Wildfire susceptibility maps display the spatial probability of an area to burn in the future, based solely on the intrinsic local proprieties of a site. Current studies in this field often rely on statistical models, often improved by expert knowledge for data retrieving and processing. In the last few years, machine learning algorithms have proven to be successful in this domain, thanks to their capability of learning from data through the modeling of hidden relationships. In the present study, authors introduce an approach based on random forests, allowing elaborating a wildfire susceptibility map for the Liguria region in Italy. This region is highly affected by wildfires due to the dense and heterogeneous vegetation, with more than 70% of its surface covered by forests, and due to the favorable climatic conditions. Susceptibility was assessed by considering the dataset of the mapped fire perimeters, spanning a 21-year period (1997–2017) and different geo-environmental predisposing factors (i.e., land cover, vegetation type, road network, altitude, and derivatives). One main objective was to compare different models in order to evaluate the effect of: (i) including or excluding the neighboring vegetation type as additional predisposing factors and (ii) using an increasing number of folds in the spatial-cross validation procedure. Susceptibility maps for the two fire seasons were finally elaborated and validated. Results highlighted the capacity of the proposed approach to identify areas that could be affected by wildfires in the near future, as well as its goodness in assessing the efficiency of fire-fighting activities.

In this study we analyzed a series of terrestrial LiDAR point clouds acquired over a cliff in Puigcercos (Catalonia, Spain). The objective was to detect and extract individual rockfall events that occurred during a time span of six months and to investigate their spatial distribution. To this end local and global cluster algorithms were applied. First we used the nearest neighbor clutter removal (NNCR) method in combination with the expectation-maximization (EM) algorithm to separate feature points from clutter; then a density based algorithm (DBSCAN) allowed us to isolate the single cluster features which represented the rockfall events. Finally we estimated the Ripley's K-function to analyze the global spatial pattern of the identified rockfalls. The computations for the cluster analyses were carried out using R free software for statistical computing and graphics. The local cluster analysis allowed a proper identification and characterization of more than 600 rockfalls. The global spatial pattern analysis showed that these rockfalls were clustered and provided the range of distances at which these events tend to be aggregated