Comparison of multiple learning artificial intelligence models for estimation of long-term monthly temperatures in Turkey

被引：43
作者：
Citakoglu H. [1 ]
机构：
[1] Civil Engineering Department, Engineering Faculty, Erciyes University, Kayseri
来源：
Arabian Journal of Geosciences | 2021年 / 14卷 / 20期
关键词：
Air temperature; Gaussian process regression; Long short-term memory; Support vector machine regression;
D O I：
10.1007/s12517-021-08484-3
中图分类号：
学科分类号：
摘要：
Performance of four different machine learning–based approaches (long short-term memory (LSTM), support vector machine regression (SVMR), Gaussian process regression (GPR), and multi-gene genetic programming (MGGP) models) in estimation of long-term monthly temperatures was investigated in this study. Data of 250 measuring stations of Turkey were used in present trials. Month numbers of the year, latitude, longitude, and altitude variables were used as input data of the models. Error statistics of mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), coefficient of determination (R2), and Nash−Sutcliffe efficiency coefficient (NSE) were used while comparing the four models. In terms of five error statistics, models yielded similar outcomes. Therefore, Taylor and Violin diagrams were used to assess how close the model-estimated values to measured data. Taylor and Violin diagrams revealed that GPR model had better performance in estimation of maximum and average temperatures than the other three models. Also, it was determined that the measured data estimated by the Kruskal–Wallis test came from the same distribution. At the end of this study, efficiency of the methods recommended for comparisons was proven. © 2021, Saudi Society for Geosciences.
引用
收藏
相关论文
共 66 条
  • [11] Cobaner M., Citakoglu H., Kisi O., Haktanir T., Estimation of mean monthly air temperatures in Turkey, Comput Electron Agric, 109, pp. 71-79, (2014)
  • [12] Cobaner M., Babayigit B., Dogan A., Estimation of groundwater levels with surface observations via genetic programming, J-Am Water Works Assoc, 108, 6, pp. E335-E348, (2016)
  • [13] Dong D., Sheng Z., Yang T., Wind power prediction based on recurrent neural network with long short-term memory units, 2018 International Conference on Renewable Energy and Power Engineering (REPE). IEEE, pp. 34-38, (2018)
  • [14] Gandomi A.H., Alavi A.H., A new multi-gene genetic programming approach to nonlinear system modeling. Part I: materials and structural engineering problems, Neural Comput & Applic, 21, 1, pp. 171-187, (2012)
  • [15] Gandomi A.H., Roke D.A., Assessment of artificial neural network and genetic programming as predictive tools, Adv Eng Softw, 88, pp. 63-72, (2015)
  • [16] Geng D., Zhang H., Wu H., Short-term wind speed prediction based on principal component analysis and LSTM, Appl Sci, 10, 13, (2020)
  • [17] Guan L., Yang J., Bell J.M., Cross-correlation between weather variables in Australia, Build Environ, 42, pp. 1054-1070, (2007)
  • [18] Kiraly A., Janosi I.M., Stochastic modeling of daily temperature fluctuations, Phys Rev E, 65, 5, (2002)
  • [19] Kisi O., Sanikhani H., Prediction of long-term monthly precipitation using several soft computing methods without climatic data, Int J Climatol, 35, 14, pp. 4139-4150, (2015)
  • [20] Kisi O., Shiri J., Prediction of long-term monthly air temperature using geographical inputs, Int J Climatol, 34, 1, pp. 179-186, (2014)
1234567