Sentinel-2 Remote Sensed Image Classification with Patchwise Trained ConvNets for Grassland Habitat Discrimination

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.

Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination

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.

Effects of pH on embryo tolerance and adult behavior in the tiger salamander, Ambystoma tigrinum tigrinum

We examined adult discrimination ability and embryo performance under different pH conditions in the eastern tiger salamander, Ambystoma tigrinum tigrinum. We collected individuals from three populations in habitats that differed naturally in pH, thus allowing interpretation of population-specific responses in embryos and adults. We conducted pool-choice experiments in the field using two pH treatments to determine adult pH discrimination ability and controlled laboratory toxicity tests using eight pH treatments to evaluate embryo performance. Adult discrimination ability differed among source populations. Male salamanders from the locality with the highest pH were more likely to stay in neutral-pH pools and more likely to leave acidic ones. Males from the locality with the lowest pH were also more likely to remain within neutral pools, but their rates of staying and leaving acidic ones did not differ. These results suggest that the pH of the source-population habitat may influence breeding-habitat discrimination by adults. Decreasing pH produced similar patterns of lethal (survival) and sublethal (date and size at hatching) effects on embryos from the three populations, with reduced performance at low pH. Survival of embryos was more than 70% at pH 4.5 and above, but decreased dramatically at lower pH levels. The pH at which 50% mortality occurs (LC50) was estimated as 4.2, suggesting that tiger salamanders from our populations were relatively acid tolerant compared with congeners. However, significant sublethal effects could reduce the subsequent success of surviving hatchlings. Our results are consistent with the hypothesis that adult discrimination ability depends on pH levels in the breeding habitat. This suggests that adult behavior patterns could influence the success of population reintroductions to previously acidified areas. Thus, data on pH responses at all stages in the amphibian life cycle should contribute to management decisions.