One of the long-term goals of Digital Transformation in agriculture and forestry is for autonomous agents to be able to perform tasks that are currently done by human workers. For reasons of increasing safety, precision and resources, autonomous robots could efficiently navigate into the forests or fields, gathering different types of data (images, 3D point clouds, tabular, and time-series). Training fast AI models with that data, with low power costs and high performance is a prerequisite for navigation, decision-making, and action. In the past, 3D point clouds have already been used for the creation of digital twins, tree classification, segmentation and forest biomass estimation. This research work tackles the problem of efficiently recognizing tree markings, which consist of a symbolic language of forest workers that need to be recognized and understood by autonomous robots if they are to undertake the tasks that are currently performed by humans. Explainable AI methods offer the necessary information for the underlying reasons for efficient tree marking recognition and actionable insights for further adaptations of the data processing, AI models and xAI methods pipeline.