Huge spatio-temporal data (e.g., traffic flow, human mobility, and geographical data) are generated in modern cities. Accurately forecasting over spatio-temporal data enables many essential applications in intelligent cities, such as traffic management, public safety, and economy. To improve the ease of use, we propose an Enhanced Automated machine learning library for Spatio-Temporal forecasting, entitled EAST. In EAST, we mainly reconstruct three types of automated machine learning methods, namely, AutoSTPoint, AutoSTGrid, and AutoSTGraph for spatio-temporal point (STPoint) forecasting, spatio-temporal grid (STGrid) forecasting, and spatiotemporal graph(STGraph) forecasting, respectively. We adapt structureaware algorithms using neural architecture search methods. The search space is elaborately designed according to the structures and characteristics of spatio-temporal data. We implement EAST with the popular deep learning frameworks. Finally, we conduct experiments on real-world datasets to demonstrate the effectiveness and superiority of our EAST.

With the unprecedented development of industrialization and urbanization, many hazardous chemicals have become an indispensable part of our daily life. They are produced, transported, and consumed in modern cities every day, which breeds many unknown hazardous chemicals-related locations (HCLs) that are out of the supervision of management departments and accompanying huge threats to urban safety. How to recognize these unknown HCLs and identify their risk levels is an essential task for urban hazardous chemicals management. To accomplish this task, in this work, we propose a system named as CityShield to discover hidden HCLs and classify their risk levels based on trajectories of hazardous chemicals transportation vehicles. The CityShield system consists of three components. The first component is Data Pre-processing, which filters noises in raw trajectories and probes stable transportation vehicles’ stay points from massive uncertain GPS points. The second is HCL Recognition, which adopts the proposed HCL-Rec algorithm to cluster stay points into polygonal HCLs, and avoids the improper location merging problem caused by the skewed spatial distribution of HCLs. The third component is HCL Classification, which introduces the HCL relation graph as auxiliary information to overcome the label scarcity problem of HCLs. It adopts a selfsupervised method consisting of four pre-training tasks to learn high-quality representations for HCLs from the graph, which are finally used to classify the categories and risk levels of HCLs. The CityShield system has been deployed in Nantong, an important hazardous chemicals import and export city in China. Experiments and case studies on two large-scale real-world datasets collected from Nantong demonstrated the effectiveness of the proposed system. In real-world applications, the CityShield system discovered 173 high-risk unknown HCLs for the Nantong government, and successfully moved the hazardous chemicals management of Nantong to the prevention rather than emergency response side.

WWW 2021

[ORAL] KDD 2020, Research Track (acceptance rate: 16.8%)

[ORAL] KDD 2019, Research Track (acceptance rate: 14.2%)

We proposed a deep-learning-based approach, called ST-ResNet, to collectively forecast the inflow and outflow of crowds in each and every region of a city.