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

ÇITAKOĞLU H., Coskun O.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, cilt.29, sa.50, ss.75487-75511, 2022 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29 Sayı: 50
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s11356-022-21083-3
  • Dergi Adı: ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
  • Derginin Tarandığı İndeksler: 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
  • Sayfa Sayıları: ss.75487-75511
  • Anahtar Kelimeler: Meteorological drought, SPI, Machine learning, Hybrid models, Sakarya, Turkey, ARTIFICIAL-INTELLIGENCE TECHNIQUES, EMPIRICAL MODE DECOMPOSITION
  • Erciyes Üniversitesi Adresli: Evet

Özet

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, R-2 = 0.9367) for 1-month time scale, hybrid VMD-GPR model (NSE = 0.9528, OI = 0.9559, R-2 = 0.9565) for 3-month time scale, and hybrid DWT-ANN model (NSE = 0.9398, OI = 0.9483, R-2 = 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.