The Potential of Sentinel-2-derived Phenological Data SRTM Data for Estimating Plant Diversity of Wetlands in the UK
Wetlands are an essential for conservation. To understand more about biodiversity of wetlands in a less labour intense way, scientists have applied remote sensed data in their researches. To test the potential of Sentinel-2-derived Phenological Data and SRTM Topographical data for the estimation of plant diversity in UK wetlands, Sentinel-2 images of 2019 all year are used to extract the phenological data of over 150 wetlands in the UK. Together with SRTM data, the extracted phenology is used to fit with the plant richness, chao1 index and Shannon index using ordinary least squares, support vector machines and random forest algorithms. The result shows that random forest have the potential to predict plant richness using NDVI phenological data and SRTM data. However, the quality of the research can be enhanced by hyperparameter optimisation for random forest models and involving the details of ecological surveys.