Comparative evaluation of daily evapotranspiration using artificial neural network and variable infiltration capacity models
- Publication Type:
- Journal Article
- Citation:
- Agricultural Engineering International: CIGR Journal, 2018, 20, (1), pp. 32-39
- Issue Date:
- 2018-01-01
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| 34_CIGR_2018.pdf | Published version | 495.45 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Evapotranspiration is a key variable for hydrologic, climatic and agricultural studies. Accurate quantification of this variable is the most important for irrigation management and crop productivity. With the availability of only meteorological data in climatic stations, reference gross evapotranspiration (ETo) estimation is becoming a challenging task. Hence, there is a scope to estimate the ETo using various physical and empirical methods. Among physical methods, FAO-56 Penman Monteith (PM) method is the best and Artificial Neural Network (ANN) model is an accurate empirical method. Further, ETo can also be estimated using a water budget approach i.e. variable infiltration capacity (VIC) model, which accounts for the sub-grid variability of land use, land cover and soil moisture accurately. In this study, the ETo was estimated by two different methods, namely, VIC and ANN for Mohanpur climatic location in India. The results of VIC-ETo showed the correlation coefficient, r = 0.853, coefficient of determination, R2 = 0.727 and index of agreement, d = 0.924; while ANN models with the FAO-56 PM method were in better agreement with r = 0.999, R2 = 0.998 and d = 0.999. Hence, it is concluded that the ANN showed better results as compared to VIC model for ETo estimation in Mohanpur climatic location.
Please use this identifier to cite or link to this item: