Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping.

Monitoring the world's areas that are more vulnerable to natural hazards has become crucial worldwide. In order to reduce disaster risk, effective tools and relevant land cover (LC) data are needed. This work aimed to generate a high-resolution LC map of flood-prone rural villages in southwest Niger using multispectral drone imagery. The LC was focused on highly thematically detailed classes. Two photogrammetric flights of fixed-wing unmanned aerial systems (UAS) using RGB and NIR optical sensors were realized. The LC input dataset was generated using structure from motion (SfM) standard workflow, resulting in two orthomosaics and a digital surface model (DSM). The LC system is composed of nine classes, which are relevant for estimating flood-induced potential damages, such as houses and production areas. The LC was generated through object-oriented supervised classification using a random forest (RF) classifier. Textural and elevation features were computed to overcome the mapping difficulties due to the high spectral homogeneity of cover types. The training-test dataset was manually defined. The segmentation resulted in an F1_score of 0.70 and a median Jaccard index of 0.88. The RF model performed with an overall accuracy of 0.94, with the grasslands and the rocky clustered areas classes the least performant.

Method for fluvial and pluvial flood risk assessment in rural settlements.

Flood risk assessments in the Global South have increased since the adoption of the United Nations Sendai Framework for Disaster Risk Reduction 2015-2030. However, they often fail to meet disaster risk reduction needs at the local scale, because they typically consider only one hazard (fluvial or pluvial floods). Furthermore, hazard and exposure are considered as stationary conditions, flood-prone assets are rarely identified, risk reduction measures are not identified in detail for specific locations, and the convenience of reducing or accepting risk is not evaluated. This paper describes a flood risk assessment method that is innovative in that it considers three hazard types (backwater, fluvial, and pluvial floods) and multiple risk scenarios; it uses orthophotos generated from images captured by an unmanned aerial vehicle and very high-resolution satellite images, and it involves communities in risk assessment. The method was applied to four rural settlements along the Sirba River, Niger. The assessment identifies the benefit of reducing risk in monetary terms, as well as the intangible benefits that reducing risk could generate, and it detects opportunities that flooding offers for rural development. The method can be replicated in all contexts where decision-making support is needed for flood risk assessment planning.•Risk analysis and evaluation is participatory.•Risk assessment is improved by combining local and technical knowledge.•Assets are identified using very-high-resolution satellite and drone images.