Abstract: Techniques are described for automated operations to determine tree inventory information for an area of land using visual data of overhead image(s), such as by using a trained prediction model specific to an ecological region to which the land area belongs as part of probabilistically determining multiple types of information about trees in that land area, and for subsequently using the determined tree inventory information in one or more manners (e.g., to improve management of trees in that land area). The images may, for example, include spectral satellite images that include at least visible light data for an area of land, and the determined tree inventory information may include information about the trees present on the land area, such as, for example, predictions of particular tree species, quantities of each of the tree species, sizes of the trees, etc.