In many countries, urban flooding due to local, intense rainfall is expected to become more frequent because of climate change and urbanization. Cities trying to adapt to this growing risk are challenged by a chronic lack of surface flooding data that are needed for flood risk assessment and planning. In this work, we propose a new approach that exploits existing surveillance camera systems to provide qualitative flood level trend information at scale. The approach uses a deep convolutional neural network (DCNN) to detect floodwater in surveillance footage and a novel qualitative flood index (namely, the static observer flooding index – SOFI) as a proxy for water level fluctuations visible from a surveillance camera's viewpoint. To demonstrate the approach, we trained the DCNN on 1218 flooding images collected from the Internet and applied it to six surveillance videos representing different flooding and lighting conditions. The SOFI signal obtained from the videos had a 75 % correlation to the actual water level fluctuation on average. By retraining the DCNN with a few frames from a given video, the correlation is increased to 85 % on average. The results confirm that the approach is versatile, with the potential to be applied to a variety of surveillance camera models and flooding situations without the need for on-site camera calibration. Thanks to this flexibility, this approach could be a cheap and highly scalable alternative to conventional sensing methods.

Precise and detailed digital elevation models (DEMs) are essential to accurately predict overland flow in urban areas. Unfortunately, traditional sources of DEM, such as airplane light detection and ranging (lidar) DEMs and point and contour maps, remain a bottleneck for detailed and reliable overland flow models, because the resulting DEMs are too coarse to provide DEMs of sufficient detail to inform urban overland flows. Interestingly, technological developments of unmanned aerial vehicles (UAVs) suggest that they have matured enough to be a competitive alternative to satellites or airplanes. However, this has not been tested so far. In this study we therefore evaluated whether DEMs generated from UAV imagery are suitable for urban drainage overland flow modelling. Specifically, 14 UAV flights were conducted to assess the influence of four different flight parameters on the quality of generated DEMs: (i) flight altitude, (ii) image overlapping, (iii) camera pitch, and (iv) weather conditions. In addition, we compared the best-quality UAV DEM to a conventional lidar-based DEM. To evaluate both the quality of the UAV DEMs and the comparison to lidar-based DEMs, we performed regression analysis on several qualitative and quantitative metrics, such as elevation accuracy, quality of object representation (e.g. buildings, walls and trees) in the DEM, which were specifically tailored to assess overland flow modelling performance, using the flight parameters as explanatory variables. Our results suggested that, first, as expected, flight altitude influenced the DEM quality most, where lower flights produce better DEMs; in a similar fashion, overcast weather conditions are preferable, but weather conditions and other factors influence DEM quality much less. Second, we found that for urban overland flow modelling, the UAV DEMs performed competitively in comparison to a traditional lidar-based DEM. An important advantage of using UAVs to generate DEMs in urban areas is their flexibility that enables more frequent, local, and affordable elevation data updates, allowing, for example, to capture different tree foliage conditions.

In the event of a flood, being able to build accurate flood level maps is essential for supporting emergency plan operations. In order to build such maps, it is important to collect observations from the disaster area. Social media platforms can be useful sources of information in this case, as people located in the flood area tend to share text and pictures depicting the current situation. Developing an effective and fully automatized method able to retrieve data from social media and extract useful information in real-time is crucial for a quick and proper response to these catastrophic events. In this paper, we propose a method to quantify flood-water from images gathered from social media. If no prior information about the zone where the picture was taken is available, one possible way to estimate the flood level consists of assessing how much the objects appearing in the image are submerged in water. There are various factors that make this task difficult: i) the precise size of the objects appearing in the image might not be known; ii) flood-water appearing in different zones of the image scene might have different height; iii) objects may be only partially visible as they can be submerged in water. In order to solve these problems, we propose a method that first locates selected classes of objects whose sizes are approximately known, then, it leverages this property to estimate the water level. To prove the validity of this approach, we first build a flood-water image dataset, then we use it to train a deep learning model. We finally show the ability of our trained model to recognize objects and at the same time predict correctly flood-water level.