In recent years, Representation Learning (RL), a subdiscipline of artificial intelligence, has proved a useful resource in many research fields for effectively mapping abstract categories into numeric scales. In this study, we explored a novel application of RL to forest ecology, labeled TreeSp2Vec, for developing tree species numeric representations using deep neural networks and data from a National Forest Inventory. Our approach consisted of a supervised species classification of individual trees using as input a set phytocentric and geocentric variables derived from forest inventory data and environmental cartography. Among the tested neural network architectures, a multi-layer perceptron with two hidden layers of 1024 units and an embedding layer of 16 units provided the best apparent and test performances (Matthew’s Correlation Coefficient = 0.89). The developed latent representations (W), or embeddings, were evaluated intrinsically by estimating their correlations with supplementary species descriptors that were not included in the training dataset. The evaluation analysis revealed some significant associations that proved the generality of the embedding model. Some latent dimensions (e.g., W6 and W16) were useful for differentiating species general features, such as conifers vs broad-leaved species, while other dimensions (e.g., W2 and W5) were related to forest ecosystem characteristics such as competition intensity (relative spacing index) and biodiversity (Simpson index). We concluded that the developed embeddings provided accurate and generalizable numeric representations of the considered tree species, which can be used as a ground for further cutting-edge forest modelling approaches and open a new range of artificial intelligence applications in ecology.