This paper discusses a methodology where geo-spatial analysis tools are used to quantify risk derived from anthropic activities on habitats and species. The method has been developed with a focus on simplification and the quality of standard procedures set on flora and fauna protected by the European Directives. In this study case, the DPSIR (Drivers, Pressures, State, Impacts, Responses) is applied using spatial procedures in a geographical information system (GIS) framework. This approach can be inserted in a multidimensional space as the analysis is applied to each threat, pressure and activity and also to each habitat and species, at the spatial and temporal scale. Threats, pressures and activities, stress and indicators can be managed by means of a geo-database and analyzed using spatial analysis functions in a tested GIS workflow environment. The method applies a matrix with risk values, and the final product is a geo-spatial representation of impact indicators, which can be used as a support for decision-makers at various levels (regional, national and European).

Background: NASA World Wind is an open source application-programming interface for developing geographic information systems based on a virtual globe rendering engine representing a planet. NASA World Wind provides the ideal environment for scientific data, their analysis, visual representation and interaction with users, in a single platform, which can be deployed both as a Java desktop application (NASA World Wind) or a JavaScript web application (ESA-NASA Web World Wind).

Commission VII, WG VII/4KEY WORDS: Machine learning, Sentinel-2, Remote sensing, Neural nets, Agriculture, Land cover, Classification ABSTRACT:Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km 2 , obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. Validation is carried out using three different approaches: (i) using pixels from the training dataset (train), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (kfold) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (full) and with k-fold cross-validation (kfold) with ten folds. Results from validation of predictions of the whole dataset (full) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines -with default radial basis function kernel -methods follow closely with comparable performance.

ABSTRACT:This paper considers Leica backpack and photogrammetric surveys of a mediaeval bastion in Padua, Italy. Furhtermore, terrestrial laser scanning (TLS) survey is considered in order to provide a state of the art reconstruction of the bastion. Despite control points are typically used to avoid deformations in photogrammetric surveys and ensure correct scaling of the reconstruction, in this paper a different approach is considered: this work is part of a project aiming at the development of a system exploiting ultra-wide band (UWB) devices to provide correct scaling of the reconstruction. In particular, low cost Pozyx UWB devices are used to estimate camera positions during image acquisitions. Then, in order to obtain a metric reconstruction, scale factor in the photogrammetric survey is estimated by comparing camera positions obtained from UWB measurements with those obtained from photogrammetric reconstruction. Compared with the TLS survey, the considered photogrammetric model of the bastion results in a RMSE of 21.9cm, average error 13.4cm, and standard deviation 13.5cm. Excluding the final part of the bastion left wing, where the presence of several poles make reconstruction more difficult, (RMSE) fitting error is 17.3cm, average error 11.5cm, and standard deviation 9.5cm. Instead, comparison of Leica backpack and TLS surveys leads to an average error of 4.7cm and standard deviation 0.6cm (4.2cm and 0.3cm, respectively, by excluding the final part of the left wing).

This paper reports a semi-automated workflow for detection and quantification of forest damage from windthrow in an Alpine region, in particular from the Vaia storm in October 2018. A web-GIS platform allows to select the damaged area by drawing polygons; several vegetation indices (VIs) are automatically calculated using remote sensing data (Sentinel-2A) and tested to identify the more suitable ones for quantifying forest damage using cross-validation with ground-truth data. Results show that the mean value of NDVI and NDMI decreased in the damaged areas, and have a strong negative correlation with severity. RGI has an opposite behavior in contrast with NDVI and NDMI, as it highlights the red component of the land surface. In all cases, variance of the VI increases after the event between 0.03 and 0.15. Understorey not damaged from the windthrow, if consisting of 40% or more of the total cover in the area, undermines significantly the sensibility of the VIs to detecting and predicting severity. Using aggregational statistics (average and standard deviation) of VIs over polygons as input to a machine learning algorithm, i.e., Random Forest, results in severity prediction with regression reaching a root mean square error (RMSE) of 9.96, on a severity scale of 0–100, using an ensemble of area averages and standard deviations of NDVI, NDMI, and RGI indices. The results show that combining more than one VI can significantly improve the estimation of severity, and web-GIS tools can support decisions with selected VIs. The reported results prove that Sentinel-2 imagery can be deployed and analysed via web-tools to estimate forest damage severity and that VIs can be used via machine learning for predicting severity of damage, with careful evaluation of the effect of understorey in each situation.