Comparison of hybrid machine learning methods for the prediction of short-term meteorological droughts of Sakarya Meteorological Station in Turkey


Environmental Science and Pollution Research, vol.29, no.50, pp.75487-75511, 2022 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 29 Issue: 50
  • Publication Date: 2022
  • Doi Number: 10.1007/s11356-022-21083-3
  • Journal Name: Environmental Science and Pollution Research
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, IBZ Online, ABI/INFORM, Aerospace Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), BIOSIS, CAB Abstracts, EMBASE, Environment Index, Geobase, MEDLINE, Pollution Abstracts, Veterinary Science Database, Civil Engineering Abstracts
  • Page Numbers: pp.75487-75511
  • Keywords: Meteorological drought, SPI, Machine learning, Hybrid models, Sakarya, Turkey, ARTIFICIAL-INTELLIGENCE TECHNIQUES, EMPIRICAL MODE DECOMPOSITION
  • Kayseri University Affiliated: No


© 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.Drought is a harmful natural disaster with various negative effects on many aspects of life. In this research, short-term meteorological droughts were predicted with hybrid machine learning models using monthly precipitation data (1960–2020 period) of Sakarya Meteorological Station, located in the northwest of Turkey. Standardized precipitation index (SPI), depending only on precipitation data, was used as the drought index, and 1-, 3-, and 6-month time scales for short-term droughts were considered. In the prediction models, drought index was predicted at t + 1 output variable by using t, t − 1, t − 2, and t − 3 input variables. Artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), Gaussian process regression (GPR), support vector machine regression (SVMR), k-nearest neighbors (KNN) algorithms were employed as stand-alone machine learning methods. Variation mode decomposition (VMD), discrete wavelet transform (DWT), and empirical mode decomposition (EMD) were utilized as pre-processing techniques to create hybrid models. Six different performance criteria were used to assess model performance. The hybrid models used together with the pre-processing techniques were found to be more successful than the stand-alone models. Hybrid VMD-GPR model yielded the best results (NSE = 0.9345, OI = 0.9438, R2 = 0.9367) for 1-month time scale, hybrid VMD-GPR model (NSE = 0.9528, OI = 0.9559, R2 = 0.9565) for 3-month time scale, and hybrid DWT-ANN model (NSE = 0.9398, OI = 0.9483, R2 = 0.9450) for 6-month time scale. Considering the entire performance criteria, it was determined that the decomposition success of VMD was higher than DWT and EMD.