Predicting Standardized Streamflow index for hydrological drought using machine learning models

Shahabbodin Shamshirband, Sajjad Hashemi, Hana Salimi, Saeed Samadianfard, Esmaeil Asadi, Sadra Shadkani, Katayoun Kargar, Amir Mosavi, Narjes Nabipour, Kwok Wing Chau

Research output: Journal article publicationJournal articleAcademic researchpeer-review

112 Citations (Scopus)


Hydrological droughts are characterized based on their duration, severity, and magnitude. Among the most critical factors, precipitation, evapotranspiration, and runoff  are essential in modeling the droughts. In this study, three indices of drought, i.e., Standardized Precipitation Index (SPI), Standardized Streamflow Index (SSI), and Standardized Precipitation Evapotranspiration Index (SPEI), are modeled using Support Vector Regression (SVR), Gene Expression Programming (GEP), and M5 model trees (MT). The results indicate that SPI delivered higher accuracy. Moreover, MT model performed better in predicting SSI by a CC of 0.8195 and a RMSE of 0.8186. Abbreviations: ANFIS: adaptive neuro-fuzzy inference system; ANN: artificial neural network; ANN: artificial neural network; BS-SVR: boosted-support Vector Regression; CC: correlation coefficient; ELM: extreme learning machine; GEP: gene Expression Programming; GP: genetic Programming; GPR: Gaussian process regression; KNN: k-nearest neighbor; LSSVM: least squares Support Vector Machine; LSSVR: least support vector regression; MAE: mean absolute error; MARS: multivariate adaptive regression splines; MLP: multilayer perceptron; MLR: multiple linear regression; MT: M5 model tree; P: precipitation; PDSI: palmer drought severity index; PET: potential evapotranspiration; RAE: relative absolute error; RMSE: root mean square error; RVM: relevance vector machine; SAR: sodium absorption index; SDR: standard deviation reduction; SPEI: standardized precipitation evapotranspiration index; SPI: standardized precipitation index; SSI: standardized streamflow index; SVM: support vector machine; SVR: support vector regression; WAANN: Wavelet-ARIMA-ANN; WANFIS: Wavelet-Adaptive Neuro-Fuzzy Inference System; WN: wavelet network.

Original languageEnglish
Pages (from-to)339-350
Number of pages12
JournalEngineering Applications of Computational Fluid Mechanics
Issue number1
Publication statusPublished - 1 Jan 2020


  • Gene expression Programming
  • hydrological drought
  • M5 model tree
  • machine learning models
  • Standardized Streamflow index
  • support vector regression

ASJC Scopus subject areas

  • Computer Science(all)
  • Modelling and Simulation

Cite this