Prediction of evaporation in arid and semi-arid regions: a comparative study using different machine learning models

被引:81
作者
Yaseen, Zaher Mundher [1 ]
Al-Juboori, Anas Mahmood [2 ]
Beyaztas, Ufuk [3 ]
Al-Ansari, Nadhir [4 ]
Chau, Kwok-Wing [5 ]
Qi, Chongchong [6 ]
Ali, Mumtaz [7 ]
Salih, Sinan Q. [8 ]
Shahid, Shamsuddin [1 ]
机构
[1] Univ Teknol Malaysia, Fac Engn, Sch Civil Engn, Skudai 81310, Johor Bahru, Malaysia
[2] Univ Mosul, Dams & Water Resources Res Ctr, Mosul, Iraq
[3] Bartin Univ, Dept Stat, TR-74100 Bartin, Turkey
[4] Lulea Univ Technol, Civil Environm & Nat Resources Engn, S-97187 Lulea, Sweden
[5] Hong Kong Polytech Univ, Dept Civil & Environm Engn, Kowloon, Hung Hom, Hong Kong, Peoples R China
[6] Cent South Univ, Sch Resources & Safety Engn, Changsha 410083, Hunan, Peoples R China
[7] Deakin Univ, Sch Informat Technol, Deakin SWU Joint Res Ctr Big Data, Geelong, Vic 3125, Australia
[8] Duy Tan Univ, Inst Res & Dev, Da Nang 550000, Vietnam
关键词
evaporation; predictive model; machine learning; arid and semi-arid regions; best input combination; SUPPORT VECTOR REGRESSION; WATER; SOIL; IMPLEMENTATION; INTELLIGENCE; COEFFICIENT; SIMULATION; INDEX; AREA;
D O I
10.1080/19942060.2019.1680576
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Evaporation, one of the fundamental components of the hydrology cycle, is differently influenced by various meteorological variables in different climatic regions. The accurate prediction of evaporation is essential for multiple water resources engineering applications, particularly in developing countries like Iraq where the meteorological stations are not sustained and operated appropriately for in situ estimations. This is where advanced methodologies such as machine learning (ML) models can make valuable contributions. In this research, evaporation is predicted at two different meteorological stations located in arid and semi-arid regions of Iraq. Four different ML models for the prediction of evaporation - the classification and regression tree (CART), the cascade correlation neural network (CCNNs), gene expression programming (GEP), and the support vector machine (SVM) - were developed and constructed using various input combinations of meteorological variables. The results reveal that the best predictions are achieved by incorporating sunshine hours, wind speed, relative humidity, rainfall, and the minimum, mean, and maximum temperatures. The SVM was found to show the best performance with wind speed, rainfall, and relative humidity as inputs at Station I (R-2 = .92), and with all variables as inputs at Station II (R-2 = .97). All the ML models performed well in predicting evaporation at the investigated locations.
引用
收藏
页码:70 / 89
页数:20
相关论文
共 47 条
  • [1] Abbas N., 2018, J ENV HYDROLOGY, V26, P1
  • [2] Extreme Learning Machines: A new approach for prediction of reference evapotranspiration
    Abdullah, Shafika Sultan
    Malek, M. A.
    Abdullah, Namiq Sultan
    Kisi, Ozgur
    Yap, Keem Siah
    [J]. JOURNAL OF HYDROLOGY, 2015, 527 : 184 - 195
  • [3] Prediction of Daily Pan Evaporation using Wavelet Neural Networks
    Abghari, Hirad
    Ahmadi, Hojjat
    Besharat, Sina
    Rezaverdinejad, Vahid
    [J]. WATER RESOURCES MANAGEMENT, 2012, 26 (12) : 3639 - 3652
  • [4] Al-Ansari N., 2014, Journal of Water Resource and Protection, V6, P1066, DOI 10.4236/jwarp.2014.612102
  • [5] Al-Taai O T., 2018, Al-Mustansiriyah Journal of Science, V29, P7
  • [6] SVR-based prediction of evaporation combined with chaotic approach
    Baydaroglu, Ozlem
    Kocak, Kaslm
    [J]. JOURNAL OF HYDROLOGY, 2014, 508 : 356 - 363
  • [7] Pham BT, 2018, SUSTAIN DEV GOAL SER, P159, DOI 10.1007/978-3-319-56469-2_11
  • [8] A LINEAR-REGRESSION MODEL COMBINED WITH A SOIL-WATER BALANCE MODEL TO DESIGN MICRO-CATCHMENTS FOR WATER HARVESTING IN ARID ZONES
    BOERS, TM
    DEGRAAF, M
    FEDDES, RA
    BENASHER, J
    [J]. AGRICULTURAL WATER MANAGEMENT, 1986, 11 (3-4) : 187 - 206
  • [9] Breiman L., 1984, The Wadsworth statisticsprobability series, V19, DOI DOI 10.1371/JOURNAL.PONE.0015807
  • [10] Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature
    Chai, T.
    Draxler, R. R.
    [J]. GEOSCIENTIFIC MODEL DEVELOPMENT, 2014, 7 (03) : 1247 - 1250