Integration of earth observation and census data for mapping a multi-temporal flood vulnerability index: a case study on Northeast Italy     

Cian  Fabio  Giupponi  Carlo  Marconcini  Mattia 《Natural Hazards》2021,106(3):2163-2184

Climate sciences foresee a future where extreme weather events could happen with increased frequency and strength, which would in turn increase risks of floods (i.e. the main source of losses in the world). The Mediterranean basin is considered a hot spot in terms of climate vulnerability and risk. The expected impacts of those events are exacerbated by land-use change and, in particular, by urban growth which increases soil sealing and, hence, water runoff. The ultimate consequence would be an increase of fatalities and injuries, but also of economic losses in urban areas, commercial and productive sites, infrastructures and agriculture. Flood damages have different magnitudes depending on the economic value of the exposed assets and on level of physical contact with the hazard. This work aims at proposing a methodology, easily customizable by experts’ elicitation, able to quantify and map the social component of vulnerability through the integration of earth observation (EO) and census data with the aim of allowing for a multi-temporal spatial assessment. Firstly, data on employment, properties and education are used for assessing the adaptive capacity of the society to increase resilience to adverse events, whereas, secondly, coping capacity, i.e. the capacities to deal with events during their manifestation, is mapped by aggregating demographic and socio-economic data, urban growth analysis and memory on past events. Thirdly, the physical dimension of exposed assets (susceptibility) is assessed by combining building properties acquired by census data and land-surface characteristics derived from EO data. Finally, the three components (i.e. adaptive and coping capacity and susceptibility) are aggregated for calculating the dynamic flood vulnerability index (FVI). The approach has been applied to Northeast Italy, a region frequently hit by floods, which has experienced a significant urban and economic development in the past decades, thus making the dynamic study of FVI particularly relevant. The analysis has been carried out from 1991 to 2016 at a 5-year steps, showing how the integration of different data sources allows to produce a dynamic assessment of vulnerability, which can be very relevant for planning in support of climate change adaptation and disaster risk reduction.

  相似文献   

A Composite Semisupervised SVM for Classification of Hyperspectral Images   总被引：2，自引：0，他引：2  

Marconcini  M. Camps-Valls  G. Bruzzone  L. 《Geoscience and Remote Sensing Letters, IEEE》2009,6(2):234-238

This letter presents a novel composite semisupervised support vector machine (SVM) for the spectral-spatial classification of hyperspectral images. In particular, the proposed technique exploits the following: 1) unlabeled data for increasing the reliability of the training phase when few training samples are available and 2) composite kernel functions for simultaneously taking into account spectral and spatial information included in the considered image. Experiments carried out on a hyperspectral image pointed out the effectiveness of the presented technique, which resulted in a significant increase of the classification accuracy with respect to both supervised SVMs and progressive semisupervised SVMs with single kernels, as well as supervised SVMs with composite kernels.  相似文献