Contents lists available at ScienceDirect Computers and Electronics in Agriculture journal homepage: www.elsevier.com/locate/compag Meteorological data mining and hybrid data-intelligence models for reference evaporation simulation: A case study in Iraq Khabat Khosravi a , Prasad Daggupati a , Mohammad Taghi Alami b , Salih Muhammad Awadh c , Mazen Ismaeel Ghareb d , Mehdi Panahi i,j , Binh Thai Pham f, ⁎ , Fatemeh Rezaie e , Chongchong Qi g , Zaher Mundher Yaseen h, ⁎ a School of Engineering, University of Guelph, Guelph, Canada b Department of Civil Engineering, University of Tabriz, Tabriz, Iran c Department of Geology, College of Science, University of Baghdad, Baghdad, Iraq d Department of Computer Science, College of Science and Technology, University of Human Development, Sulaymaniyah, Kurdistan Region, Iraq e Department of Geophysics, Young Researchers and Elites Club, North Tehran Branch, Islamic Azad University, Tehran, Iran f Institute of Research and Development, Duy Tan University, Da Nang 550000, Viet Nam g School of Resources and Safety Engineering, Central South University, Changsha 410083, Hunan Province, PR China h Sustainable Developments in Civil Engineering Research Group, Faculty of Civil Engineering, Ton Duc Thang University, Ho Chi Minh City, Viet Nam i Division of Science Education, Kangwon National University, Chuncheon-si, Gangwon-do 24341, Republic of Korea j Geoscience Platform Research Division, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124, Gwahak-ro Yuseong-gu, Daejeon 34132, Republic of Korea ARTICLE INFO Keywords: Evaporation rate prediction Data mining Bio-inspired ANFIS model Arid and semi-arid climatic Iraq region ABSTRACT To model an agriculture process for any region, it is significantly essential to accurately simulate the reference evaporation (ET o ) from the available regional meteorological parameters. Nine models, including five data mining algorithms and four adaptive neuro-fuzzy inference systems (ANFISs), were tested for their ability to predict ET o at meteorological stations in Baghdad and Mosul (Iraq). Various weather parameters (e.g., wind speed, sunshine hours, rainfall, maximum and minimum temperature and relative humidity) were recorded and employed as explanatory variables in the models. Pearson correlation analysis showed ET o to have the closest correlation with sunshine hours, maximum and minimum temperatures, and relative humidity. The modeling performance was assessed using the statistical measures of coefficient of determination (R 2 ), root mean square error (RMSE), mean absolute error (MAE), Nash-Sutcliffeefficiency (NSE), percentage of bias (PBIAS), and the ratio of RMSE to the standard deviation of observations (RSR). Investigations on the modeling accuracy with different input parameter combinations showed that, despite the different structures of the models, no single input combination showed a consistent modeling outcome. Fewer variables were necessary to achieve the same high predictive power for the models developed for the Baghdad station than for those developed for the Mosul station. For both stations, the ANFIS-GA model generally showed the greatest predictive power whereas the random tree algorithm showed the poorest. Moreover, hybrid models showed a higher predictive power than the individual models. 1. Introduction As a key process in the hydrologic cycle, evaporation affects water resources planning and operations (Priestley and Taylor, 1972). Ac- cordingly, it is critical to be able to predict its magnitude and pattern (Qasem et al., 2019), particularly for arid and semi-arid environments such as those found in Iraq (Sayl et al., 2016). Owing to the substantial volume of water that evaporates from reservoirs, natural lakes, and river basins on a yearly basis (often with important cost implications), it becomes essential to consider the rate of water evaporation from these sources when designing and operating dams. The association of water evaporation rate with climatic changes heightens its impact on the surface water balance (Sartori, 2000). Recent climatic models have pointed towards global warming increasing the rate of evaporative losses from water bodies over time, thereby being of increasing im- portance to water resources management as time goes on (Eames et al., 1997). In low rainfall regions, large volumes of water can be lost through https://doi.org/10.1016/j.compag.2019.105041 Received 6 July 2019; Received in revised form 2 October 2019; Accepted 3 October 2019 ⁎ Corresponding authors. E-mail addresses: phamthaibinh2@duytan.edu.vn (B.T. Pham), yaseen@tdtu.edu.vn (Z.M. Yaseen). Computers and Electronics in Agriculture 167 (2019) 105041 0168-1699/ © 2019 Elsevier B.V. All rights reserved. T