نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه شهید چمران اهواز، اهواز، ایران

2 گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه شهید چمران اهواز ، اهواز ، ایران

چکیده

باتوجه به فقدان تجهیزات مناسب در ایستگاه‌های رسوب‌سنجی کشور و اندازه‌گیری بسیار محدود داده‌های رسوب، تخمین مقدار رسوب در روزهای فاقد داده در راستای مدیریت منابع آب و خاک بسیار حائز اهمیت است. در این پژوهش، از تکنیک‌های مختلف یادگیری ماشینی شامل، شبکه عصبی مصنوعی (ANN)، سیستم استنتاجی فازی-عصبی تطبیقی (ANFIS) و جنگل تصادفی (RF) به‌منظور شبیه‌سازی رسوب و برآورد آن در روزهای فاقد داده استفاده شد. برای دستیابی به اهداف پژوهش، ابتدا داده‌های بلند مدت هواشناسی و هیدرومتری (سال 2000 تا 2020) از سازمان‌های مرتبط جمع‌آوری و قبل از ورود به مدل پیش-پردازش شدند. متغیرهای ورودی به مدل‌ها شامل بارندگی، دبی جریان، شاخص پوشش گیاهی نرمال‌شده، دمای حداکثر و دمای حداقل بود و مقادیر رسوب معلق به عنوان خروجی تمام مدل‌ها در نظر گرفته شد. داده-ها قبل از مدل‌سازی با نسبت 70 -30 به دو گروه داده-های آموزشی و داده‌های آزمون تقسیم شدند. کارایی مدل‌ها با استفاده از پنج شاخص ضریب تبیین (R2)، جذر میانگین مربعات خطا (RMSE)، درصد اریب (PBIS)، میانگین خطای مطلق (MAE) و ضریب ناش-ساتکلیف (NSE) ارزیابی شدند. نتایج نشان داد که در مورد ایستگاه ماشین از بین تکنیک‌های مختلف، مدل شبکه عصبی دارای بیشترین مقدار ضریب تبیین (78/0) و کمترین مقدار خطا بود. همچنین در مورد ایستگاه منجنیق، مدل شبکه عصبی و نروفازی عملکرد تقریبا مشابهی را نشان دادند. لذا، مدل شبکه عصبی به عنوان مدل برتر در این پژوهش انتخاب شد. میانگین تولید سالانه رسوب برای کل دوره آماری بر اساس مدل شبکه عصبی، برابر با 1 تن در هکتار در سال بدست آمد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Simulation of daily suspended sediment of Roud-Zard River using different machine learning techniques

نویسندگان [English]

  • Heidar Ghafari 1
  • Hadi Ameri khah 2

1 Soil Science Department , Agriculture Faculty, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

2 Department of Soil Science, Faculty of Agriculture, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

چکیده [English]

Introduction: The processes of soil erosion and sediment transport along rivers are the main causes of some socio-economic and environmental problems, such as a reduction in water quality, storage capacity of dams, destruction of aquatic habitats, failure of hydroelectric power plants, and soil degradation. Therefore, understanding the sedimentation status of watersheds is crucial for the effective management of soil and water resources. However, due to the lack of technical and human resources, continuous recording of sediment data is not possible in most sediment measuring stations, and sediment data are recorded only for a few days. In such a situation, a model that can estimate the amount of sediment load using auxiliary variables such as stream discharge and rainfall becomes crucial. Today, it is believed that techniques based on artificial intelligence have a much greater ability to uncover hidden relationships between variables than classical methods and are thus very useful and effective in modeling natural processes.
Materials and methods: In this study, various machine learning techniques, including Artificial Neural Network (ANN), Adaptive Fuzzy-Neural Inference System (ANFIS), and Random Forest (RF), were used for sediment load modeling and sediment forecast for days without measurements. To achieve the research objectives, long-term meteorological and hydrometric data ranging from 2000 to 2020 were collected from related organizations and pre-processed before entering the model. The input variables for the models included 24-hour rainfall, flow rate, normalized difference vegetation index, maximum and minimum temperature, and daily suspended sediment as the dependent variable. Prior to modeling, the entire dataset was divided into two parts, training and testing, in a 70:30 ratio. Relationship modeling was performed using the training data, and model validation was conducted using the test dataset. The efficiency of the models was evaluated using two indicators, the coefficient of explanation (R2) and the root mean square error (RMSE). Additionally, morphometric parameters such as form factor (FF), drainage density (DF) coefficient, and relief ratio (RR) were utilized in modeling.
Results and discussion: The hydrological analysis of the basin revealed that the highest annual amount of rainfall and erosivity index were recorded at the Sheyvand station in the east of the basin, while the lowest values were observed at the Ramhormoz station. The highest average monthly flow rate of 5.8 cubic meters per second was obtained at the Manjeniq station in April, and at the Mashin station, the highest average monthly flow rate of 8.8 cubic meters per second was recorded in December and January. Morphometrically, the studied basin belonged to the class of elongated basins, sloping basins in terms of relief, and the medium class in terms of drainage density. Analysis of the time series of NDVI index showed that the highest vegetation cover occurred in March, while the lowest values were recorded in September and October. The annual trend of the vegetation index indicated an overall improvement in vegetation cover in the region from 2000 to 2020, with the NDVI value increasing from 0.15 to 0.22.
Among the different machine learning techniques studied, the Artificial Neural Network (ANN) model had the highest coefficient of explanation (R2=0.87) and the lowest RMSE for both sediment measuring stations in the region, making it the best model. The optimal inputs for the neural network model at Mashin station were daily average flow adjusted by the basin shape factor, daily rainfall, last day's rainfall, daily minimum temperature and daily maximum temperature. For the Manjeniq station, the optimal inputs were daily average flow, daily rainfall, last day's rainfall, cumulative rainfall for the past two days, and cumulative rainfall for the past three days. The NDVI index was removed from the model due to its low significance. The Random Forest (RF) model ranked second, and the Adaptive Fuzzy-Neural Inference System (ANFIS) model ranked third, with weak performance, especially for the Mashin station, where out-of-range errors occurred.
Temporal analysis of sediment values showed that the highest sediment production occurred in December and January for Mashin station and in April for Manjeniq station. The highest production of sediment occurred in 2006 and 2002, and the trend of changes from 2011 to 2018 showed a decline, attributed to consecutive droughts and lack of rainfall. The annual average sediment production calculated using the values estimated with the neural network model was 88017 tons, equivalent to 1 ton per hectare per year.
Conclusion: Overall, this research demonstrated that machine learning methods, especially the neural network model, are highly effective for modeling and predicting sediment on a daily scale. These methods can compensate for the lack of sediment measuring facilities and equipment in most existing hydrometric stations in the country and eliminate the need for continuous sediment data and other water quality parameters.

کلیدواژه‌ها [English]

  • Sedimentation
  • artificial neural network
  • adaptive fuzzy-neural inference system
  • random forest
  • understimation
  • Al-Mukhtar, M., 2019. Random forest, support vector machine, and neural networks to modelling suspended sediment in Tigris River-Baghdad. Environ Monit Assess 191, 673.
  • Arabkhedri, M., 2005. Investigation of suspended load in Iran's watershed basin. Iranian J. Water Resour. Res. 1: 2. 51-60. (In Persian)
  • Chen XY, Chau K.W., 2016. A hybrid double feedforward neural network for suspended sediment load estimation. Water Resour Manag 30: 2179–2194
  • Doğan E, Yüksel İ, Kişi Ö., 2007. Estimation of total sediment load concentration obtained by experimental study using artificial neural Networks. Environ Fluid Mech 7:271–288
  • Duan Y, Edwards JS, Dwivedi YK., 2019. Artificial intelligence for decision making in the era of Big Data–evolution, challenges and research agenda. Int J Inf Manag 48:63–71
  • Ebrahimi Heravi B., Rangzan K., Kabolizadeh M., Daneshian H. 2017. Comparing Methods of Artificial Neural Network and Fuzzy System in Determining Pre-flooding Warning (Case Study: Zard River Sub-basin- Khuzestan Province). Journal of Geography and Environmental Planning, Vol 28, No. 1, Ser No. (65) Spring 2017. (in Persian with English abstract)
  • Ebtehaj I, Bonakdari H., 2014. Performance evaluation of adaptive neural fuzzy inference system for sediment transport in sewers. Water Resour Manag 28:4765–4779
  • Fu Z., Yang M. Batista J. R., 2020. "Using Fuzzy Models and Time Series Analysis to Predict Water Quality", International Journal of Intelligent Systems and Applications (IJISA), Vol.12, No.2, pp.1-10,.
  • Gupta D., Hazarika B. B., Berlin M., Sharma U. M., and Mishra K. 2021. "Artificial intelligence for suspended sediment load prediction: a review" Environmental earth sciences 80, no. 9: 346. doi: 1007/s12665-021-09625-3
  • Hassan M, Shamim MA, Sikandar A, Mehmood I, Ahmed I, Ashiq SZ, Khitab A., 2015. Development of sediment load estimation models by using artificial neural networking techniques. Environ Monit Assess 187:686
  • Hayatzadeh , Chezgi J., Dastorani M.T. 2015. Evaluation of Sediments Using Rating Curve and Artificial Neural Network Methods by Combining Morphological Parameters of Basin (Case Study: Bagh Abbas Basin). Journal of Water and Soil Science 19(72): 217-228. (in Persian with English abstract)
  • Jang, J.S.R. 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics, 23 (3): 665–685.
  • Karimzadeh, H.; Alizadeh, M. 2018. Spatial Estimation of Soil Erosion in Iran Using RUSLE Model. Iran. J. Echohydology., 5, 551–569. (in Persian with English abstract)
  • Khazayi, M., Dastranj A, Kazemi M, Falah S, Adeli, B. 2014. Assessment corrective methods for estimating suspended sediment (Case Study: Beshaar Watershed). E.E.R.., 2014; 4 (3) :47-57 (in Persian with English abstract)
  • Kisi O. 2005. Suspended sediment estimation using neuro-fuzzy and neural network approaches. Hydrol Sci J 50 (4):683–696
  • Kisi, O., Haktanir, T., Ardiclioglu, M., Ozturk, O., Yalcin, E. and Uludag, S. 2009. Adaptive neuro-fuzzy computing technique for suspended sediment estimation. Advances in Engineering Software, 40(6): 438-444.
  • Lafdani EK, Nia AM, Ahmadi A., 2013. Daily suspended sediment load prediction using artificial neural networks and support vector machines. J Hydrol 478:50–62
  • Leal Filho W, Skanavis C, Kounani A, Brandli LL, Shiel C, do Paco A, Salvia AL., 2019. The role of planning in implementing sustainable development in a higher education context. J Clean Prod 235:678– 687
  • Li, L., Jiang P., Guang H., Dong L., Wu G., and Wu H. 2019. "Water quality prediction based on recurrent neural network and improved evidence theory: a case study of Qiantang River, China," Environmental Science and Pollution Research, vol. 26, no. 19, pp. 19879-19896, Mar.. London, UK, 2017; pp. 39–82.
  • Misra D, Oommen T, Agarwal A, Mishra SK, Thompson AM., 2009. Application and analysis of support vector machine based simulation for runoff and Sediment Yield. Biosyst Eng 103:527–535
  • Nourani V, Andalib G., 2015. Daily and monthly suspended sediment load predictions using wavelet based artificial intelligence approaches. J Mt Sci 12:85–100
  • Nourani, V., 2009. Using Artificial Neural Network (ANNs) For Sediment Load Forecasting of Talkherood River Mouth. Urban and Environmental Engineering, 3(1): 1- 6. (in Persian with English abstract)
  • Olyaie E, Banejad H, Kw C, Am M., 2015. A comparison of various artificial intelligence approaches performance for estimating suspended sediment load of river systems: a case study in United States. Environ Monit Assess 187:189
  • Pimentel, D. and Kounang, N., 1998. Ecology of soil erosion in ecosystems. Ecosystem 1, 418–426.
  • Pimentel, D., Burgess, M., 2013. Soil Erosion Threatens Food Production. Agriculture 3, 443-463.
  • Pohlert, T. 2015. Projected climate change impact on soil erosion and sediment uield in the River Elbe catchment. Springer International Publishing Switzerland, 97-108.
  • Rajabi M. Feyzolahpour M., Roostaiee S., 2015. Estimating Suspended Sediment Concentration by a Neaural Differential Evolution and Comparision it with ANFIS and RBF Models (Case study: Givi Chay River). 13-39. P 1-16. (in Persian with English abstract)
  • Rajaee T, Jafari H., 2020. Two decades on the artificial intelligence models advancement for modeling river sediment concentration: state-of-the-art. J Hydrol 588:125011
  • Rajpurkar, P., Chen, E., Banerjee, O., 2022.  AI in health and medicine. Nat Med 28, 31–38. https://doi.org/10.1038/s41591-021-01614-0
  • Rezaei, K., Pradhan, B., Vadiati, M., 2021. Suspended sediment load prediction using artificial intelligence techniques: comparison between four state-of-the-art artificial neural network techniques. Arab J Geosci 14, 215.
  • Riahi S, M Nasrabadi and SM Mosavi. 2013. Application of the Intelligent Systems and Statistical Models in Estimation of Suspended Sediment Distribution. Water and Soil Science 24-3. P. 231-242. (in Persian with English abstract)
  • Sadeghi, H. 2005. Development of sediment rating curve equations for rising and falling limbs of hydrograph using regression models. Iran. J. Water Res. 1: 1. 101-103. (In Persian)
  • Shamaei E, Kaedi M., 2016. Suspended sediment concentration estimation by stacking the genetic programming and neuro-fuzzy predictions. Appl Soft Comput 45:187–196
  • Tayfur, G., Ozdemir, S. and Singh, V. P., 2003. Fuzzy logic algorithm for runoff-induced sediment transport from bare soil surfaces. Advances in water Resource, 26(12): 1249-1256.
  • Vinutha, D.N. and Janardhana, M.R., 2014. Morphometry of the Payaswini Watershed, Coorg District, Karnataka, India, Using Remote Sensing and GIS Techniques. International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), 3, 516-524.
  • Walling, D.E. 2011. Human impact on the sediment loads of Asian rivers. Sediment Problems and Sediment. Management in Asian River Basins. IAHS Publ., 349, 37–51.
  • Walling, D.E. 2017. Measuring sediment yield from river basins. In Soil Erosion Research Methods; Routledge: London, UK,; pp. 39–82.
  • Yosefi, M. 2014. Suspended sediment estimation using neural network and algorithms assessment, case study: Lorestan Province. Journal of Watershed Management Research, 5(10): 85-97 (in Persian with English abstract)
  • Zounemat-KermaniM, Kişi Ö, Adamowski J, Ramezani-Charmahineh A., 2016. Evaluation of data driven models for river suspended sediment concentration modeling. J Hydrol 535:457–472
  • Zhou, Shangguan & Zhao. 2006. Zhou Z, Shangguan Z, Zhao D. Modeling vegetation coverage and soil erosion in the Loess Plateau Area of China. Ecological Modelling. 2006;198(1–2):263–268.