با همکاری انجمن هیدرولیک ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشیار، گروه مهندسی عمران، دانشگاه آزاد اسلامی واحد خرم آباد، خرم آباد، ایران

2 استادیارگروه عمران، مرکز تحقیقات مواد و انرژی، واحد دزفول، دانشگاه آزاد اسلامی، دزفول، ایران.

3 دکتری علوم و مهندسی آب، بخش تحقیقات حفاظت خاک و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان لرستان، سازمان تحقیقات، آموزش و ترویج کشاورزی، خرم آباد، ایران.

10.22077/jaaq.2025.8579.1083

چکیده

در این پژوهش از مدل هیریدی رگرسیون بردار پشتیبان با الگوریتم های بهینه سازی موجک، کرم شب تاب و گرگ خاکستری به منظور برآورد میزان سختی آب زیرزمینی چاه ناصروند واقع در دشت خرم آباد استان لرستان استفاده شد. جهت مدل‌سازی از داده‌های کیفی چاه موجود شامل پارامتر هیدروژن کربنات (HCO3)، کلرید (Cl)، سولفات (So4)، منیزیم(mg)، کلسیم(ca) و سختی آب (TH) همگی بر حسب ppm در مقیاس زمانی ماهانه در طی سال آبی (1402-1382) بعنوان ورودی و میزان سختی آب زیرزمینی به عنوان خروجی مدل انتخاب گردید. به منظور ارزیابی عملکرد مدلها از معیارهای ارزیابی ضریب همبستگی، ریشه میانگین مربعات خطا، میانگین قدر مطلق خطا و ضریب نش ساتکلیف استفاده شد. همچنین جهت تحلیل نتایج مدلها از نمودار سری زمانی و باکس پلات و تیلور استفاده شد. نتایج نشان داد سناریو های ترکیبی در مدلهای مورد بررسی باعث بهبود عملکرد مدل می شود. مقایسه نتایج نشان داد مدل رگرسیون بردار پشتیبان – موجک عملکرد بهتری نسبت به مدل رگرسیون بردار پشتیبان-گرگ خاکستری در مدل‌سازی دارد، بگونه ای که مدل رگرسیون بردار پشتیبان – موجک با ضریب همبستگی 0/917، کمترین ریشه میانگین مربعات (ppm) 0/190، کمترین میانگین قدر مطلق خطا (ppm) 0/115 و بیشترین ضریب نش ساتکلیف 0/920 در مرحله صحت سنجی در اولویت قرار گرفت. درمجموع نتایج نشان داد استفاده از مدلهای هوشمند مبتنی بر رویکرد رگرسیون بردار پشتیبان می تواند رویکردی موثر در مدیریت کیفی آبهای زیرزمینی باشد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Assessment of Groundwater Hardness in Khorramabad Plain Using Hybrid Models Based on Metaheuristic Algorithms

نویسندگان [English]

  • Hamidreza Babaali 1
  • Ebrahim Nohani 2
  • Reza Dehghani 3

1 Associate Professor, Department of Civil Engineering, Islamic Azad University, Khorramabad branch, Khorramabad, Iran

2 Assistant Professor, Department of Civil Engineering, Materials and Energy Research Center, Dezful Branch, Islamic Azad University, Dezful, Iran.

3 PhD in Water Sciences and Engineering, Department of Soil Conservation and Watershed Management, Lorestan Province Agriculture and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization,

چکیده [English]

In this study, a hybrid Support Vector Regression (SVR) model, combined with optimization algorithms including Wavelet, Firefly, and Grey Wolf, was employed to estimate groundwater hardness at the Naservand well in the Khorramabad Plain of Lorestan Province. For modeling, monthly quality data of the well during the water year (1382-1402) were used. This included parameters such as bicarbonate (HCO3), chloride (Cl), sulfate (SO4), magnesium (Mg), calcium (Ca), and total hardness (TH), all measured in ppm, which were used as inputs. Groundwater hardness was selected as the model output. To evaluate the performance of the models, assessment metrics such as the correlation coefficient, root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency coefficient (NSE) were used. Time series, box plots, and Taylor diagrams were also used for analyzing the model results. The results indicated that hybrid scenarios in the studied models improve the model’s performance. Comparing results showed that the Support Vector Regression-Wavelet model performed better than the Support Vector Regression-Grey Wolf model, with the Support Vector Regression-Wavelet model achieving a correlation coefficient of 0.917, the lowest RMSE of 0.190 ppm, the lowest MAE of 0.115 ppm, and the highest NSE of 0.920 in the validation stage. Overall, the results indicate that using intelligent models based on the Support Vector Regression approach can be an effective approach for managing groundwater quality.

کلیدواژه‌ها [English]

  • Groundwater
  • Khorramabad
  • Support Vector Regression
  • Metaheuristics
Chandel, N., Gupta, S., Ravi, A. (2024).Ground Water Quality Analysis using Machine Learning Techniques: a Critical Appraisal. Journal of Mining and Environment (JME), 15(2),  419-426.https://doi.org/10.22044/jme.2023.13452.2484
Chawla, V.K., Chanda, A.K., Angra, S. (2019). The scheduling of automatic guided vehicles for the workload balancing and travel time minimi-zation in the flexible manufacturing system by the nature-inspired algorithm. Journal of Project Management, 4(1):19-30.10.5267/j.jpm.2018.8.001
Dehghani, R., Babaali, H.(2023). Evaluation of Statistical Models and Modern Hybrid Artificial Intelligence in Simulation of Runoff Precipitation Process. Sustain. Water Resour. Manag, 8, 154-172. https://doi.org/10.1007/s40899-022-00743-9.
Dehghani, R., Torabi Poudeh, H., Younesi, H., Shahinejad, B.(2020). Daily Streamflow Prediction Using Support Vector Machine-Artificial Flora (SVM-AF) Hybrid Model. Acta Geophysica, 68(6), 51-66. https://doi.org/10.1007/s11600-020-00472-7
Dehghani, R., Torabi, H.(2021). Dissolved oxygen concentration predictions for running waters using hybrid machine learning techniques. Modeling Earth Systems and Environment, 6(2), 64-78. https://doi.org/10.1007/s40808-021-01253-x.
Dwivedi, S. L., & Pathak, V. (2007). A preliminary assignment of water quality index to Mandakini River, Chitrakoot. Indian Journal of Environmental Protection, 27(11), 103-122.10.4236/jwarp.2011.36050.
Emami, S., Emami, H., Choopan, Y., Jahandideh, O.(2021). Modeling groundwater quality using three novel hybrid support vector regression models. Advances in Environmental Technology .2 (4),99-110.10.22104/aet.2021.4286.1212
Gupta, S. K., Singh, P. K., Tyagi, J., Sharma, G., & Jethoo, A. S. (2020). Rainstorm‐generated sediment yield model based on soil moisture proxies (SMP). Hydrological Processes, 34(16), 3448-3463. https://doi.org/10.1002/hyp.13789.
Gupta, S. K., Tyagi, J., Sharma, G., Jethoo, A. S., & Singh, P. K. (2019). An event-based sediment yield and runoff modeling using soil moisture balance/budgeting (SMB) method. Water Resources Management, 33, 3721-3741.https://doi.org/10.1007/s11269-019-02329-1.
Khan, M. F., Aadil, F., Maqsood, M., Khan, S., & Bukhari, B. H. (2018). An efficient optimization technique for node clustering in VANETs using gray wolf optimization. KSII Transactions on Internet and Information Systems (TIIS), 12(9), 4228-4247.‏
Kisi, O., Karahan, M., Sen, Z. (2006). River-suspended sediment modeling using the fuzzy logic approach. Hydrol Process, 20(2),4351-4362.10.1002/hyp.6166.
Mohammed, M.A.A., Khleel, N.A.A., Szabó, N.P., Szűcs , P. (2023). Modeling of groundwater quality index by using artificial intelligence algorithms in northern Khartoum State, Sudan. Model. Earth Syst. Environ. 9, 2501–2516.https://doi.org/10.1007/s40808-022-01638-6.
Nagy, H. M., Watanabe, K. A. N. D., & Hirano, M. (2002). Prediction of sediment load concentration in rivers using artificial neural network model. Journal of Hydraulic Engineering, 128(6), 588-595.‏
Nourani, V., Ghaffari, A., Behfar, N., Foroumandi, E., Zeinali, A., Qing, C., Sankaran, A.(2024).Spatiotemporal assessment of groundwater quality and quantity using geostatistical and ensemble artificial intelligence tools. Journal of Environmental Management.355(4),120-145.10.1016/j.jenvman.2024.120495 .
Nourani, V., Tajbakhsh, A.D., Molajou, A. (2018). Data mining based on wavelet and decision tree for rainfall-runoff simulation. Hydrol. Res, 50, 75–84. https://doi.org/ 10.2166/nh.2018.049.
Ostu, N. A. (1979). Threshold Selection Method from Gray-Level Histograms [J]. IEEE Transactions on Systems Man and Cybernetics,9 (1), 62-66.10.1109/TSMC.1979.4310076.
Raj, C., & Singh, V. (2021). Spatial and temporal variation of fluvial islands and sandbars in River Ganga from Bhagalpur to Farakka during 1955– 2019. Sustainable Water Resources Management, 7(3), 22-38.https://doi.org/10.1007/s40899-021-00522-y.
Shin, S., Kyung, D., Lee, S., Taik & Kim, J., and Hyun, J. (2005). An application of support vector machines in bankruptcy prediction model. Expert Systems with Applications, 28(4), 127-135.https://doi.org/10.1016/j.eswa.2004.08.009.
Vapnik, V., Chervonenkis, A.(1991). The necessary and sufficient conditions for consistency in the empirical risk minimization method. Pattern Recognition and Image Analysis,1(3), 283-305.10.12691/jgg-2-3-9.
Vapnik, V.N. (1995).The nature of statistical learning theory. Springer, New York, 3(1), 250-320.https://doi.org/10.1007/978-1-4757-3264-1.
Vapnik, V.N.(1998). Statistical learning theory. Wiley, New York, 4(1), 250-320. https://doi.org/10.1007/978-1-4757-3264-1.
Wang, D., Safavi, A.A., and Romagnoli, J.A.(2000). Wavelet-based adaptive robust M-estimator for non-linear system identification. AIChE Journal,46(4),  1607-1615. https://doi.org/10.1002/aic.690460812.
Yan, X., Zhu, Y., Wu, J., Chen, H.(2012). An improved firefly algorithm with adaptive strategies. Adv Sci Lett, 16(1), 249–254.https://doi.org/10.1016/j.eswa.2020.113340.
Yang, X.S.(2008). Firefly algorithm, nature-inspired meta-heuristic algorithms. Wiley Online Libr, 20, 79–90.https://doi.org/10.1007/978-3-642-29694-9_16.
Zeidalinejad, N., Dehghani, R.(2023). Use of meta-heuristic approach in the estimation of aquifer's response to climate change under shared socioeconomic pathways. Groundwater for Sustainable Development, 20(4), 112-132.https://doi.org/10.1016/j.gsd.2022.100882.
Zhu, Y. M., Lu, X. X., & Zhou, Y. (2007). Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology, 84(1-2), 111-125.‏