Habitat classification using convolutional neural networks and multitemporal multispectral aerial imagery

Abstract

The monitoring of threatened habitats is a key objective of European environmental policies. Due to the high cost of current field-based habitat mapping techniques, there is keen interest in proposing solutions that can reduce cost through increased levels of automation. Our study aims to propose a habitat mapping solution that benefits both from the merits of convolutional neural networks (CNNs) for image classification tasks, as well as from the high spatial, spectral, and multitemporal unmanned aerial vehicle image data, which shows great potential for accurate vegetation classification. The proposed CNN-based method uses multitemporal multispectral aerial imagery for the classification of threatened coastal habitats in the Maharees (Ireland) and shows a high level of classification accuracy.

Predicting Abiotic Soil Characteristics Using Sentinel-2 at Nature-Management-Relevant Spatial Scales and Extent

“…Including habitat type improved our models significantly so being able to remotely sense this information and feed it into models like ours would be clearly desirable. Currently, researchers and technicians from several different parts of the World are or have been working on such remotesensing-based classification of habitat types over large areas [42][43][44]. While these models are still far from perfect, they are slowly improving and that could possibly enhance our ability to improve models like the ones we developed here.…”