Real-time prediction of daily reference crop evapotranspiration (ET0) is the basis for estimating crop evapotranspiration and for computing crop irrigation requirements. In recent years, least-squares support vector machines (LSSVMs) have been applied for forecasting in many fields of engineering. In this paper, LSSVMs are applied to forecast ET0 using public weather forecasting data (minimum and maximum temperature, average relative humidity, wind scale and weather conditions). LSSVM-estimated ET0 is compared with Penman–Monteith (PM)-estimated ET0 using measured meteorological data. Based on a comparison between LSSVM and PM over a 2 month period, the results show that the root mean square error and mean absolute error are less than 0.5 and 0.4 mm d−1, respectively, and that the model efficiency is greater than 90%. This indicates that ET0 can be successfully estimated using public weather forecasts through the LSSVM approach.
Skip Nav Destination
Article navigation
Research Article|
August 01 2011
Prediction of daily crop reference evapotranspiration (ET0) values through a least-squares support vector machine model
Xianghong Guo;
Xianghong Guo
1College of Water Resource Science and Engineering, Taiyuan University of Technology, Taiyuan 030024, China
Search for other works by this author on:
Xihuan Sun;
1College of Water Resource Science and Engineering, Taiyuan University of Technology, Taiyuan 030024, China
E-mail: [email protected]
Search for other works by this author on:
Juanjuan Ma
Juanjuan Ma
1College of Water Resource Science and Engineering, Taiyuan University of Technology, Taiyuan 030024, China
Search for other works by this author on:
Hydrology Research (2011) 42 (4): 268–274.
Article history
Received:
June 30 2009
Accepted:
July 07 2010
Citation
Xianghong Guo, Xihuan Sun, Juanjuan Ma; Prediction of daily crop reference evapotranspiration (ET0) values through a least-squares support vector machine model. Hydrology Research 1 August 2011; 42 (4): 268–274. doi: https://doi.org/10.2166/nh.2011.072
Download citation file: