Under global climate change, urban flooding occurs frequently, leading to huge economic losses and human casualties. Extreme rainfall is one of the direct and key causes of urban flooding, and accurate rainfall estimates at high spatiotemporal resolution are of great significance for real-time urban flood forecasting. Using existing rainfall intensity measurement technologies, including ground rainfall gauges, ground-based radar, and satellite remote sensing, it is challenging to obtain estimates of the desired quality and resolution. However, an approach based on processing distributed surveillance camera network imagery through machine learning algorithms to estimate rainfall intensities shows considerable promise. Here, we present a novel approach that first extracts raindrop information from the surveillance camera images (rather than using the raw imagery directly), followed by the use of convolutional neural networks to estimate rainfall intensity from the resulting raindrop information. Evaluation of the approach on 12 rainfall events under both daytime and nighttime conditions shows that generalization ability, and especially nighttime predictive performance, is significantly improved. This represents an important step toward achieving real-time, high spatiotemporal resolution, measurement of urban rainfall at relatively low cost.

Water quality sensors are often spatially distributed in water distribution systems (WDSs) to detect contamination events and monitor quality parameters (e.g., chlorine residual levels), thereby ensuring safety of a WDS. The performance of a water quality sensor placement strategy (WQSPS) is not only affected by sensor spatial deployment that has been extensively analyzed in literature, but also by possible sensor failures that have been rarely explored so far. However, enumerating all possible sensor failure scenarios is computationally infeasible for a WQSPS with a large number of sensors. To this end, this paper proposes an evolutionary algorithm (EA) based method to systematically and efficiently investigate the WQSPS′ global resilience considering all likely sensor failures. First, new metrics are developed in the proposed method to assess the global resilience of a WQSPS. This is followed by a proposal of an efficient optimization approach based on an EA to identify the values of global resilience metrics. Finally, the sensors within the WQSPS are ranked to identify their relative importance in maintaining the WQSPS's detection performance. Two real-world WDSs with four WQSPSs for each case study are used to demonstrate the utility of the proposed method. Results show that: (i) compared to the traditional global resilience analysis method, the proposed EA-based approach identifies improved values of global resilience metrics, (ii) the WQSPSs that deploy sensors close to large demand users are overall more resilient in handling sensor failures relative to other design solutions, thus offering important insight to facilitate the selection of WQSPSs, and (iii) sensor rankings based on the global resilience can identify those sensors whose failure would significantly reduce the WQSPS's performance thereby providing guidance to enable effective water quality sensor management and maintenance.