.C. 2002. Optimal division of data for neural network models in water resources applications. Water Resources Research. 38. 2: 2-10.
Chiang, J.L., Tsai, K.J., Chen, Y.R., Lee, M.H and Sun, J.W. 2014. Suspended Sediment Load Prediction Using Support Vector Machines in the Goodwin Creek Experimental Watershed. In EGU General Assembly Conference Abstracts. 16: 5285.
Emamgholizadeh, S and Karimi Demneh, R. 2018. The comparison of artificial intelligence models for the estimation of daily suspended sediment load: a case study on Telar and Kasilian Rivers in Iran. Water Science and Technology: Water Supply. 1-14. https://doi.org/10.2166/ws.2018.062.
Ferreira, C. 2006. Automaticlly defined functions in gene expression programming. In: Nedjah, N. Mourelle, L.M. Abraham, A. (Eds.), Genetic Systems Programming: Theory and Experiences, Studies in Computational Intelligence, Springer-Verlag. 13. Pp: 21-56.
Ferreira, C. 2004. Gene expression programming and the evolution of computer programs. In: Castro, L.N. Von Zuben, F.J. (Eds.), Recent Developments in Biologically Inspired Computing, Pp: 82-103.
Ferreira, C. 2001. Gene expression programming: a new adaptive algorithm for solving problems. Complex Systems. 13. 2: 87-129.
Ghavidel, S.Z.Z and Montaseri, M. 2014. Application of different data-driven methods for the prediction of total dissolved solids in the Zarinehroud basin. Stochastic Environmental Research and Risk Assessment. Pp: 1-18. 
Guven, A and Kişi, O. 2011. Estimation of Suspended Sediment Yield in Natural Rivers Using Machine-coded Linear Genetic Programming. Water Resources Management. 25. 2: 691-704.
Jaiyeola, A.T and Adeyemo, J. 2019. Performance comparison between genetic programming and sediment rating curve for suspended sediment prediction. African Journal of Science, Technology, Innovation and Development. 1-17.
Khan, M.Y.A., Tian, F., Hasan, F and Chakrapani, G.J. 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.
Kisi, O and Ozkan, C. 2017. A new approach for modeling sediment-discharge relationship: Local weighted linear regression. Water Resources Management. 30. 2: 1-23.
Kisi, O and Fedakar, H.I. 2014. Modeling of Suspended Sediment Concentration Carried in Natural Streams Using Fuzzy Genetic Approach. Computational Intelligence Techniques in Earth and Environmental Sciences, Springer Netherlands. Pp: 175-196.
Lopes, H.S and Weinert, W.R 2004. EGYPSIS: An enhanced gene expression programming approach for symbolic regression problems. Journal of Applied Mathematics and Computer Science. 14. 3: 375-384.
May, R.J., Maier, H.R and Dandy, G.C. 2010. Data splitting for artificial neural networks using SOM-based stratified sampling. Neural Networks. 23. 2: 283-294.
Melesse, A.M., Ahmad, S., McClain, M.E., Wang, X and Lim, Y.H. 2011. Suspended sediment load prediction of river systems: An artificial neural network. Agricultural Water Management. 98. 5: 855-866.
Nivesh, S., Kumar, P., Sawant, P and Verma, R. 2018. Application of Fuzzy Logic and Statistical Approaches for Estimation of Suspended Sediment Concentration. International Journal of Current Microbiology and Applied Sciences. 7. 2: 3716-3733.
Nivesh, S.h and Kumar, P. 2017. Modelling river suspended sediment load using artificial neural network and multiple linear regression: Vamsadhara River Basin, India. International Journal of Chemical Studies. 5. 5: 337-344.
Ouillon, S. 2018. Why and how do we study sediment transport? Focus on coastal zones and ongoing methods. Water. 10: 4. 390p.
Rodríguez-Blanco, M.L., Taboada-Castro, M.M., Palleiro-Suárez, L and Taboada-Castro, M.T. 2010. Temporal changes in suspended sediment transport in an Atlantic catchment, NW Spain. Geomorphology, 123. 1: 181-188.
Tabatabaei, M and Salehpour Jam, A. 2017. Optimization of sediment rating curve coefficients using evolutionary algorithms and unsupervised artificial neural network. Caspian Journal of Environmental Sciences. 15. 4: 387-401.
Tabatabaei, M., Solaimani, K. Habibnejad Roshan, M and Kavian, A. 2014. Estimation of daily Suspended Sediment Concentration using Artificial Neural Networks and data clustering by Self-Organizing Map (case study: Sira Hydrometry Station- Karaj Dam Watershed). Journal of Watershed Management Research, 5. 10: 98-116. (in persian)
Tayfur, G. 2012. Soft Computing in Water Resources Engineering - Artifical Neural Networks, Fuzzy Logic and Genetic Algorithms. WIT Press, Southampton, England, UK. 267p.
Theodosiou, M. 2011. Disaggregation & Aggregation of Time Series Components: A Hybrid Forecasting Approach Using Generalized Regression Neural Networks and the Theta Method, Neurocomputing 74: 896– 905.
Ulke, A., Tayfur, G and Ozkul, S. 2009. Predicting suspended sediment loads and missing data for Gediz River, Turkey. Journal of Hydrologic Engineering. 14. 9: 954-965.
Wang, P., Xu, L., Zhou, S., Fan, Z., Li, Y and Feng, S. 2010. A Novel Bayesian Learning Method for Information Aggregation in Modular Neural Networks. Expert Systems with Applications. 37: 1071– 1074.
Wilson, W.S. 2008. Classifier conditions using gene expression programming. IlliGAL report. 4998: 206-217.
Yadav, A., Chatterjee, S.S.k and Equeenuddin, M.d. 2018. Prediction of suspended sediment yield by artificial neural network and traditional mathematical model in Mahanadi river basin, India. Sustainable Water Resources Management. 4. 4: 745-759.
Zounemat-Kermani, M., Kişi, O., Adamowski, J and Ramezani-Charmahineh, A. 2016. Evaluation of data driven models for river suspended sediment concentration modeling. Journal of Hydrology. 16. 2: 1-40.
نشریه آبیاری و زهکشی ایران
دوره 13، شماره 6 - شماره پیاپی 78
بهمن و اسفند 1398
صفحه 1638-1650

فایل ها

هم رسانی

ارجاع به این مقاله

آمار