The characterization of multispectral images of the Batangas coastline using machine learning and UAV imaging

Accurate and precise monitoring of coastal environments allows for the better preservation of their biodiversity. This study applies multispectral imaging, Unmanned Aerial Vehicles (UAVs), and supervised and unsupervised techniques to characterize a coastal area in Batangas, Philippines. Multispectral image data was gathered using a DJI Mavic 3M drone. Afterwards, vegetation maps using NDVI, GNDVI, NDRE, and LCI were generated. Regions of the image were then clustered using the k-means clustering algorithm to define habitats in the area of study. These clusters were then used to train supervised machine-learning algorithms for pixel-based image classification. After classifying the entire image with these models, the identified habitats were characterized based on their associated vegetation index measurements. It was found that aquatic areas of the image possessed scores associated with healthy and photosynthetically active water.