The field of plant identification is moving towards leveraging AI and machine learning to improve the efficiency of ecological studies. The integration of automated identification systems can help extend the scope and coverage of these studies, particularly in data-deficient regions such as tropical countries. Recent developments have focused on cross-domain classification tasks, where training sets consist of herbarium collections and photos, to learn a correspondence between the two domains. This approach has shown promise in improving the identification of flora in regions with limited data. Noteworthy papers include: Overview of PlantCLEF 2024, which provides a detailed description of a new test set and evaluation methodology for multi-species plant identification in vegetation plot images. Overview of PlantCLEF 2021, which assesses the extent to which automated identification of flora in data-poor regions can be improved by using herbarium collections.