Analyzing the impact of area of interest (AOI) size and endmember selection on evapotranspiration (ET) estimation through a contextual model (SEBAL)

Accurate estimation of evapotranspiration (ET) is essential for effective water resource management, particularly in arid and semi-arid areas. Advancements in remote sensing technology have made ET models indispensable, offering high-resolution spatial and temporal assessments. Contextual models such as the Surface Energy Balance Algorithm for Land (SEBAL) are particularly valuable for ET estimation. However, one major challenge for these models is the identification of endmembers representing the wet and dry extremes within the AOI. Furthermore, the influence of AOI size on endmember selection raises important considerations for model performance. This work examines how the size of the AOI and endmember selection impact heat flux estimation using the SEBAL model. The research was conducted in an olive orchard at the Agdal site in Marrakech, from May 2022 to April 2023, and at a rainfed wheat field at the Sidi Rehal site from August 2017 to March 2019, using Landsat imagery (L8 and L9) and ERA5 land reanalysis data. For that, SEBAL was applied to six different AOI, ranging from small and homogeneous areas to the full extent of the Landsat imagery. Based on comparisons of SEBAL estimates with eddy covariance data collected from the Agdal site, the analysis shows that difficulties in accurately identifying endmembers are influenced by the size of the AOI. For homogeneous areas, the model struggles to capture the full range of heat fluxes, leading to poor regression relationships. Conversely, applying a shapefile that covers the entire Landsat imagery led to a more uniform distribution of latent heat flux, especially in winter/spring (when the climatic demand is low), which reduced the model’s ability to capture spatial variability. The AOI, which includes a mix of agricultural areas, bare soil, water bodies, and small towns, and whose boundary is relatively close to the measurement station, yielded the best results. It achieved R2 values of 0.95 for H and 0.88 for LE, with RMSE values of 51.24 and 52.41 W/m² for H and LE, respectively. At the regional scale, the larger AOI size produced the lowest results with greater dispersion at the rainfed wheat site, with RMSE values of 104.99 and 93.30 W/m² for H and LE, respectively. In contrast, segmenting the region into optimal size of AOI produced more accurate results, achieving R2 values of 0.96 for H and 0.92 for LE, with corresponding RMSE values of 56.9 and 35.88 W/m², respectively. These findings emphasize the critical role of AOI size and endmember identification in improving SEBAL model accuracy and enhancing ET estimation for the sustainable management of water resources at both local and regional levels.