摘要：Reference evapotranspiration (ET o ) is an agrometeorological variable widely used in hydrology and agriculture. The FAO-56 Penman-Monteith combination method (PM method) is a standard for computing ET o for water management. However, this scheme is limited to areas where climatic data with good quality are available. Maps of 10-day averaged ET o at 5 km × 5 km grid spacing for the Taiwan region were produced by multiplying pan evaporation (E pan ), derived from ground solar radiation (GSR) retrieved from satellite images using the Heliosat-3 method, by a fixed pan coefficient (K p ). Validation results indicated that the overall mean absolute percentage error (MAPE) and normalized root-mean-square deviation (NRMSD) were 6.2 and 7.7%, respectively, when compared with ET o computed by the PM method using spatially interpolated 10-day averaged daily maximum and minimum temperature datasets and GSR derived from satellite inputs. Land coefficient (K L ) values based on the derived ET o estimates and long term latent heat flux measurements, were determined for the following landscapes: Paddy rice ( Oryza sativa ), subtropical cypress forest ( Chamaecyparis obtusa var. formosana and Chamaecyparis formosensis ), warm-to-temperate mixed rainforest ( Cryptocarya chinensis , Engelhardtia roxburghiana , Tutcheria shinkoensis , and Helicia formosana ), and grass marsh ( Brachiaria mutica and Phragmites australis ). The determined land coefficients are indispensable to scale ET o in estimating regional evapotranspiration.
