پیش‌بینی پیشروی آب شور در آبخوان ساحلی با استفاده از ماشین‌بردار پشتیبان رگرسیونی به‌عنوان مدل جایگزین

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکترا، گروه مهندسی عمران، دانشکده مهندسی، دانشگاه شهید چمران اهواز، اهواز، ایران

2 استاد، گروه مهندسی عمران، دانشکده مهندسی، دانشگاه شهبد چمران اهواز، اهواز، ایران

3 استادیار، گروه مهندسی عمران، دانشکده مهندسی، دانشگاه شهید چمران اهواز، اهواز، ایران

10.22093/wwj.2019.161020.2803

چکیده

پیش‌بینی هجوم آب شور به آبخوان ساحلی در اثر تغییر میزان برداشت از آب زیرزمینی یکی از پیش‌نیازهای مدیریت آب زیرزمینی است. این پژوهش قابلیت انواع مختلف مدل‌های ماشین‌بردار پشتیبان رگرسیونی (SVR) را برای پیش‌بینی میزان شوری در چاه پایش منتخب در یک آبخوان ساحلی کوچک تحت شرایط مختلف برداشت آب زیرزمینی بررسی می‌کند. مدل‌های SVR با مجموعه‌های ورودی (پمپاژگذرای تصادفی از چاه‌های آبده) حاصل از نمونه‌برداری ابرمکعب لاتین و خروجی (غلظت شوری در چاه پایش منتخب) آموزش یافته و آزمایش شدند. سپس، مدل‌های آموزش یافته و آزمایش شده برای پیش‌بینی میزان شوری در چاه پایش منتخب برای مجموعه داده‌های جدید پمپاژ استفاده شدند. قابلیت پیش‌بینی و تعمیم‌دهی عملی مدل‌ها در مقایسه با مدل رایج شبکه عصبی مصنوعی با استفاده از شاخص‌های ارزیابی مختلف بررسی شد. نتایج ارزیابی عملکرد مدل‌ها نشان داد که قابلیت پیش‌بینی مدل SVR چندجمله‌ای بر سایر مدل‌ها برتری دارد. همچنین همه مدل‌های SVR مورد بررسی به‌جز مدل SVR خطی، پیشروی آب شور را به‌طور قابل قبولی پیش‌بینی کردند. قابلیت پیش‌بینی و تعمیم‌دهی مدل‌های SVR چندجمله‌ای، استفاده از آنها را برای اتصال به الگوریتم بهینه‌سازی در شیوه بهینه‌سازی- شبیه‌سازی مبتنی بر مدل جانشین برای مدیریت آبخوان‌های ساحلی توصیه می‌کند.

کلیدواژه‌ها


عنوان مقاله [English]

Predicting Saltwater Intrusion into Coastal Aquifers Using Support Vector Regression Surrogate Models

نویسندگان [English]

  • Fatemeh Fa'al 1
  • Hamid Reza Ghafouri 2
  • Seyed Mohammad Ashrafi 3
1 PhD Student, Dept. of Civil Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
2 Prof., Dept. of Civil Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
3 Assist. Prof., Dept. of Civil Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
چکیده [English]

The prediction of the intrusion of saline water into coastal aquifers as a result of changing the amount of groundwater extractions is a prerequisite for managing groundwater. This study investigates the capability of different types of Support Vector Regression (SVR) models to predict salinity concentrations at the selected well in the small coastal aquifer under different groundwater abstraction conditions. SVR models were trained and tested using input (random transient pumping from the production wells) derived from Latin Hypercube Sampling and output (salinity concentration at the selected well) datasets. The trained and tested models were then used to predict salinity concentrations at the selected well for new pumping datasets. The models ability for predicting and generalizing compared with commonly used artificial neural network (ANN) model was evaluated using different performance criteria. The results of the performance evaluation of the models showed that the predictive capability of the polynomial SVR model is superior to other models. Also, comparing different performance criteria for all SVR models, except for linear SVR model, proved their acceptable predictive performance. The prediction and generalisation ability of polynomial SVR, recommends using these models to connect to the optimization algorithm for a surrogate model based simulation-optimization approach in sustainable management of coastal aquifers.

کلیدواژه‌ها [English]

  • Coastal Aquifers
  • Saltwater intrusion
  • Surrogate Models
  • Support vector regression
  • Prediction Capability

Bhattacharjya, R. K. & Datta, B. 2005. Optimal management of coastal aquifers using linked simulation optimization approach. Water Resources Management, 19, 295-320.

Bhattacharjya, R. K., Datta, B. & Satish, M. G. 2007. Artificial neural networks approximation of density dependent saltwater intrusion process in coastal aquifers. Journal of Hydrologic Engineering, 12, 273-282.

Chevalier, R. F., Hoogenboom, G., Mcclendon, R. W. & Paz, J. A. 2011. Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks. Neural Comput and Applic, 20, 151-159.

Chitsazan, N. 2014. Bayesian saltwater intrusion prediction and remediation design under uncertainty. PhD Thesis, Louisiana State University, USA.

Christelis, V. & Mantoglou, A. 2016. Pumping optimization of coastal aquifers assisted by adaptive metamodelling methods and radial basis functions. Water Resources Management, 30(15), 5845-5859.

Cristianini, N. & Shawe-taylor, J. 2014. An introduction to support vector machines and other Kernel-Based learning methods, Cambridge University Press.

Dhar, A. & Datta, B. 2009. Saltwater intrusion management of coastal aquifers. I: linked simulation-optimization. Journal of Hydrologic Engineering, 14, 1263-1272.

Forrester, A., Sobester, A. & Keane, A. 2008. Engineering design via surrogate modelling: a practical guide, John Wiley & Sons. N.Y.

Kopsiaftis, G., Protopapadakis, E., Voulodimos, A., Doulamis, N. & Mantoglou, A. 2019. Gaussian process regression tuned by bayesian optimization for seawater intrusion prediction. Computational Intelligence and Neuroscience, 10, 1-12.

Kourakos, G. & Mantoglou, A. 2009. Pumping optimization of coastal aquifers based on evolutionary algorithms and surrogate modular neural network models. Advances in Water Resources, 32 (4), 507-521.

Lal, A. & Datta, B. 2018. Development and implementation of support vector machine regression surrogate models for predicting groundwater pumping-Induced saltwater intrusion into coastal aquifers. Water Resources Management, 32(7), 2405-25419.

Lin, R. S., Horn, S. D., Hurdle, J. F. & GoldfarB-Rumyantzev, A. S. 2008. Single and multiple time-point prediction models in kidney transplant outcomes. Journal of Biomedical Informatics, 41, 944-952.

Loh, W.-L. 1996. On Latin hypercube sampling. The Annals of Statistics, 24, 2058-2080.

Papadopoulou, M. P., Nikolos, I. K. & Karatzas, G. P. 2010. Computational benefits using artificial intelligent methodologies for the solution of an environmental design problem: saltwater intrusion. Water Science Technology, 62, 1479-1490.

Pillay, N. 2004. An investigation into the use of genetic programming for the induction of novice procedural programming solution algorithms in intelligent programming tutors. University of KwaZulu-Natal Durban.

Rao, S., Sreenivasulu, V., Bhallamudi, S. M., Thandaveswara, B. & Sudheer, K. 2004. Planning groundwater development in coastal aquifers. Hydrological Sciences Journal, 49, 155-170.

Razavi, S., Tolson, B. A. & Burn, D. H. 2012. Numerical assessment of metamodelling strategies in computationally intensive optimization. Environmental Modelling Software, 34, 67-86.

Roy, D. K. 2018. Development of a sustainable groundwater management strategy and sequential compliance monitoring to control saltwater intrusion in coastal aquifers. PhD Thesis, James Cook University, Australia.

Roy, D. K. & Datta, B. 2017a. Fuzzy C-mean clustering based inference system for saltwater intrusion processes prediction in coastal aquifers. Water Resources Management, 31, 355-376.

Roy, D. K. & Datta, B. 2017b. Multivariate adaptive regression spline ensembles for management of multilayered coastal aquifers. Journal of Hydrologic Engineering, 22, 04017031.

Roy, D. K. & Datta, B. 2017c. Optimal management of groundwater extraction to control saltwater intrusion in multi-layered coastal aquifers using ensembles of adaptive neuro-fuzzy inference system. World Environmental and Water Resources Congress. 139-150.

Shu, C. & Ouarda, T. 2008. Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology, 349, 31-43.

Sreekanth, J. & Datta, B. 2010. Multi-objective management of saltwater intrusion in coastal aquifers using genetic programming and modular neural network based surrogate models. Journal of Hydrology, 393, 245-256.

Sreekanth, J. & Datta, B. 2011. Comparative evaluation of genetic programming and neural network as potential surrogate models for coastal aquifer management. Water Resources Management, 25, 3201-3218.

Tenne, Y. & Goh, C.-K. 2010. Computational intelligence in expensive optimization problems, Springer Science & Business Media, Switzerland.

Vapnik, V. 1995. The nature of statistical learning theory, Springer, New York.

Werner, A. D., Bakker, M., Post, V. E., Vandenbohede, A., Lu, C., Ataie-Ashtiani, B., et al. 2013. Seawater intrusion processes, investigation and management: recent advances and future challenges. Advances in Water Resources, 51, 3-26.

Yoon, H., Jun, S.-C., Hyun, Y., Bae, G.-O. & Lee, K.-K. 2011. A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. Journal of Hydrology, 396, 128-138.

Yoon, H., KIM, Y., Ha, K., Lee, S.-H. & Kim, G.-P. 2017. Comparative evaluation of ANN- and SVM-time series models for predicting freshwater-saltwater interface fluctuations. Water, Doi: 36390/w9050323.