Ameneh Miananadi; a a; Hossein Sanaeinejad; b gh; kamran davary
Abstract
The SEBAL algorithm is used to estimate spatial distribution of actual evapotranspiration using remote sensing imageries of MODIS or Landsat. Despite having a better spatial resolution than MODIS imageries (30 m instead of 1000 m), Landsat imageries do not have an appropriate temporal resolution (every ...
Read More
The SEBAL algorithm is used to estimate spatial distribution of actual evapotranspiration using remote sensing imageries of MODIS or Landsat. Despite having a better spatial resolution than MODIS imageries (30 m instead of 1000 m), Landsat imageries do not have an appropriate temporal resolution (every 16 days instead of daily). On the other hand, the daily imageries of MODIS can be difficult to use under cloudy condition. Additionally, it is also a time-consuming process to interpret all the imageries. In this research, we chose the appropriate imageries from MODIS to be able to monitor the sudden weather changes as well as rainfall events and to reduce the interpretation time, while keeping the important information of the daily MODIS imageries in order to obtain the better actual evapotranspiration estimates. Due to the importance of hot and cold pixel selection, whose selection needs time and proficiency, we applied the automated method of hot and cold pixel selection (without user-intervention) using Landsat imageries. To integrate evapotranspiration over time, we used linear-logarithmic interpolation method in addition to linear interpolation method. The estimated actual evapotranspiration by SEBAL was compared to the estimated actual evapotranspiration from water balance equation and SWAT model for 3 years including a wet year (2004-2005), a normal year (2005-2006) and a dry year (2007-2008) in the Neishaboor-Rokh watershed. Furthermore, we used the Budyko framework to validate the evapotranspiration estimated by SEBAL and SWAT. The results showed that in comparison to SWAT, the linear-logarithmic interpolation method performed better than the linear method to estimate evapotranspiration. For linear-logarithmic method, RMSE, MBE, and MAE were 20.4, 0.09, and 18.4 mm year-1, respectively; and for the linear method, they were 21.8, -2.4, and 20.8 mm year-1, respectively. The results also demonstrated that the SEBAL algorithm with automated cold and hot pixel selection is able to have a good estimate of actual evapotranspiration at annual time scale and watershed scale. But, the algorithm does not perform well at HRUs and monthly scale in comparison to SWAT model. Results showed that by taking irrigation into account, evaporation estimated by SEBAL and SWAT follows the Budyko framework.