In the semi-arid areas of Petrolina municipality, Northeast Brazil, irrigated agriculture has replaced the natural vegetation, being important the quantification of the energy exchanges between the plants and the low atmosphere. MODIS satellite images and agro-meteorological data for the years of 2010 and 2011 were used together, for modelling the energy balance components under these conditions. Surface albedo (α0), NDVI and surface temperature (T0) were the remote sensing parameters necessary to calculate the latent heat flux (λE) and the surface resistance to evapotranspiration (rs) on a large scale. The daily net radiation (Rn) was retrieved from α0, air temperature (Ta) and transmissivity (τsw), allowing the quantification of the sensible heat flux (H) by residual in the energy balance. With threshold values for rs, it was possible to do a simplified vegetation classification. The incident solar radiation (RS↓) partitioned as Rn ranged from 0.40 to 0.51, corresponding respectively to periods after the rainy season and the driest conditions of the year, with the differences between irrigated crops and natural ecosystem not significant. Considering all periods along the year the averaged fractions of Rn partitioned as H, were 31 and 78%, for irrigated crops and natural vegetation, respectively, while as λE the corresponding ratios were 69 and 22%. It was observed heat advection from the dry areas to irrigated plots, with λE exceeding Rn by 9% during the coldest periods. The models tested here can be used for monitoring the energy exchanges in agro-ecosystems under conditions of land use and climate changes.