GIS, Remote Sensing and Machine Learning: Data Integration to Support the Management of Coastal Island Ecosystems.

Abstract

Islands are important components of many coastal areas around the world; however, by virtue of their geographical isolation, the state of these ecosystems is often poorly known. To address the knowledge gap for the province of Nova Scotia, Canada, geographic information systems (GIS), remote sensing (RS), and machine learning (ML) were used to examine the status of nearly 4000 islands. We classified islands topographically and determined, based on 1 m resolution LiDAR, that approximately 70% are <2 m average elevation and highly vulnerable to partial or complete flooding under near-term regimes of sea level rise and storm surge potential. Vegetation cover was strongly related to topographic class, with higher, more steeply-sided islands having more tree cover and less sand, rock, and wetland. Climatic changes were most pronounced in the form of sea surface temperature (SST) warming, with August changes (+0.063 °C yr^-1) being 6.3× higher than the global mean background rate, particularly affecting the Gulf of St. Lawrence subregion. Human activity, in the form of marine traffic, is a pervasive stress. To integrate all these factors, a random forest ML model was trained using tree mortality from forest inventory records as the environmental response, and the predictions were used to define a region-wide Ecosystem Stress Index (ESI). These findings demonstrate the kinds of insights geospatial data and ML can provide, and offer tools for improving our understanding of coastal island vulnerability.