International Journal of Remote Sensing · 2019 · 21 citations · 73 references
Natural ResourcesEcologyForestryLandscape Pattern AnalysisRemote SensingTerrestrial EcologyRemote Sensing Change DetectionRemote Sensing For Biodiversity MonitoringRemote Sensing For Forest InventoryRemote Sensing For Resource AssessmentVegetation Change DetectionVegetation MonitoringGray-level Co-occurrence MatricesHigh-resolution Imagery AnalysisIsland EcologyNative Tree SpeciesRemote Sensing-based AssessmentSatellite Imagery AnalysisSatellite-based Forest InventoryTropical Forest Monitoring
Native forests on islands throughout the global tropics face increasing pressure from the human-driven expansion of coconut palm (Cocos nucifera) planted for the purposes of coconut oil harvest. Conversion from native forests to Cocos monocultures leads to drastic ecological consequences in island environments and alters terrestrial and marine food webs through a variety of cascading effects and feedbacks. Despite the ecological significance and geographic range of Cocos expansion, large-scale assessments of coconut proliferation are still lacking due to the isolated nature of many islands where Cocos is found. Remote sensing approaches are often used to monitor forest composition at broad scales, but the small physical size of most islands limits the use of many popular satellite sensors with 15–30 m resolution. The recent availability of very high resolution (<5 m) satellite imagery facilitates novel assessment of this major ecological pattern, but the increased resolution introduces problematic ‘salt-and-pepper’ effects due to the heterogeneous nature of palm frond canopies. This case study evaluates the effectiveness of applying grey-level co-occurrence matrix (GLCM) textural features to very high resolution (0.5–2 m) WorldView-2 imagery to resolve the canopy heterogeneity problem and map the extent of Cocos spread on 21 islets of Palmyra Atoll, a protected United States National Wildlife Refuge in the Northern Line Islands. A random forest (RF)-driven classification scheme differentiating between coconut palms, native trees including Pisonia grandis, and endemic Scaevola sericea shrubs achieved 97.0% overall accuracy and 98.4% producer’s and user’s accuracies for the coconut palm class when trained on a combined spectral and GLCM textural feature set. Classifications restricted to the eight spectral bands of WorldView-2 are not only less accurate (89.4% overall accuracy), but also significantly worse at identifying Cocos canopies (79.0% versus 98.0% accuracy when GLCM textures are included). However, paring down the full set of sixteen spectral and textural features to the three most important of each type did not result in significant changes in accuracy. These results demonstrate the effectiveness of a joint high-resolution textural and spectral approach for remotely quantifying the spread of Cocos and its impacts on native tree communities throughout the tropics, including remote island locations.
73
R: A Language and Environment for Statistical Computing
R Core Team · 2000 · 353K citations · Full text
Natural Sciences, Computer Science, Statistical Computing +10
Leo Breiman · Machine Learning · 2001 · 126.2K citations · Full text
High-Resolution Global Maps of 21st-Century Forest Cover Change
Matthew C. Hansen, Peter Potapov, Rebecca Moore et al. · Science · 2013 · 11.6K citations
Photogrammetric Engineering and Remote Sensing
John Nicol, B. King · UCL Discovery (University College London) · 2007 · 9.4K citations