High-Resolution Hyperspectral Mapping: From Vegetation Biodiversity to Urban Land Classification

his collection explores the powerful applications of hyperspectral remote sensing for high-resolution mapping of vegetation biodiversity, urban land classification, and crop type detection. It includes studies utilizing advanced techniques like convolutional autoencoders and convolutional neural networks (CNNs), along with evaluations of PRISMA and AVIRIS-NG hyperspectral data for environmental monitoring and land use analysis. These studies offer valuable methodologies for researchers, remote sensing professionals, and students to enhance land management, ecological studies, and precision agriculture through the use of high-resolution hyperspectral imagery.