Classification of protected grassland habitats using deep learning architectures on Sentinel-2 satellite imagery data

• This study evaluates CNNs and ViT models for grassland classification with Copernicus S2 imagery. • ResNet-50 and SwinV2-t showed the best results in precision and recall. • Slight performance differences among models highlight the potential of CNNs and ViTs in conservation. • Data augmentation, SGD with momentum optimizer and Categorical Cross Entropy enhanced performance across various metrics. • The findings suggest using these techniques in other vegetation classes and more data could improve classification. This study examines the effectiveness of five deep learning models—ViTb-19, SwinV2-t, VGG-16, ResNet-50, and DenseNet-121—in distinguishing different vegetation types in the protected grasslands of Castilla y León region, Spain, following the guidelines of the Natura 92/43/CEE directive. Among the models, ResNet-50 achieved the highest weighted overall accuracy (OA) of 0.95, closely followed by SwinV2-t with an OA of 0.94, demonstrating their strong ability to detect complex patterns in satellite imagery. DenseNet-121 also performed competitively with a weighted OA of 0.93, while ViTb-19 and VGG-16 showed slightly lower performance. SwinV2-t, a transformer-based model, outperformed traditional CNN architectures in data-rich classes but faced challenges in classifying habitats with limited representation. Consequently, this study identifies these challenges that conventional transformer architectures pose in classifying certain habitats with limited representation and intricate features. Highlighting the advantages of deep learning technologies for environmental monitoring and conservation, the study provides important insights for adjusting neural network architectures for effective habitat classification. This suggests the necessity of selecting appropriate architectures such as SwinV2-t and ResNet50 to to effectively address the intricate requirements of satellite imagery analysis.