Search

The present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxonomies). For this purpose, an intra-annual time-series of 30 Sentinel-2 images, embedding phenology information, were investigated for 2018. The methodology adopted was based on a two-stage workflow employing a Support Vector Machine classifier. In the first stage only four Sentinel-2 multi-season images were analyzed, to provide an updated land cover map from where the grassland layer was extracted. The layer obtained was then used for masking the input features to the second stage. The latter stage discriminated the four grassland habitats by analyzing several input features configurations. These included multiple spectral indices selected from the time-series and the Digital Terrain Model. The results obtained from the different input configurations selected were compared to evaluate if the phenology information from time-series could improve grassland habitats discrimination. The highest F1 values (95.25% and 80.27%) were achieved for 6210/E1.263 and 6220/E1.434, respectively, whereas the results remained stable (97,33%) for 62A0/E1.55 and quite low (75,97%) for X/E1.61-E1.C2-E1.C4. However, since for all the four habitats analyzed no single configuration resulted effective, a Majority Vote algorithm was applied to achieve a reduction in classification uncertainty. [ABSTRACT FROM AUTHOR]

Abstract: Monitoring protected areas and their surrounds at local to regional scales is essential given their vulnerability to anthropogenic pressures, including those associated with climatic fluctuation, and important for management and fulfilment of national and international directives and agreements. Whilst monitoring has commonly revolved around field data, remote sensing can play a key role in establishing baselines of the extent and condition of habitats and associated species diversity as well as quantifying losses, degradation or recovery associated with specific events or processes. Landsat images constitute a major data source for habitat monitoring, capturing broad scale information on changes in habitat extent and spatial patterns of fragmentation that allow disturbances in protected areas to be identified. These data are, however, less able to provide information on changes in habitat quality, species distribution and fine-scale disturbances, and hence data from other spaceborne optical sensors are increasingly being considered. Very High Resolution (VHR) optical datasets have been exploited to a lesser extent, partly because of the relative recency of spaceborne observations and challenges associated with obtaining and routinely extracting information from airborne multi-spectral and hyperspectral datasets. The lack of a shortwave infrared band in many VHR datasets and provision of too much detail (e.g., shadows within and from landscape objects) also present challenges in some cases. Light Detection and Ranging (LiDAR) and Synthetic Aperture Radar (SAR) data, particularly when used synergistically with optical data, have benefited the detection of changes in the three-dimensional structure of habitats. This review shows that remote sensing has a strong, yet underexploited potential to assist in the monitoring of protected areas. However, the data generated need to be utilized more effectively to enable better management of the condition of protected areas and their surrounds, prepare for climate change, and assist planning for future landscape management. [Copyright &y& Elsevier]

The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the "Murgia Alta" protected site. To this end, we compared two approaches differing only by the first layer machinery, which, in one case, is instantiated as a fully-connected layer and, in the other case, results in a ConvNet equipped with kernels covering the whole input (wide-kernel ConvNet). A patchwise approach, tessellating training reference data in square patches, was adopted. Besides assessing the effectiveness of ConvNets with patched multispectral data, we analyzed how the information needed for classification spreads to patterns over convex sets of pixels. Our results show that: (a) with an F1-score of around 97% (5 × 5 patch size), ConvNets provides an excellent tool for patch-based pattern recognition with multispectral input data without requiring special feature extraction; (b) the information spreads over the limit of a single pixel: the performance of the network increases until 5 × 5 patch sizes are used and then ConvNet performance starts decreasing. [ABSTRACT FROM AUTHOR]