Predicting Barrier Island Shrub Presence Using Remote Sensing Products and Machine Learning Techniques

Abstract Barrier islands are highly dynamic coastal landforms that are economically, ecologically, and societally important. Woody vegetation located within barrier island interiors can alter patterns of overwash, leading to periods of periodic‐barrier island retreat. Due to the interplay between island interior vegetation and patterns of barrier island migration, it is critical to better understand the factors controlling the presence of woody vegetation on barrier islands. To provide new insight into this topic, we use remote sensing data collected by LiDAR, LANDSAT, and aerial photography to measure shrub presence, coastal dune metrics, and island characteristics (e.g., beach width, island width) for an undeveloped mixed‐energy barrier island system in Virginia along the US mid‐Atlantic coast. We apply decision tree and random forest machine learning methods to identify new empirical relationships between island geomorphology and shrub presence. We find that shrubs are highly likely (90% likelihood) to be present in areas where dune elevations are above ∼1.9 m and island interior widths are greater than ∼160 m and that shrubs are unlikely (10% likelihood) to be present in areas where island interior widths are less than ∼160 m regardless of dune elevation. Our machine learning predictions are 90% accurate for the Virginia Barrier Islands, with almost half of our incorrect predictions (5% of total transects) being attributable to system hysteresis; shrubs require time to adapt to changing conditions and therefore their growth and removal lags changes in island geomorphology, which can occur more rapidly. Plain Language Summary In this study, we present two machine learning models for predicting the presence of shrubs on barrier islands. We use data derived from satellites, LiDAR, and aerial imagery to create machine learning models. Using these models, we find that whether or not shrubs are present on barrier islands depends on dune elevation and the width of island interior sustained over time; sufficiently high dune elevations and sufficiently wide widths are necessary to support shrubs. Additionally, in certain areas, we observe a lag between predicted and observed behavior. We attribute this lag to the different time scales over which shrub and barrier island geomorphology processes operate; barrier island geomorphology can change rapidly, but it can take several years for shrubs to respond to these changes. Key Points Decision tree analysis and random forest modeling can predict shrub presence on barrier islands in Virginia with ∼90% accuracy Shrub presence on barrier islands correlates with dune elevations >1.9 m and maintenance of island interior widths >160 m over a ∼6‐year period Shrub establishment and removal lags changes in geomorphic conditions, indicating hysteresis