Irrigation Sciences and Engineering

Irrigation Sciences and Engineering

Evaluation of the Performance of CANFIS, MLPNN, MLR and M5 Models in the Simulation of Meteorological Drought Index (Case Study: Kermanshah Synoptic Station)

Document Type : Research Paper

Authors
Hamed Mazandarani zadeh 1
Fariba Khodabakhshi 2
1 Associate Professor, Department of Water Engineering and Sciences, Imam Khomeini International University, Qazvin, Iran.
2 PhD Student, Department of Water Engineering and Sciences, Imam Khomeini International University, Qazvin, Iran.
10.22055/jise.2023.42231.2046
Abstract
Drought is one of the most destructive phenomena in the world, especially in Iran. The timely prediction of drought and its severity can make it easier to take the necessary measures to combat this phenomenon. Different methods have been proposed to predict droughts; however, what matters is which method can make the predictions more accurate. Many researchers have compared the CANFIS model with other models such as neural networks and linear regression Malik and Kumar (2020b); Malik et al(2020a); Malik et al (2019), but it has not been tested against the M5 tree model. In this study, CANFIS, M5, MLPNN and MLR models have been used to predict drought in Kermanshah synoptic station, to enhance the accuracy of drought prediction by using a variety of modeling methods in addition to the influential variables of the SPI index.
Keywords
drought index
drought prediction
fuzzy-neural model
decision tree
Subjects
  • F. Byzedi, M. and Kaki, M., 2016. Monitoring and prediction of drought in western Urmia lake basin rain gage stations by ANFIS model. Iranian Journal of Ecohydrology, 3(2): 205-218. (In Persian) Doi: doi: 10.22059/ije.2016.59661.

 

  • Aytek, A., 2009. Co-active neurofuzzy inference system for evapotranspiration modeling. Soft Computer, 13. pp. 691–700.

 

  • Firat, M. Gungor, M., 2007. River flow estimation using adaptive neuro fuzzy inference system. Mathematics and Computers in Simulation, 75. pp. 87-96. Doi: 10.1016/j.matcom.2006.09.003.

 

  • Haghizadeh, A. Bayat, V. and Arshia A., 2019 Estimation of The Evapotranspiration potential of Kermanshah synoptic stations. Using Genetic Programming, 19(67) pp.29-42.

 

  • Hemachandra, S. and Satyanarayana, R. 2013. Co-Active Neuro-Fuzzy Inference System for prediction of electric load. International Journal of Electrical and Electronics Engineering Research, 3(2), pp. 217-222.

 

  • Jang, J.S., 1993 ANFIS adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man, and Cybernetics. 23(3), pp. 665-685.

 

  • Khorrim M, and Boghroniya A., 2006 Analysis of time series with MINITAB AB14 software, Sokhongostar publications. 151 p (In Persian).

 

  • Komasi, M. Ghobadi Khosro, S. and hashemi, M., 2018. Comparison Genetic Programming model and M5 model tree in Drought Forecasting. Iranian Water Researches Journal, 12(2), pp. 81-90 (In Persian).

 

  • Koohi, S., Azizian, A., and Mazandarani Zadeh, H., 2022. The Effects of Climate Change on Drought Conditions Using Fuzzy Logic under SSP3 and SSP5 scenarios. Iran-Water Resources Research (In Persian).

 

  • Malik A, Kumar A, and Kisi, O., 2017 Monthly pan-evaporation estimation in Indian central Himalayas using different heuristic approaches and climate based models. Computers and Electronics in Agriculture. 143(3), pp. 302–313. Doi: 10.1016/j.compag.2017.11.008.

 

  • Malik A, Kumar A, Salih S.Q, Kim S, Kim N.W. Yaseen, Z.M. and Singh, VP., 2020 Drought index prediction using advanced fuzzy logic model: Regional case study over Kumaon in India. Journal PLoS, 15(5), pp. 256-271. Doi: 1371/journal.pone.0233280.

 

  • Malik A, and Kumar A., 2015. Pan Evaporation Simulation Based on Daily Meteorological Data Using Soft Computing Techniques and Multiple Linear Regression. Water Resources Management, 29(3), pp. 124-139.

 

  • Malik Kumar A, and Singh R.P., 2019 Application of Heuristic Approaches for Prediction of Hydrological Drought Using Multi-scalar Streamflow Drought Index. Water Resource Manage 33(2), pp. 3985–4006.

 

  • Malik and Kumar A., 2020 Meteorological drought prediction using heuristic approaches based on effective drought index: a case study in Uttarakhand. Arabgeo 13(2), pp. 27-39.

 

  • Mashayekhi M, and Zakeri Niri M 2020a. Meteorological, Hydrological and Agricultural Droughts Prediction Using Wavelet Method in Tehran. Iran-Water Resources Research, 16(3), pp.120-132 (In Persian).

 

  • McKee T. Doesken J, and Kleist, D., 1993 the relationship of drought frequency and duration to time scales. Proc. of the 8th Conference on Applied Climatology, American Meteorological Society, Boston, 12(4), pp.179-184.

 

  • Minasny B, and Mcbratney, A.B., 2002. The neuro-m method for fitting neural network parametric pedotransfer Soil Science Society of America Journal, 66(3), pp. 352-361. Doi: 10.2136/sssaj2002.3520.

 

  • Moradi, M. and Rahimikhoob, A., 2013 Estimation of Reference Evapotranspiration Using NOAA Satellite Images and M5 Model Tree for Irrigation Networks - Case Study: Gazvin Irrigation Network. JWSS, 16(62), pp. 123-135 (In Persian).

 

  • Nourani, V. and Molajou A., 2017. Application of a hybrid association rules/decision tree model for drought monitoring. Global and Planetary Change 159(5), pp.37-45. Doi: 10.1016/j.gloplacha.2017.10.008.

 

  • Poursalehi, F. Shahidi, A. and Khashei Siuki, A., 2020. Comparison of Decision Tree M5 and K-Nearest Neighborhood Algorithm Models in the Prediction of Monthly Precipitation (Case Study: Birjand Synoptic Station), Iranian journal of irrigation and drainage, 13(5), pp. 1283-1293. (In Persian).

 

  • Rezaei M, and Memarian, H., 2016 Application of Rainfall Time Series and Climatic Indices for Drought Prediction using Co-Active Neurofuzzy Inference System (Case Study: Birjand, Southern Khorasan). Journal of Arid Biome, 5(2), pp. 51-67(In Persian).

 

  • Sattari, Rezazadeh Joudi, A. and Nahrein F., 2014 Monthly Rainfall Prediction using Artificial Neural Networks and M5 Model Tree (Case study: Station of AHAR). Physical Geography Research Quarterly, 46(2), pp. 247-260. Doi: 10.22059/jphgr.2014.51428 (In Persian).

 

  • Sattari, M.T. Nahrein, F. and Azimi, V., 2013. M5 model trees and neural networks based prediction of daily ETO (case study: Bonab station). Iranian Journal of Irrigation and Drainage 7(1), pp.104-113 (In Persian).

 

  • Sattari, M. Mirabbai Najafabadi, R. and Alimohammadi, M., 2016. Application of M5 Tree Model in Forecasting Drought (Case Study, Maragheh, Iran). Hydro geomorphology, 3(8), pp. 73-92. (In Persian).

 

  • Talebkeikhah, F. Rasam, S. Talebkeikhah, M. Torkashvand, M. Salimi, A. Moraveji, M. K., 2020. Investigation of effective processes parameters on lead (II) adsorption from wastewater by biochar in mild air oxidation pyrolysis process. International Journal of Environmental Analytical Chemistry, 12(1), pp. 1-21. Doi: 10.1080/03067319.2020.1777291.
Irrigation Sciences and Engineering
Volume 47, Issue 1
Spring 2024
Pages 83-98

  • Receive Date 11 November 2022
  • Revise Date 22 June 2023
  • Accept Date 26 June 2023
  • Publish Date 21 May 2024