Artificial Intelligence for Tree Risk Prediction

Vegetation management is typically one of a utility’s largest budget items. Presently, identification of high-risk trees near utility lines is labor intensive, time consuming, and costly. In this presentation, Ryan Suttle and Nasko Apostolov share a study that describes a machine-learning approach which trains a novel convolutional neural network (CNN) to automatically classify trees, using only a single photograph and with a high degree of accuracy, into likelihood of failure categories. The CNN’s high degree of accuracy demonstrates the potential of artificial intelligence to automate risk assessment and consequently to reduce costs. Preliminary results are extremely promising for future study and improvement.