Comparison of multi-gene genetic programming and dynamic evolving neural-fuzzy inference system in modeling pan evaporation

• DOI: 10.2166/nh.2017.076
• Publication Date: 2017-11-15T01:20:08Z
• Authors: Okan Eray; Cihan Mert; Ozgur Kisi
• Keywords: Pan evaporation; Inference system

Abstract Accurately modeling pan evaporation is important in water resources planning and management also environmental engineering. This study compares the accuracy of two new data-driven methods, multi-gene genetic programming (MGGP) approach dynamic evolving neural-fuzzy inference system (DENFIS), monthly evaporation. The climatic data, namely, minimum temperature, maximum solar radiation, relative humidity, wind speed, evaporation, obtained from Antakya Antalya stations, Mediterranean Region Turkey were utilized study. MGGP DENFIS methods compared with (GP) calibrated version Hargreaves Samani (CHS) empirical method. For station, GP had slightly better than models all performed superior to CHS while provided performance other at station. effect periodicity input models' was investigated it found that adding significantly increased models.