Simulation of groundwater head using LS-SVM and comparison with ANN & MLR

Document Type : Research paper

Authors

1 University of Tehran

2 Department of Irrigation and Drainage, University of Tabriz

3 Department of Irrigation and Drainage, College of Aburaihan, University of Terhran

4 Department of Water Resources monitoring, Jahad Daneshgahi Environment Institut, Guilan, Rasht

Abstract

Nowadays, in order to implement management scenarios, choosing appropriate practical solutions for managing groundwater resources as well as determining the appropriate groundwater harvesting rate requires a simplified aquifer model and its simulation. On the other hand, modeling of groundwater aquifers is very important for simulating and predicting the water level. The first step in groundwater management is the simulation of groundwater level which is followed by its prediction based on the factors affecting the groundwater level. In this study, three models, namely, least-square support vector machine (LS-SVM), multivariate linear regression (MLR) and artificial neural networks (ANN) were used to simulate the groundwater level. The study was carried out on Imam-Zadeh Jafar aquifer in Kohgilouye and Boyerahmad province, Iran. To do this, several input features including groundwater level in previous month, precipitation, temperature, aquifer exploitation, and evaporation in the current month were considered to predict groundwater level at the end of the current month. The target time period was monthly data of 20 years from 1997 to 2016. About 75% of the data were used for model training and the remaining for test. The results revealed that all three models were capable of simulating groundwater level with acceptable performance. Among them, LS-SVM having groundwater level in previous month, aquifer exploitation, and precipitation as input features resulted in the highest accuracy with RMSE, MAPE, and R2 equal to 0.61, 0.069, and 0.99, respectively. These models can be used as alternatives for numerical models to manage and predict groundwater level in groundwater resources management problems.

Keywords

References

باباعلی، حر، دهقانی، ر. 1396. مقایسه مدل های شبکه عصبی موجک و شبکه عصبی مصنوعی در پیش بینی سطح آب زیرزمینی، مجله هیدروژئولوژی، 2 (2)، 96-108.
رضای، ا، خاشعی سیوکی، ع، و، شهیدی، ع. 1393. طراحی شبکه پایش سطح آب زیر‏زمینی با استفاده از مدل حداقل مربعات ماشین بردار پشتیبان (LS-، SVM), تحقیقات آب و خاک ایران، (4)45، 389-396.
سعیدی رضوی، ب، عرب، عر. 1397. پیش‌بینی سطح آب زیرزمینی با استفاده از مدل‌های منطق فازی، شبکه عصبی و سری‌ زمانی، مجله هیدروژئولوژی، (2) 3 ،61-83.
گویلی،س، جوادی، س، بنی حبیب، م، ا، و، ثانی خانی، ه. 1397 مقایسه مدل‌های هوشمند در پیش‌بینی نوسانات تراز سطح آب دریاچه زریوار با درنظرگیری تراز آب زیرزمینی. مجله تحقیقات منابع آب ایران، (3)14، 268-277.
عینی، م ر، جوادی، س، دلاور، م، دارند‎، م. 1397. ‎شناخت دقت پایگاه دادۀ ماهواره‏ ای بارش PERSIANN-CDR در شبیه‏ سازی رواناب مدل SWAT بر روی پهنۀ حوضۀ دریاچۀ مهارلو‎. پژوهشهای جغرافیای طبیعی 50 (3), 563-576.
ندیری، عطاالله، طاهرخانی، ز، و، صادقی, ف. 1396. پیش‌بینی سطح آب زیرزمینی دشت بستان‌آباد با استفاده از ترکیب نظارت شده مدل‌های هوش‌ مصنوعی. مجله تحقیقات منابع آب ایران, 13(3), 43-55.
نیکبخت، ج، و، نوری، س، 1395. پیش‌‌بینی تراز سطح آب زیرزمینی با کمک شبکه‌های موجک-عصبی (مطالعه موردی: دشت مراغه-آذربایجان‌شرقی).، مجله هیدروژئولوژی، (1)1، 29-43.
Banihabib ME, Mousavi-Mirkalaei P. Extended linear and non-linear auto-regressive models for forecasting the urban water consumption of a fast-growing city in an arid region. Sustainable Cities and Society. 2019 Jul 1;48:101585.
Bouzerdoum, M., Mellit, A. and Pavan, A.M., 2013. A hybrid model (SARIMA–SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant. Solar Energy, 98, pp.226-235.
Cawley, G.C. and Talbot, N.L., 2002. Improved sparse least-squares support vector machines. Neurocomputing, 48(1-4), pp.1025-1031.
Chang, J., Wang, G. and Mao, T., 2015. Simulation and prediction of suprapermafrost groundwater level variation in response to climate change using a neural network model. Journal of Hydrology, 529, pp.1211-1220.
Chang, J., Wang, G. and Mao, T., 2015. Simulation and prediction of suprapermafrost groundwater level variation in response to climate change using a neural network model. Journal of Hydrology, 529, pp.1211-1220.
Chen, L. H., Chen, C. T., & Pan, Y. G. 2009. Groundwater level prediction using SOM-RBFN multisite model. Journal of Hydrologic Engineering, 15(8), 624-631.
Cortes, C. and Vapnik, V., 1995. Support-vector networks. Machine learning, 20(3), pp.273-297.
Coulibaly, P., Anctil, F., Aravena, R. and Bobée, B., 2001. Artificial neural network modeling of water table depth fluctuations. Water resources research, 37(4), pp.885-896.
Emamgholizadeh, S., Moslemi, K. and Karami, G., 2014. Prediction the groundwater level of bastam plain (Iran) by artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). Water resources management, 28(15), pp.5433-5446.
Gestel, T.V., Suykens, J.A., Lanckriet, G., Lambrechts, A., Moor, B.D. and Vandewalle, J., 2002. Bayesian framework for least-squares support vector machine classifiers, Gaussian processes, and kernel Fisher discriminant analysis. Neural computation, 14(5), pp.1115-1147.
Guzman, S.M., Paz, J.O., Tagert, M.L.M. and Mercer, A.E., 2019. Evaluation of Seasonally Classified Inputs for the Prediction of Daily Groundwater Levels: NARX Networks Vs Support Vector Machines. Environmental Modeling & Assessment, 24(2), pp.223-234.
Haykin, S., 1994. Neural networks: a comprehensive foundation. Prentice Hall PTR.
Jalalkamali, A., Sedghi, H. and Manshouri, M., 2010. Monthly groundwater level prediction using ANN and neuro-fuzzy models: a case study on Kerman plain, Iran. Journal of hydroinformatics, 13(4), pp.867-876.
Khaki, M., Yusoff, I. and Islami, N., 2015. Simulation of groundwater level through artificial intelligence system. Environmental earth sciences, 73(12), pp.8357-8367.
Krishna, B., Satyaji Rao, Y.R. and Vijaya, T., 2008. Modelling groundwater levels in an urban coastal aquifer using artificial neural networks. Hydrological Processes: An International Journal, 22(8), pp.1180-1188.
Lippman, R.P., 1987. An introduction to computing with neural nets. iEEE ASSP Magazine. DeTienne et al./NEURAL NETWORKS AS STATISTICAL TOOLS, 263, pp.4-22.
Moghaddam, H.K., Moghaddam, H.K., Kivi, Z.R., Bahreinimotlagh, M. and Alizadeh, M.J., 2019. Developing comparative mathematic models, BN and ANN for forecasting of groundwater levels. Groundwater for Sustainable Development, 9, p.100237.
Milan, S. G., Roozbahani, A., & Banihabib, M. E. 2018. Fuzzy optimization model and fuzzy inference system for conjunctive use of surface and groundwater resources. Journal of hydrology, 566, 421-434.
Nadiri, A. A., Naderi, K., Khatibi, R., & Gharekhani, M., 2019. Modelling groundwater level variations by learning from multiple models using fuzzy logic. Hydrological sciences journal, 64(2), 210-226.‏
Nie, S., Bian, J., Wan, H., Sun, X. and Zhang, B., 2016. Simulation and uncertainty analysis for groundwater levels using radial basis function neural network and support vector machine models. Journal of Water Supply: Research and Technology—AQUA, 66(1), pp.15-24.
Nourani, Vahid, Asghar Asghari Mogaddam, and Ata Ollah Nadiri., 2008 An ANN‐based model for spatiotemporal groundwater level forecasting. Hydrological Processes: An International Journal 22.26  5054-5066.
Nourani, V., Ejlali, R.G. and Alami, M.T., 2011. Spatiotemporal groundwater level forecasting in coastal aquifers by hybrid artificial neural network-geostatistics model: a case study. Environmental Engineering Science, 28(3), pp.217-228.
Ocampo-Duque, W., Ferre-Huguet, N., Domingo, J. L., & Schuhmacher, M. 2006. Assessing water quality in rivers with fuzzy inference systems: A case study. Environment International, 32(6), 733-742.
Rajaee, T., Ebrahimi, H., & Nourani, V. (2019). A review of the artificial intelligence methods in groundwater level modeling. Journal of hydrology.
Roozbahani, A., Ebrahimi, E., & Banihabib, M. E. 2018. A framework for ground water management based on bayesian network and MCDM techniques. Water resources management, 32(15), 4985-5005.
Sahoo S, Jha MK. Groundwater-level prediction using multiple linear regression and artificial neural network techniques: a comparative assessment. Hydrogeology Journal. 2013 Dec 1;21(8):1865-87.
Sreekanth, P.D., Sreedevi, P.D., Ahmed, S. and Geethanjali, N., 2011. Comparison of FFNN and ANFIS models for estimating groundwater level. Environmental Earth Sciences, 62(6), pp.1301-1310.
Suykens, J.A. and Vandewalle, J., 1999. Least squares support vector machine classifiers. Neural processing letters, 9(3), pp.293-300.
Wen, X., Feng, Q., Deo, R.C., Wu, M. and Si, J., 2016. Wavelet analysis–artificial neural network conjunction models for multi-scale monthly groundwater level predicting in an arid inland river basin, northwestern China. Hydrology Research, 48(6), pp.1710-1729.
Yoon, H., Hyun, Y., Ha, K., Lee, K.K. and Kim, G.B., 2016. A method to improve the stability and accuracy of ANN-and SVM-based time series models for long-term groundwater level predictions. Computers & geosciences, 90, pp.144-155.
Yu, H., Wen, X., Feng, Q., Deo, R.C., Si, J. and Wu, M., 2018. Comparative study of hybrid-wavelet artificial intelligence models for monthly groundwater depth forecasting in extreme arid regions, Northwest China. Water resources management, 32(1), pp.301-323.
Zyoud, S. H., Kaufmann, L. G., Shaheen, H., Samhan, S., & Fuchs-Hanusch, D. 2016. A framework for water loss management in developing countries under fuzzy environment: Integration of Fuzzy AHP with Fuzzy TOPSIS. Expert Systems with Applications, 61, 86-105.
Hydrogeology
Volume 5, Issue 1
September 2020
Pages 118-133

Files

Share

How to cite

Statistics