Machine Learning and Unmanned Aerial Systems for Managing Autumn Olive (Elaeagnus Umbellata) on Reclaimed Surface Mines

Abstract This research provides an innovative approach for managing autumn olive ( Elaeagnus umbellata ) on reclaimed surface mines through the use of machine learning and unmanned aerial systems. The proliferation of autumn olive presents significant ecological challenges on disturbed landscapes, necessitating more efficient detection and control methods. This study evaluated the machine learning method of random forest for identifying autumn olive across four phenological stages using high-resolution imagery. The peak growing stage exhibited the highest detection performance for autumn olive with a producer’s accuracy of 70.3% and a user’s accuracy of 68.9%. The F1-score reached its maximum value of 0.696 during this stage, indicating optimal overall performance for autumn olive detection. Unmanned aerial herbicide applications demonstrated effective control with minimal impact on surrounding vegetation and reduced labor requirements. The workflow from unmanned arial system (UAS)–based detection to UAS-based treatment represents a promising opportunity for invasive species management on reclaimed mine lands, offering enhanced accuracy, efficiency and cost-effectiveness compared with traditional management practices.