Mapping the recovery of Mountain Ash (Eucalyptus regnans) and Alpine Ash (E. delegatensis) using satellite remote sensing and a machine learning classifier

Abstract

This research presents a random forest classification approach to map the response of the obligate-seeder Eucalyptus species, Mountain Ash (Eucalyptus regnans) and Alpine Ash (E. delegatensis), to disturbance from timber harvesting in the Victorian Central Highlands in south-eastern Australia. A Sentinel-2 MultiSpectral Instrument (MSI) composite image was classified and analysed using a random forest algorithm trained using field data collected within fifty-three sites. Training and validation datasets were produced by randomly sub setting using a 70:30 split. Validation was performed by producing a confusion matrix using the points which were excluded from model training. The random forest model demonstrated strong performance at distinguishing Eucalyptus regrowth from the dominant understory species, Silver Wattle (Acacia dealbata), achieving an F1-score of 97.3% and true skill statistic of 96.4%.

This study showcases the operational insights that satellite remote sensing data and machine learning can provide for regional-scale monitoring and management of E. regnans and E. delegatensis dominant ecosystems following disturbance. Due to the high conservation value of these communities, and their sensitivity to frequent high intensity disturbance and low precipitation during regeneration, this research seeks to provide a means to assess the condition of regenerating forest and in doing so enhance our understanding of these ecologically significant ecosystems in response to changing environmental conditions.