Estimating forest transpiration is of great importance for Adaptive Forest Management (AFM) in the scope of climate change prediction. AFM in the Mediterranean region usually generates a mosaic of different canopy covers within the same forest. Several models and methods are available to estimate forest transpiration, but most require a homogeneous forest cover, or an individual calibration/validation process for each cover stand. Hence, a model capable of reproducing accurately the transpiration of the whole canopy-cover mosaic is necessary. In this paper, the use of Artificial Neural Network (ANN) is proposed as a flexible tool for estimating forest transpiration using the forest cover as an input variable. To that end, sap flow, soil water content and other environmental variables were experimentally collected under five Aleppo pine stands of different canopy covers for two years. These sets of inputs were then used for the ANN training. Stand transpiration was accurately estimated using climate data, soil water content and forest cover through the ANN approach (correlation coefficient R = 0.95; Nash-Sutcliffe coefficient E = 0.90; root-meansquare error RMSE = 0.078 mm day -1 ). Finally, the input value for soil water content (when not available) was computed using the process-based model Gotilwa+. Then, this computed soil water content was used as input in the proposed ANN. This combination predicted the forest transpiration with values of R = 0.90, E = 0.63, and RMSE = 0.068 mm day -1 . Artificial Neural Network proved to be a useful and flexible tool to predict the transpiration dynamics of an Aleppo pine stand regardless of the heterogeneity of the forest cover produced by adaptive forest management.