Abstract Disasters vary greatly in their nature, severity and underlying distribution. A streamlined model is crucial for assessing the impact of unexpected disasters. Previous methods rely on training with historical disaster data to evaluate the damage caused. However, in practice, this approach rarely achieves acceptable performance due to domain shift. Therefore, existing models need to be adapted to the emergent disaster quickly. A promising way to achieve this goal is through unsupervised domain adaptation (UDA). To this end, many advancements have been made toward better transferability of the model, including the Domain Adversarial Neural Network (DANN), which utilizes adversarial training to attain a domain-invariant feature extractor. The Adversarial sliced Wasserstein Domain Adaptation Network (AWDAN) further improves on DANN by using sliced Wasserstein distance as a measure between the features extracted from the source and target domains. Inspired by these advancements, we explore the utility of UDA approaches in the disaster response domain. Specifically, we perform extensive experiments on real-world images collected from Twitter during four major disasters. We train a total of 216 models to benchmark six methods across all possible source–target domain combinations. We improve the performance of the previous state-of-the-art DANN-based method for rapid damage assessment by enhancing it with a deeper backbone architecture to learn better feature representations. Furthermore, we adopt AWDAN to more effectively mitigate the distribution shift in data obtained from different disaster events. Experimental results demonstrate that the proposed approach achieves statistically significant performance gains, with up to 11.4% improvement in F1-score and 8.9% improvement in accuracy over the source-only model, consistently outperforming several state-of-the-art domain adaptation frameworks, including DANN, CORAL, MMD, and CDAN.

Intelligent transportation systems are a key component in smart cities, and the estimation and prediction of the spatiotemporal traffic state is critical to capture the dynamics of traffic congestion, i.e., its generation, propagation and mitigation, in order to increase operational efficiency and improve livability within smart cities. And while spatiotemporal data related to traffic is becoming common place due to the wide availability of cheap sensors and the rapid deployment of IoT platforms, the data still suffer some challenges related to sparsity, incompleteness, and noise which makes the traffic analytics difficult. In this article, we investigate the problem of missing data or noisy information in the context of real-time monitoring and forecasting of traffic congestion for road networks in a city. The road network is represented as a directed graph in which nodes are junctions (intersections) and edges are road segments. We assume that the city has deployed high-fidelity sensors for speed reading in a subset of edges; and the objective is to infer the speed readings for the remaining edges in the network; and to estimate the missing values in the segments for which sensors have stopped generating data due to technical problems (e.g., battery, network, etc.). We propose a tensor representation for the series of road network snapshots, and develop a regularized factorization method to estimate the missing values, while learning the latent factors of the network. The regularizer, which incorporates spatial properties of the road network, improves the quality of the results. The learned factors, with a graph-based temporal dependency, are then used in an autoregressive algorithm to predict the future state of the road network with a large horizon. Extensive numerical experiments with real traffic data from the cities of Doha (Qatar) and Aarhus (Denmark) demonstrate that the proposed approach is appropriate for imputing the missing data and predicting the traffic state. It is accurate and efficient and can easily be applied to other traffic datasets.