Improved LC/LU maps and flood models through crowdsourced information

Flood risk prediction has been traditionally based on models that are developed from time-series of data collected over long periods of time from expensive and hard to maintain in situ sensors available only in specific areas. SCENT is a H2020 project which provides an integrated toolbox of smart collaborative and innovating technologies that augment costly in situ infrastructure, enabling citizens to become the ‘eyes’ of the policy makers by monitoring LC/LU changes in their everyday activities and related environmental phenomena like floods by crowdsourcing relevant information. Policy makers and relevant stakeholders are able to set-up citizen science campaigns in areas where specific environmental information is needed. These data may include images that are processed through an intelligent engine and classified based on a LC/LU taxonomy, sensor measurements with low-cost portable environmental sensor or river measurements. The crowdsourced LC/LU information is used to created improved and more detailed maps of the area of interest where taxonomy elements such as river banks are identified and categorized base on their coverage, such as low grass and stone. The produced LC/LU maps along with the sensor and river measurements are used to create flood models, used by public authorities and stakeholders to better understand the area of interest, its needs and the steps needed to support its sustainability