Smart Structures and Systems

  • 제32권1호
  • /
  • Pages.37-47
  • /
  • 2023
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Teaching-learning-based strategy to retrofit neural computing toward pan evaporation analysis

  • 투고 : 2020.09.09
  • 심사 : 2023.07.07
  • 발행 : 2023.07.25
⟨ 이전 논문 다음 논문 ⟩

초록

Indirect determination of pan evaporation (PE) has been highly regarded, due to the advantages of intelligent models employed for this objective. This work pursues improving the reliability of a popular intelligent model, namely multi-layer perceptron (MLP) through surmounting its computational knots. Available climatic data of Fresno weather station (California, USA) is used for this study. In the first step, testing several most common trainers of the MLP revealed the superiority of the Levenberg-Marquardt (LM) algorithm. It, therefore, is considered as the classical training approach. Next, the optimum configurations of two metaheuristic algorithms, namely cuttlefish optimization algorithm (CFOA) and teaching-learning-based optimization (TLBO) are incorporated to optimally train the MLP. In these two models, the LM is replaced with metaheuristic strategies. Overall, the results demonstrated the high competency of the MLP (correlations above 0.997) in the presence of all three strategies. It was also observed that the TLBO enhances the learning and prediction accuracy of the classical MLP (by nearly 7.7% and 9.2%, respectively), while the CFOA performed weaker than LM. Moreover, a comparison between the efficiency of the used metaheuristic optimizers showed that the TLBO is a more time-effective technique for predicting the PE. Hence, it can serve as a promising approach for indirect PE analysis.

키워드

과제정보

This work was supported by the General Projects of Guangdong Natural Science Research Projects (grant number 2023A1515011520).

참고문헌

  1. Ali Ghorbani, M., Kazempour, R., Chau, K.W., Shamshirband, S. and Taherei Ghazvinei, P. (2018), "Forecasting pan evaporation with an integrated artificial neural network quantum-behaved particle swarm optimization model: a case study in Talesh, Northern Iran", Eng. Applicat. Computat. Fluid Mech., 12(1), 724-737. https://doi.org/10.1080/19942060.2018.1517052 
  2. Allawi, M.F. and El-Shafie, A. (2016), "Utilizing RBF-NN and ANFIS methods for multi-lead ahead prediction model of evaporation from reservoir", Water Resour. Manage., 30(13), 4773-4788. https://doi.org/10.1007/s1126900-016-1452-1 
  3. Almedeij, J. (2012), "Modeling pan evaporation for Kuwait by multiple linear regression", Scientif. World J., 2012. https://doi.org/10.1100/2012/574742 
  4. Anderson, D. and McNeill, G. (1992), "Artificial neural networks technology", Kaman Sci. Corp. 258(6), 1-83. 
  5. Asadi Nalivan, O., Mousavi Tayebi, S.A., Mehrabi, M., Ghasemieh, H. and Scaioni, M. (2022), "A hybrid intelligent model for spatial analysis of groundwater potential around Urmia Lake, Iran", Stoch. Environ. Res. Risk Assess.. 37, 1821-1838. https://doi.org/10.1007/s00477-022-02368-y 
  6. Djaman, K., Koudahe, K. and Ganyo, K.K. (2017), "Trend analysis in annual and monthly pan evaporation and pan coefficient in the context of climate change in togo", J. Geosci. Environ. Protection, 5(12), 41-56. https://doi.org/10.4236/gep.2017.512003 
  7. Eesa, A.S., Brifcani, A.M.A. and Orman, Z. (2013), "Cuttlefish algorithm-a novel bio-inspired optimization algorithm", Int. J. Scientif. Eng. Research 4 (9), 1978-1986. 
  8. Eesa, A.S. and Orman, Z. (2020), "A new clustering method based on the bio-inspired cuttlefish optimization algorithm", Expert Syst., 37(2), e12478. https://doi.org/10.1111/exsy.12478 
  9. Faiz, M.A., Liu, D., Fu, Q., Wrzesinski, D., Baig, F., Nabi, G., Khan, M.I., Li, T. and Cui, S. (2018), "Extreme precipitation and drought monitoring in northeastern China using general circulation models and pan evaporation-based drought indices", Climate Res., 74(3), 231-250. https://doi.org/10.3354/cr01503 
  10. Feng, Y., Jia, Y., Zhang, Q., Gong, D. and Cui, N. (2018), "National-scale assessment of pan evaporation models across different climatic zones of China", J. Hydrol., 564, 314-328. https://doi.org/10.1016/j.jhydrol.2018.07.013 
  11. Giernacki, W., Espinoza Fraire, T. and Kozierski, P. (2017), "Cuttlefish optimization algorithm in autotuning of altitude controller of unmanned aerial vehicle (UAV)", In: Iberian Robotics Conference, pp. 841-852. https://doi.org/10.1007/978-3-319-70833-1_68 
  12. Goyal, M.K., Bharti, B., Quilty, J., Adamowski, J. and Pandey, A. (2014), "Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS", Expert Syst. Applicat., 41(11), 5267-5276. https://doi.org/10.1016/j.eswa.2014.02.047 
  13. Guan, Y., Mohammadi, B., Pham, Q.B., Adarsh, S., Balkhair, K.S., Rahman, K.U., Linh, N.T.T. and Tri, D.Q. (2020), "A novel approach for predicting daily pan evaporation in the coastal regions of Iran using support vector regression coupled with krill herd algorithm model", Theor. Appl. Climatol., 1-19. https://doi.org/10.1007/s00704-020-03283-4 
  14. Guven, A. and Kisi, O. (2011), "Daily pan evaporation modeling using linear genetic programming technique", Irrig. Sci., 29(2), 135-145. https://doi.org/10.1007/s00271-010-0225-5 
  15. Guven, A. and Kisi, O. (2013), "Monthly pan evaporation modeling using linear genetic programming", J. Hydrol., 503, 178-185. https://doi.org/10.1016/j.jhydrol.2013.08.043 
  16. Hakim, S.J.S. and Razak, H.A. (2014), "Modal parameters based structural damage detection using artificial neural networks-a review", Smart Struct. Syst., Int. J., 14(2), 159-189. https://doi.org/10.12989/sss.2014.14.2.159 
  17. Hornik, K., Stinchcombe, M. and White, H. (1989), "Multilayer feedforward networks are universal approximators", Neural Networks, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8 
  18. Kerem, A. and Saygin, A. (2019), "Scenario-based wind speed estimation using a new hybrid metaheuristic model: Particle swarm optimization and radial movement optimization", Measur. Control, 52(5-6), 493-508. https://doi.org/10.1177/0020294019842597 
  19. Keshtegar, B. and Kisi, O. (2017), "Modified response-surface method: new approach for modeling pan evaporation", J. Hydrol. Eng., 22(10), 04017045. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001541 
  20. Keshtegar, B., Piri, J. and Kisi, O. (2016), "A nonlinear mathematical modeling of daily pan evaporation based on conjugate gradient method", Comput. Electron. Agricul., 127, 120-130. https://doi.org/10.1016/j.compag.2016.05.018 
  21. Kisi, O. (2009), "Daily pan evaporation modelling using multi-layer perceptrons and radial basis neural networks", Hydrol. Processes: Int. J., 23(2), 213-223. https://doi.org/10.1002/hyp.7126 
  22. Kisi, O., Mansouri, I. and Hu, J.W. (2017), "A new method for evaporation modeling: dynamic evolving neural-fuzzy inference system", Adv. Meteorol., 2017. https://doi.org/10.1155/2017/5356324 
  23. Lin, G.F., Lin, H.Y. and Wu, M.C. (2013), "Development of a support-vector-machine-based model for daily pan evaporation estimation", Hydrol. Processes, 27(22), 3115-3127. https://doi.org/10.1002/hyp.9428 
  24. Liu, B., Xu, M., Henderson, M. and Gong, W. (2004), "A spatial analysis of pan evaporation trends in China, 1955-2000", J. Geophys. Res.: Atmospheres, 109(D15). https://doi.org/10.1029/2004JD004511 
  25. Lu, X., Ju, Y., Wu, L., Fan, J., Zhang, F. and Li, Z. (2018), "Daily pan evaporation modeling from local and cross-station data using three tree-based machine learning models", J. Hydrol., 566, 668-684. https://doi.org/10.1016/j.jhydrol.2018.09.055 
  26. Malik, A., Kumar, A. and Kisi, O. (2018), "Daily pan evaporation estimation using heuristic methods with gamma test", J. Irrig. Drain. Eng., 144(9), 04018023. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001336 
  27. Malik, A., Rai, P., Heddam, S., Kisi, O., Sharafati, A., Salih, S.Q., Al-Ansari, N. and Yaseen, Z.M. (2020), "Pan evaporation estimation in Uttarakhand and Uttar Pradesh States, India: validity of an integrative data intelligence model", Atmosph., 11(6), 553. https://doi.org/10.3390/atmos11060553 
  28. Mehrabi, M. (2021), "Landslide susceptibility zonation using statistical and machine learning approaches in Northern Lecco, Italy", Natural Hazards, 1-37. https://doi.org/10.1007/s11069-021-05083-z 
  29. Mehrabi, M. and Moayedi, H. (2021), "Landslide susceptibility mapping using artificial neural network tuned by metaheuristic algorithms", Environ. Earth Sci., 80(24), 1-20. https://doi.org/10.1007/s12665-021-10098-7 
  30. Mehrabi, M., Pradhan, B., Moayedi, H. and Alamri, A. (2020), "Optimizing an adaptive neuro-fuzzy inference system for spatial prediction of landslide susceptibility using four state-of-the-art metaheuristic techniques", Sensors, 20(6), 1723. https://doi.org/10.3390/s20061723 
  31. Moayedi, H., Mehrabi, M., Mosallanezhad, M., Rashid, A.S.A. and Pradhan, B. (2019), "Modification of landslide susceptibility mapping using optimized PSO-ANN technique", Eng. Comput., 35(3), 967-984. https://doi.org/10.1007/s00366-018-0644-0 
  32. Moayedi, H., Mehrabi, M., Bui, D.T., Pradhan, B. and Foong, L.K. (2020), "Fuzzy-metaheuristic ensembles for spatial assessment of forest fire susceptibility", J. Environ. Manag., 260, 109867. https://doi.org/10.1016/j.jenvman.2019.109867 
  33. Moayedi, H., Ghareh, S. and Foong, L.K. (2021), "Quick integrative optimizers for minimizing the error of neural computing in pan evaporation modeling", Eng. Comput., 38, 1331-1347. https://doi.org/10.1007/s00366-020-01277-4 
  34. Moazenzadeh, R., Mohammadi, B., Shamshirband, S. and Chau, K.W. (2018), "Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran", Eng, Applicat. Computat. Fluid Mech., 12(1), 584-597. https://doi.org/10.1080/19942060.2018.1482476 
  35. Mohammadrezapour, O., Piri, J. and Kisi, O. (2019), "Comparison of SVM, ANFIS and GEP in modeling monthly potential evapotranspiration in an arid region (Case study: Sistan and Baluchestan Province, Iran)", Water Supply, 19(2), 392-403. https://doi.org/10.2166/ws.2018.084 
  36. More, J.J. (1978), Numerical Analysis, Springer, pp. 105-116.
  37. Muhammad, M.K.I., Nashwan, M.S., Shahid, S., Ismail, T.B., Song, Y.H. and Chung, E.S. (2019), "Evaluation of empirical reference evapotranspiration models using compromise programming: a case study of Peninsular Malaysia", Sustainability, 11(16), 4267. https://doi.org/10.3390/su11164267 
  38. Nehdi, M. and Greenough, T. (2007), "Modeling shear capacity of RC slender beams without stirrups using genetic algorithms", Smart Struct. Syst., Int. J., 3(1), 51-68. https://doi.org/10.12989/sss.2007.3.1.051 
  39. Nguyen, H., Mehrabi, M., Kalantar, B., Moayedi, H. and Abdullahi, M.A.M. (2019), "Potential of hybrid evolutionary approaches for assessment of geo-hazard landslide susceptibility mapping", Geomat. Natural Hazards Risk, 10(1), 1667-1693. https://doi.org/10.1080/19475705.2019.1607782 
  40. Pinkus, A. (1999), "Approximation theory of the MLP model in neural networks", Acta numerica, 8, 143-195. https://doi.org/10.1017/S0962492900002919 
  41. Qasem, S.N., Samadianfard, S., Kheshtgar, S., Jarhan, S., Kisi, O., Shamshirband, S. and Chau, K.W. (2019), "Modeling monthly pan evaporation using wavelet support vector regression and wavelet artificial neural networks in arid and humid climates", Eng. Applicat. Computati. Fluid Mech., 13(1), 177-187. https://doi.org/10.1080/19942060.2018.1564702 
  42. Rao, R.V., Savsani, V.J. and Vakharia, D.P. (2011), "Teaching-learning-based optimization: a novel method for constrained mechanical design optimization problems", Comput.-Aided Des., 43(3), 303-315. https://doi.org/10.1016/j.cad.2010.12.015 
  43. Riffi, M.E. and Bouzidi, M. (2015), "Discrete cuttlefish optimization algorithm to solve the travelling salesman problem", Proceedings of 2015 3rd World Conference on Complex Systems (WCCS), pp. 1-6. https://doi.org/10.1109/ICoCS.2015.7483231 
  44. Roushangar, K. and Shahnazi, S. (2019), "Bed load prediction in gravel-bed rivers using wavelet kernel extreme learning machine and meta-heuristic methods", Int. J. Environ. Sci. Technol., 16(12), 8197-8208. https://doi.org/10.1007/s13762-019-02287-6 
  45. Salih, S.Q., Allawi, M.F., Yousif, A.A., Armanuos, A.M., Saggi, M.K., Ali, M., Shahid, S., Al-Ansari, N., Yaseen, Z.M. and Chau, K.W. (2019), "Viability of the advanced adaptive neuro-fuzzy inference system model on reservoir evaporation process simulation: case study of Nasser Lake in Egypt", Eng. Applicat. Computat. Fluid Mech., 13(1), 878-891. https://doi.org/10.1080/19942060.2019.1647879 
  46. Sanikhani, H., Kisi, O., Nikpour, M.R. and Dinpashoh, Y. (2012), "Estimation of daily pan evaporation using two different adaptive neuro-fuzzy computing techniques", Water Resour. Manag., 26(15), 4347-4365. https://doi.org/10.1007/s11269-012-0148-4 
  47. Sayari, S., Mahdavi-Meymand, A. and Zounemat-Kermani, M. (2020), "Prediction of critical velocity in pipeline flow of slurries using TLBO algorithm: a comprehensive study", J. Pipeline Syst. Eng. Practice, 11(2), 04019057. https://doi.org/10.1061/(ASCE)PS.1949-1204.0000439 
  48. Shimi, M., Najjarchi, M., Khalili, K., Hezavei, E. and Mirhoseyni, S.M. (2020), "Investigation of the accuracy of linear and nonlinear time series models in modeling and forecasting of pan evaporation in IRAN", Arab. J. Geosci., 13(2), 59. https://doi.org/10.1007/s12517-019-5031-7 
  49. Termeh, S.V.R., Kornejady, A., Pourghasemi, H.R. and Keesstra, S. (2018), "Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms", Sci. Total Environ., 615, 438-451. https://doi.org/10.1016/j.scitotenv.2017.09.262 
  50. Tikhamarine, Y., Malik, A., Kumar, A., Souag-Gamane, D. and Kisi, O. (2019), "Estimation of monthly reference evapotranspiration using novel hybrid machine learning approaches", Hydrol. Sci. J., 64(15), 1824-1842. https://doi.org/10.1080/02626667.2019.1678750 
  51. Xu, C.Y., Gong, L., Jiang, T., Chen, D. and Singh, V.P. (2006), "Analysis of spatial distribution and temporal trend of reference evapotranspiration and pan evaporation in Changjiang (Yangtze River) catchment", J. Hydrol., 327(1-2), 81-93. https://doi.org/10.1016/j.jhydrol.2005.11.029 
  52. Yaseen, Z.M., Ehteram, M., Sharafati, A., Shahid, S., Al-Ansari, N. and El-Shafie, A. (2018), "The integration of nature-inspired algorithms with least square support vector regression models: application to modeling river dissolved oxygen concentration", Water, 10(9), 1124. https://doi.org/10.3390/w10091124 
  53. Yaseen, Z.M., Faris, H. and Al-Ansari, N. (2020), "Hybridized extreme learning machine model with salp swarm algorithm: a novel predictive model for hydrological application", Complexity, 2020. https://doi.org/10.1155/2020/8206245 
  54. Ye, X., Moayedi, H., Khari, M. and Foong, L.K. (2020), "Metaheuristic-hybridized multilayer perceptron in slope stability analysis", Smart Struct. Syst., Int. J., 26(3), 263-275. https://doi.org/10.12989/sss.2020.26.3.263 
  55. Zeinolabedini Rezaabad, M., Ghazanfari, S. and Salajegheh, M. (2020), "ANFIS modeling with ICA, BBO, TLBO, and IWO optimization algorithms and sensitivity analysis for predicting daily reference evapotranspiration", J. Hydrol. Eng., 25(8), 04020038. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001963 
  56. Zhang, Y., Jin, Z. and Chen, Y. (2020), "Hybrid teaching-learning-based optimization and neural network algorithm for engineering design optimization problems", Knowledge-Based Syst., 187, 104836. https://doi.org/10.1016/j.knosys.2019.07.007 
  57. Zhang, Y., Liu, L., Zhu, Y., Wang, P. and Foong, L.K. (2022), "Novel integrative soft computing for daily pan evaporation modeling", Smart Struct. Syst., Int. J., 30(4), 421-432. https://doi.org/10.12989/sss.2022.30.4.421 
  58. Zhou, G., Moayedi, H. and Foong, L.K. (2020), "Teaching-learning-based metaheuristic scheme for modifying neural computing in appraising energy performance of building", Eng. Comput., 37, 3037-3048. https://doi.org/10.1007/s00366-020-00981-5