Sains Malaysiana 50(9)(2021): 2765-2779

http://doi.org/10.17576/jsm-2021-5009-22

Streamflow Estimation at Ungauged Basin using Modified Group Method of Data Handling

(Anggaran Aliran Sungai di Lembangan Tiada Data menggunakan Kaedah Kumpulan Terubahsuai Pengendalian Data)

BASRI BADYALINA¹*, ANI SHABRI² & MUHAMMAD FADHIL MARSANI²

¹Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Cawangan Johor, Kampus Segamat, 85000 Segamat, Johor Darul Takzim, Malaysia

²Department of Mathematics, Faculty of Science, Universiti Teknologi Malaysia, 81310 Skudai, Johor Darul Takzim, Malaysia

Diserahkan: 24 Ogos 2020/Diterima: 17 Januari 2021

ABSTRACT

Among the foremost frequent and vital tasks for hydrologist is to deliver a high accuracy estimation on the hydrological variable, which is reliable. It is essential for flood risk evaluation project, hydropower development and for developing efficient water resource management. Presently, the approach of the Group Method of Data Handling (GMDH) has been widely applied in the hydrological modelling sector. Yet, comparatively, the same tool is not vastly used for the hydrological estimation at ungauged basins. In this study, a modified GMDH (MGMDH) model was developed to ameliorate the GMDH model performance on estimating hydrological variable at ungauged sites. The MGMDH model consists of four transfer functions that include polynomial, hyperbolic tangent, sigmoid and radial basis for hydrological estimation at ungauged basins; as well as; it incorporates the Principal Component Analysis (PCA) in the GMDH model. The purpose of PCA is to lessen the complexity of the GMDH model; meanwhile, the implementation of four transfer functions is to enhance the estimation performance of the GMDH model. In evaluating the effectiveness of the proposed model, 70 selected basins were adopted from the locations throughout Peninsular Malaysia. A comparative study on the performance was done between the MGMDH and GMDH model as well as with other extensively used models in the area of flood quantile estimation at ungauged basins known as Linear Regression (LR), Nonlinear Regression (NLR) and Artificial Neural Network (ANN). The results acquired demonstrated that the MGMDH model possessed the best estimation with the highest accuracy comparatively among all models tested. Thus, it can be deduced that MGMDH model is a robust and efficient instrument for flood quantiles estimation at ungauged basins.

Keywords: GMDH; hyperbolic tangent; PCA; radial basis; ungauged basin

ABSTRAK

Antara tugas yang paling kerap dan penting bagi ahli hidrologi ialah memberikan anggaran ketepatan yang tinggi untuk pemboleh ubah hidrologi yang boleh dipercayai. Ini adalah sangat penting untuk projek penilaian risiko banjir, pembangunan tenaga air dan untuk pengurusan sumber air yang cekap. Pada masa ini, pendekatan Kaedah Pengendalian Data (GMDH) telah banyak digunakan dalam sektor pemodelan hidrologi. Namun, secara perbandingan, model tersebut tidak banyak digunakan untuk anggaran pemboleh ubah hidrologi di lembangan yang tiada data. Dalam kajian ini, model GMDH yang diubah suai (MGMDH) dikembangkan untuk memperbaiki prestasi model GMDH dalam menganggar pemboleh ubah hidrologi di lokasi yang tiada data. Model MGMDH terdiri daripada empat fungsi pemindahan yang merangkumi polinomial, hiperbolik tangen, sigmoid dan asas radial untuk anggaran pemboleh ubah hidrologi di lembangan yang tiada data; serta; ia menggabungkan Analisis Komponen Utama (PCA) dalam model GMDH. Tujuan PCA adalah untuk mengurangkan kerumitan model GMDH; Sementara itu, pelaksanaan empat fungsi pemindahan adalah untuk meningkatkan prestasi anggaran model GMDH. Untuk menilai keberkesanan model yang dicadangkan, 70 lembangan dari lokasi di seluruh Semenjung Malaysia telah dipilih. Kajian perbandingan mengenai prestasi dilakukan antara model MGMDH dan GMDH serta model lain yang digunakan secara meluas di kawasan taksiran kuantitatif banjir di lembangan yang tiada data yang dikenali sebagai Regresi Linear (LR), Regresi Bukan Linear (NLR) dan Rangkaian Neural Buatan (ANN). Hasil yang diperoleh menunjukkan bahawa model MGMDH memiliki anggaran terbaik dengan ketepatan yang tertinggi berbanding semua model yang diuji. Oleh itu, dapat disimpulkan bahawa model MGMDH adalah instrumen yang kuat dan cekap untuk anggaran kuantil banjir di lembangan yang tiada data.

Kata kunci: Asas radial; GMDH; hiperbolik tangen; lembangan tiada data; PCA

REFERENCES

Abbas, A.K., Al-haideri, N.A. & Bashikh, A.A. 2019. Implementing artificial neural networks and support vector machines to predict lost circulation. Egyptian Journal of Petroleum 28(4): 339-347.

Abdullah A. Mamun, Alias Hashim & Zalin Amir. 2012. Regional statistical models for the estimation of flood peak values at ungauged catchments: Peninsular Malaysia. Journal of Hydrologic Engineering 17(4): 547-553.

Alobaidi, M.H., Marpu, P.R., Ouarda, T.B.M.J. & Chebana, F. 2015. Regional frequency analysis at ungauged sites using a two-stage resampling generalized ensemble framework. Advances in Water Resources 84: 103-111.

Arsenault, R., Breton-Dufour, M., Poulin, A., Dallaire, G. & Romero-Lopez, R. 2019. Streamflow prediction in ungauged basins: Analysis of regionalization methods in a hydrologically heterogeneous region of Mexico. Hydrological Sciences Journal 64(11): 1297-1311.

Aziz, K., Haque, M.M., Rahman, A., Shamseldin, A.Y. & Shoaib, M. 2017. Flood estimation in ungauged catchments: Application of artificial intelligence based methods for Eastern Australia. Stochastic Environmental Research and Risk Assessment 31(6): 1499-1514.

Bowden, G.J., Dandy, G.C. & Maier, H.R. 2005. Input determination for neural network models in water resources applications. Part 1 - Background and methodology. Journal of Hydrology 301(1-4): 75-92.

Comber, A.J., Harris, P. & Tsutsumida, N. 2016. Improving land cover classification using input variables derived from a geographically weighted principal components analysis. ISPRS Journal of Photogrammetry and Remote Sensing 119: 347-360.

Du, T.Y. 2019. Dimensionality reduction techniques for visualizing morphometric data: Comparing principal component analysis to nonlinear methods. Evolutionary Biology 46(1): 106-121.

Farrokhi, F., Firoozfar, A. & Maghsoudi, M.S. 2020. Evaluation of liquefaction-induced lateral displacement using a GMDH-type neural network optimized by genetic algorithm. Arabian Journal of Geosciences 13(1): 4.

Fathi, S., Eftekhari Yazdi, M. & Adamian, A. 2020. Estimation of contact heat transfer between curvilinear contacts using inverse method and group method of data handling (GMDH)-type neural networks. Heat and Mass Transfer 56: 1961-1970.

Firdaus Mohamad Hamzah, Siti Hawa Mohd Yusoff & Othman Jaafar. 2019. L-moment-based frequency analysis of high-flow at Sungai Langat, Kajang, Selangor, Malaysia. Sains Malaysiana48(7): 1357-1366.

Hailegeorgis, T.T. & Alfredsen, K. 2017. Regional flood frequency analysis and prediction in ungauged basins including estimation of major uncertainties for Mid-Norway. Journal of Hydrology: Regional Studies 9: 104-126.

Hasfazilah Ahmat, Ahmad Shukri Yahaya & Nor Azam Ramli. 2015. PM₁₀ analysis for three industrialized areas using extreme value. Sains Malaysiana44(2): 175-185.

Hecht-Nielsen, R. 1990. Neurocomputing. Reading, MA: Addison-Wesley.

Ivakhnenko, A.G. 1971. Polynomial theory of complex systems. IEEE Transactions on Systems, Man, and Cybernetics. 4: 364-378.

Jolánkai, Z. & Koncsos, L. 2018. Base flow index estimation on gauged and ungauged catchments in Hungary using digital filter, multiple linear regression and artificial neural networks. Periodica Polytechnica Civil Engineering 62(2): 363-372.

Jolliffe, I.T. & Cadima, J. 2016. Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374(2065): 20150202.

Kim, N.W., Lee, J-Y., Park, D-H. & Kim, T-W. 2019. Evaluation of future flood risk according to RCP scenarios using a regional flood frequency analysis for ungauged watersheds. Water 11(5): 992.

Kondo, T. & Ueno, J. 2009. Medical image recognition of abdominal multi-organs by RBF GMDH-type neural network. International Journal of Innovative Computing Information and Control 5(1): 225-240.

Koopialipoor, M., Nikouei, S.S., Marto, A., Fahimifar, A., Armaghani, D.J. & Mohamad, E.T. 2019. Predicting tunnel boring machine performance through a new model based on the group method of data handling. Bulletin of Engineering Geology and the Environment 78(5): 3799-3813.

Mehrabani, M.N., Golafshani, E.M. & Ravanshadnia, M. 2020. Scoring of tenders in construction projects using group method of data handling. KSCE Journal of Civil Engineering 24: 1996-2008.

Meresa, H. 2019. Modelling of river flow in ungauged catchment using remote sensing data: Application of the empirical (SCS-CN), artificial neural network (ANN) and hydrological model (HEC-HMS). Modeling Earth Systems and Environment 5(1): 257-273.

Mohebbian, M.R., Dinh, A., Wahid, K. & Alam, M.S. 2020. Blind, cuff-less, calibration-free and continuous blood pressure estimation using optimized inductive group method of data handling. Biomedical Signal Processing and Control 57: 101682.

Noori, R., Karbassi, A. & Sabahi, M.S. 2010. Evaluation of PCA and gamma test techniques on ANN operation for weekly solid waste prediction. Journal of Environmental Management 91(3): 767-771.

Nurhaziyatul A. Yahya, Ruhaidah Samsudin, Ani Shabri & Faisal Saeed. 2019. Combined group method of data handling models using artificial bee colony algorithm in time series forecasting. Procedia Computer Science 163: 319-329.

Ojha, R. & Tripathi, S. 2018. Using attributes of ungauged basins to improve regional regression equations for flood estimation: A deep learning approach. ISH Journal of Hydraulic Engineering 24(2): 239-248.

Pandey, G.R. & Nguyen, V-T-V. 1999. A comparative study of regression based methods in regional flood frequency analysis. Journal of Hydrology 225(1-2): 92-101.

Prusty, M.R., Jayanthi, T., Chakraborty, J. & Velusamy, K. 2017. Feasibility of ANFIS towards multiclass event classification in PFBR considering dimensionality reduction using PCA. Annals of Nuclear Energy 99: 311-320.

Radaideh, M.I. & Kozlowski, T. 2020. Analyzing nuclear reactor simulation data and uncertainty with the group method of data handling. Nuclear Engineering and Technology 52(2): 287-295.

Rahmati, O. & Pourghasemi, H.R. 2017. Identification of critical flood prone areas in data-scarce and ungauged regions: A comparison of three data mining models. Water Resources Management 31(5): 1473-1487.

Rezazadeh Eidgahee, D., Haddad, A. & Naderpour, H. 2019. Evaluation of shear strength parameters of granulated waste rubber using artificial neural networks and group method of data handling. Scientiairanica 26(6): 3233-3244.

Rostami, A., Hemmati-Sarapardeh, A., Karkevandi-Talkhooncheh, A., Husein, M.M., Shamshirband, S. & Rabczuk, T. 2019. Modeling heat capacity of ionic liquids using group method of data handling: A hybrid and structure-based approach. International Journal of Heat and Mass Transfer 129: 7-17.

Samantaray, S. & Ghose, D.K. 2020. Modelling runoff in a River Basin, India: An integration for developing un-gauged catchment. International Journal of Hydrology Science and Technology 10(3): 248-266.

Seber, G.A.F. & Wild, C.J. 2003. Nonlinear Regression. Hoboken, New Jersey: John Wiley & Sons. p. 63.

Shaghaghi, S., Bonakdari, H., Gholami, A., Ebtehaj, I. & Zeinolabedini, M. 2017. Comparative analysis of GMDH neural network based on genetic algorithm and particle swarm optimization in stable channel design. Applied Mathematics and Computation 313: 271-286.

Shahabi, S., Mohammad-Javad, K. & Kermani, M.H. 2016. Hybrid wavelet-GMDH model to forecast significant wave height. Water Science and Technology: Water Supply 16(2): 453-459.

Shu, C. & Ouarda, T.B.M.J. 2008. Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology 349(1-2): 31-43.

Sivapalan, M., Takeuchi, K., Franks, S.W., Gupta, V.K., Karambiri, H., Lakshmi, V., Liang, X., Mcdonnell, J.J., Mendiondo, E.M., O’Connell, P.E., Oki, T., Pomeroy, J.W., Schertzer, D., Uhlenbrook, S. & Zehe, E. 2003. IAHS decade on predictions in ungauged basins (PUB), 2003-2012: Shaping an exciting future for the hydrological sciences. Hydrological Sciences Journal 48(6): 857-880.

Tang, Z. & Fishwick, P.A. 1993. Feedforward neural nets as models for time series forecasting. ORSA Journal on Computing 5(4): 374-385.

Tournier, J-D., Smith, R., Raffelt, D., Tabbara, R., Dhollander, T., Pietsch, M., Christiaens, D., Jeurissen, B., Yeh, C-H. & Connelly, A. 2019. MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation. NeuroImage 202: 116137.

Tsegaw, A.T., Alfredsen, K., Skaugen, T. & Muthanna, T.M. 2019. Predicting hourly flows at ungauged small rural catchments using a parsimonious hydrological model. Journal of Hydrology 573: 855-871.

Wałęga, A., Młyński, D., Wojkowski, J., Radecki-Pawlik, A. & Lepeška, T. 2020. New empirical model using landscape hydric potential method to estimate median peak discharges in mountain ungauged catchments. Water 12(4): 983.

Wong, F.S. 1991. Time series forecasting using backpropagation neural networks. Neurocomputing 2(4): 147-159.

Wu, J., Wang, Y., Zhang, X. & Chen, Z. 2016. A novel state of health estimation method of li-ion battery using group method of data handling. Journal of Power Sources 327: 457-464.

Yang, S., Yang, D., Chen, J., Santisirisomboon, J., Lu, W. & Zhao, B. 2020. A physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data. Journal of Hydrology 590: 125206.

Yang, S., Wang, P., Lou, H., Wang, J., Zhao, C. & Gong, T. 2019. Estimating river discharges in ungauged catchments using the slope-area method and unmanned aerial vehicle. Water 11(11): 2361.

Wan Zawiah Wan Zin, Abdul Aziz Jemain, Marina Zahari & Kamarulzaman Ibrahim. 2020. Scaling analysis for extreme rainfall events in Peninsular Malaysia. Sains Malaysiana 49(10): 2573-2585.

Wan Zin Wan Zawiah, Abdul Aziz Jemain, Kamarulzaman Ibrahim, Jamaludin Suhaila & Mohd Deni Sayang. 2009. A comparative study of extreme rainfall in Peninsular Malaysia: With reference to partial duration and annual extreme series. Sains Malaysiana 38(5): 751-760.

*Pengarang untuk surat-menyurat; email: basribdy@uitm.edu.my