Expansive areas of low elevation in many densely populated coastal areas are at elevated risk of storm surges and flooding due to torrential precipitation, as a result of sea level rise. These phenomena could have catastrophic impacts on coastal communities and result in the destruction of critical infrastructure, disruption of economic activities and salt water contamination of the water supply. The objective of the study presented in this paper was to identify various impacts of sea level rise on civil infrastructures in coastal areas and examine the adaptation measures suggested in the existing literature. To this end, a systemic review of the existing literature was conducted in order to identify a repository of studies addressing sea level rise impacts and adaptation measures in the context of infrastructure systems. The study focused on three infrastructure sectors: water and wastewater, energy, and road transportation. The collected information was then analyzed in order to identify different categories of sea level rise impacts and corresponding adaptation measures. The findings of the study are threefold: (1) the major categories of sea level rise impacts on different infrastructure systems; (2) measures for protection, accommodation, and retreat in response to sea level rise impacts; and (3) challenges related to implementing adaptation measures.

In this paper, we propose a deep learning model to forecast the range of increase in COVID-19 infected cases in future days and we present a novel method to compute equidimensional representations of multivariate time series and multivariate spatial time series data. Using this novel method, the proposed model can both take in a large number of heterogeneous features, such as census data, intra-county mobility, inter-county mobility, social distancing data, past growth of infection, among others, and learn complex interactions between these features. Using data collected from various sources, we estimate the range of increase in infected cases seven days into the future for all U.S. counties. In addition, we use the model to identify the most influential features for prediction of the growth of infection. We also analyze pairs of features and estimate the amount of observed second-order interaction between them. Experiments show that the proposed model obtains satisfactory predictive performance and fairly interpretable feature analysis results; hence, the proposed model could complement the standard epidemiological models for national-level surveillance of pandemics, such as COVID-19. The results and findings obtained from the deep learning model could potentially inform policymakers and researchers in devising effective mitigation and response strategies. To fast-track further development and experimentation, the code used to implement the proposed model has been made fully open source.

While conceptual definitions have provided a foundation for measuring inequality of access and resilience in urban facilities, the challenge for researchers and practitioners alike has been to develop analytical support for urban system development that reduces inequality and improves resilience. Using 30 million large-scale anonymized smartphone-location data, here, we calibrate models to optimize the distribution of facilities and present insights into the interplay between equality and resilience in the development of urban facilities. Results from ten metropolitan counties in the United States reveal that inequality of access to facilities is due to the inconsistency between population and facility distributions, which can be reduced by minimizing total travel costs for urban populations. Resilience increases with more equitable facility distribution by increasing effective embeddedness ranging from 10% to 30% for different facilities and counties. The results imply that resilience and equality are related and should be considered jointly in urban system development.

The objective of this study is to create and test a hybrid deep learning (DL) model, FastGRNN‐FCN (fast, accurate, stable and tiny gated recurrent neural network‐fully convolutional network), for urban flood prediction and situation awareness using channel network sensors data. The study used Harris County, Texas, as the testbed, and obtained channel sensor data from three historical flood events (e.g., 2016 Tax Day Flood, 2016 Memorial Day Flood, and 2017 Hurricane Harvey Flood) for training and validating the hybrid DL model. The flood data are divided into a multivariate time series and used as the model input. Each input comprises nine variables, including information of the studied channel sensor and its predecessor and successor sensors in the channel network. Precision‐recall curve and F‐measure are used to identify the optimal set of model parameters. The optimal model with a weight of 1 and a critical threshold of 0.59 are obtained through 100 iterations based on examining different weights and thresholds. The test accuracy and F‐measure eventually reach 97.8% and 0.792, respectively. The model is then tested in predicting the 2019 Imelda Flood in Houston and the results show an excellent match with the empirical flood. The results show that the model enables accurate prediction of the spatial–temporal flood propagation and recession and provides emergency response officials with a predictive flood warning tool for prioritizing the flood response and resource allocation strategies.

In this study, we propose a contagion model as a simple and powerful mathematical approach for predicting the spatial spread and temporal evolution of the onset and recession of floodwaters in urban road networks. A network of urban roads resilient to flooding events is essential for the provision of public services and for emergency response. The spread of floodwaters in urban networks is a complex spatial–temporal phenomenon. This study presents a mathematical contagion model to describe the spatial–temporal spread and recession process of floodwaters in urban road networks. The evolution of floods within networks can be captured based on three macroscopic characteristics—flood propagation rate ( $$\beta$$β ), flood incubation rate ( $$\alpha$$α ), and recovery rate ( $$\mu$$μ )—in a system of ordinary differential equations analogous to the Susceptible-Exposed-Infected-Recovered (SEIR) model. We integrated the flood contagion model with the network percolation process in which the probability of flooding of a road segment depends on the degree to which the nearby road segments are flooded. The application of the proposed model is verified using high-resolution historical data of road flooding in Harris County during Hurricane Harvey in 2017. The results show that the model can monitor and predict the fraction of flooded roads over time. Additionally, the proposed model can achieve 90% precision and recall for the spatial spread of the flooded roads at the majority of tested time intervals. The findings suggest that the proposed mathematical contagion model offers great potential to support emergency managers, public officials, citizens, first responders, and other decision-makers for flood forecast in road networks.

Damages in critical infrastructure occur abruptly, and disruptions evolve with time dynamically. Understanding the situation of critical infrastructure disruptions is essential to effective disaster response and recovery of communities. Although the potential of social media data for situation awareness during disasters has been investigated in recent studies, the application of social sensing in detecting disruptions and analyzing evolutions of the situation about critical infrastructure is limited. To address this limitation, this study developed a graph‐based method for detecting credible situation information related to infrastructure disruptions in disasters. The proposed method was composed of data filtering, burst time‐frame detection, content similarity calculation, graph analysis, and situation evolution analysis. The application of the proposed method was demonstrated in a case study of Hurricane Harvey in 2017 in Houston. The findings highlighted the capability of the proposed method in detecting credible situational information and capturing the temporal and spatial patterns of critical infrastructure events that occurred in Harvey, including disruptive events and their adverse impacts on communities. The proposed methodology can improve the ability of community members, volunteer responders, and decision makers to detect and respond to infrastructure disruptions in disasters.