Forest-type classification is a very complex and difficult subject. The complexity increases with urban and peri-urban forests because of the variety of features that exist in remote sensing images. The success of forest management that includes forest preservation depends strongly on the accuracy of forest-type classification. Several classification methods are used to map urban and peri-urban forests and to identify healthy and non-healthy ones. Some of these methods have shown success in the classification of forests where others failed. The successful methods used specific remote sensing data technology, such as hyper-spectral and very high spatial resolution (VHR) images. However, both VHR and hyper-spectral sensors are very expensive, and hyper-spectral sensors are not widely available on satellite platforms, unlike multi-spectral sensors. Moreover, aerial images are limited in use, very expensive, and hard to arrange and manage. To solve the aforementioned problems, an advanced method, self-organizing–deep learning (SO-UNet), was created to classify forests in the urban and peri-urban environment using multi-spectral, multi-temporal, and medium spatial resolution Sentinel-2 images. SO-UNet is a combination of two different machine learning technologies: artificial neural network unsupervised self-organizing maps and deep learning UNet. Many experiments have been conducted, and the results showed that SO-UNet overwhelms UNet significantly. The experiments encompassed different settings for the parameters that control the algorithms.
1 January 2021 in European Journal of Remote Sensing
This study proposes an automated method for distinguishing trees (T) from no-trees (NT) by means of optical data. We make use of an optical approach based on a statistical threshold to detect T areas on visible and near infrared bands. An object-based image classification allows to detect three kinds of tree out of forest (TOF) structures: forest patches (FP), isolated trees (IT), tree hedgerows (THR), distinguished from forest (F). Ground truth validation allows estimating the accuracy of classification. Four optical bands and six spectral indices are compared detecting images’ T areas: B2, B3, B4 and B8 bands, Negative Luminance (NL), Normalized Difference Vegetation index (NDVI), Green NDVI (GNDVI), Blue NDVI (BNDVI), Panchromatic NDVI (PNDVI) and Enhanced Vegetation Index (EVI). NL shows a relatively better capability for TOF detection and classification, with overall accuracy (OA) exceeding 92% and p-value = 10−5. Experiments were conducted on optical data acquired by Sentinel-2 in 2016 over the Alfina highland, central Italy. The tree characteristics were extracted exploiting GNU Octave Image Package. Our results show that this new approach could be extended to the detection and mapping of TOF within large areas of agroforestry landscape.
The use of isotopic signatures in animal tissues provides information on the environment where they are living and, notably, on their diet. Carbon and, whenever possible, nitrogen stable isotope analyses were performed in animal hairs, muscles and fat. Particularly, we analyzed both carbon and nitrogen isotopic compositions (δ13C and δ15N) on wild boar samples across three different areas of central Italy (Latium region): Tyrrhenian Coast (TC), Maremma (MA) and Central Plains (CP). The agricultural habits of these areas imply that, in winter, no crops are available for wild boars, which feed mainly on acorns and natural feeds (tubers, earthworms etc.). In addition, the three areas were influenced by oak masting. One of these areas (CP) was characterised by the spreading of corn during the hunting season to attract the animals. For each area, we sampled 10 animals aged between 12 and 24 months and balanced by gender. Anenrichment of δ13C in CP area, where corn was used, was observed in all the analysed tissues in comparison to other areas (MA and TC). In CP area, enriched values of δ15N were also observed in all the tissues. The research demonstrates that both δ13C andδ15N in free-living wild boar tissues are influenced by sampling area. According to feeding habits of the species and wildlife management (feed supplementation), the differences observed in δ13C and δ15Nare based on the specific feeding regime; particularly the use of corn in wintertime. Furthermore, the research highlights and discusses diversities and relationships among δ13C and δ15N in the hair, fat and muscles of free-living wild boar.