Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities最新文献

{"title":"Data-driven mobility models for COVID-19 simulation","authors":"John Pesavento, A. Chen, Rayan Yu, Joon-Seok Kim, H. Kavak, T. Anderson, Andreas Züfle","doi":"10.1145/3423455.3430305","DOIUrl":"https://doi.org/10.1145/3423455.3430305","url":null,"abstract":"Agent-based models (ABM) play a prominent role in guiding critical decision-making and supporting the development of effective policies for better urban resilience and response to the COVID-19 pandemic. However, many ABMs lack realistic representations of human mobility, a key process that leads to physical interaction and subsequent spread of disease. Therefore, we propose the application of Latent Dirichlet Allocation (LDA), a topic modeling technique, to foot-traffic data to develop a realistic model of human mobility in an ABM that simulates the spread of COVID-19. In our novel approach, LDA treats POIs as \"words\" and agent home census block groups (CBGs) as \"documents\" to extract \"topics\" of POIs that frequently appear together in CBG visits. These topics allow us to simulate agent mobility based on the LDA topic distribution of their home CBG. We compare the LDA based mobility model with competitor approaches including a naive mobility model that assumes visits to POIs are random. We find that the naive mobility model is unable to facilitate the spread of COVID-19 at all. Using the LDA informed mobility model, we simulate the spread of COVID-19 and test the effect of changes to the number of topics, various parameters, and public health interventions. By examining the simulated number of cases over time, we find that the number of topics does indeed impact disease spread dynamics, but only in terms of the outbreak's timing. Further analysis of simulation results is needed to better understand the impact of topics on simulated COVID-19 spread. This study contributes to strengthening human mobility representations in ABMs of disease spread.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128971419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing community-based intelligent systems for water infrastructure resilience","authors":"N. Venkatasubramanian, C. Davis, R. Eguchi","doi":"10.1145/3423455.3430318","DOIUrl":"https://doi.org/10.1145/3423455.3430318","url":null,"abstract":"In this paper, we discuss how data-driven approaches using emerging IoT and machine learning based analytics can revolutionize the resilience and efficiency of urban water systems. Key challenges in creating a next generation water infrastructure includes issues of how and where to place instruments to gather a wide variety of information useful for improving operational efficiencies and for damage detection after major disasters. We discuss how an understanding of deployed infrastructure in diverse geographies and the dynamics of interconnected systems can help design more effective placement of technology solutions. We showcase recent work illustrating how knowledge of network structures and their behavior can help to more effectively instrument and gather operational data and how AI-based approaches utilizing geospatial data more effectively can help to maintain real-time awareness of system states which allows decision makers to more effectively monitor and control their systems.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132959486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Constructing a digital city on a web-3D platform: simultaneous and consistent generation of metadata and tile data from a multi-source raw dataset","authors":"Toshikazu Seto, Y. Sekimoto, Kosuke Asahi, Takahiro Endo","doi":"10.1145/3423455.3430316","DOIUrl":"https://doi.org/10.1145/3423455.3430316","url":null,"abstract":"In this study, we develop a platform that can display approximately 20 types of data via a web browser to realize a digital twin of a wider area, including a detailed reading display of block units and individual three-dimensional point cloud data (point cloud) of a city. Using actual data, we examine if the data model and visualization design correspond with the zoom level. Owing to the comparative examination of the wide-area display performance and the map representation design in a JavaScript-based open-source library, we were able to develop a platform with light architecture and an easily customizable display. Furthermore, prototyping, based on Mapbox GL JS and Deck.GL, and the display of spatiotemporal flow layers, such as background maps, point cloud data in many places, dozens of layer display types, and the General Transit Feed Specification (GTFS) allowed for the seamless transition from the local government to the wide-area display in the prefecture unit in approximately 10-20 s. It is recommended that this digital smart city platform should be standardized by other local governments, especially in areas where higher-order data visualization is yet to advance. To display this digital city in a lightweight environment, we consider the digital data situation of local governments in Japan. It is necessary to define the visualized design for each zoom level according to the characteristics of the data. We then arranged the display model of each zoom level for 20 types of urban infrastructure data related to the digital smart city by referring to the style schema of the tile form. Through these tasks, we organized the commonality and optimization of data models and formats.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126471201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploiting points of interest for predictive policing","authors":"Luís Gustavo Coutinho do Rêgo, T. C. D. Silva, R. P. Magalhães, J. Macêdo, W. C. P. Silva","doi":"10.1145/3423455.3430319","DOIUrl":"https://doi.org/10.1145/3423455.3430319","url":null,"abstract":"High crime rates have become a public health problem in many important cities, according to World Health Organization. Many researchers have been developing algorithms to predict crime occurrences to tackle this problem. The smart cities' environment can provide us enough ubiquitous data, e.g., traffic flow, human mobility, and Points of Interest (POI) information, to feed those predictive policing algorithms and reflect city dynamics. POIs data provide essential information such as geographical location, category, customer reviews, and busy hours. Recent studies have shown that POI geographical locations are useful for predictive policing. In this paper, we aim at predicting crimes in a delimited region around the POIs of a city with new environmental features. We investigate the relevance of POIs location and the semantic and the temporal features from POIs data in our problem. We also propose and analyze different machine learning approaches to train prediction functions based on these features and conduct experiments on real crime data over multiple years. The experiments demonstrate that the popular time feature is more relevant than the historical information about the number of crimes around a POI, but both information is much less critical than the spatio-temporal information. This work is the first that studies the popular time feature extracted from POIs data and historical criminal information for predictive policing from the authors' knowledge.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126488059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seismic risk assessments of water pipelines: a case study for the city of los angeles Water system pipeline network","authors":"Yajie Lee, Zhenghui Hu, R. Eguchi, Jianping Hu, Alek Harounian","doi":"10.1145/3423455.3430304","DOIUrl":"https://doi.org/10.1145/3423455.3430304","url":null,"abstract":"Understanding the system-level risks of an infrastructure network is a critical step in developing a seismically-resilient network. In a complex seismic environment, numerous future earthquakes that have a broad range of magnitude, rupture location, and probability can affect a spatially distributed network and cause drastically different damage severity and service interruption time. Characterizing system-level risks involves the assessments of system damage potentials from all possible future earthquakes probabilistically. This paper shows a case study where system-level damage potentials for the City of Los Angeles water pipeline network were assessed using a stochastic method. The study considers both the distribution of earthquake-induced shaking and ground deformations, and the locations of the pipe network within the areas of varying shaking and ground deformation. System-level damages, including repair costs and repair time, were established at various target probability levels.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116833379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reducing and linking spatio-temporal datasets with kD-STR","authors":"L. Steadman, N. Griffiths, S. Jarvis, M. Bell, Shaun Helman, Caroline Wallbank","doi":"10.1145/3423455.3430317","DOIUrl":"https://doi.org/10.1145/3423455.3430317","url":null,"abstract":"When linking spatio-temporal datasets, the kD-STR algorithm can be used to reduce the datasets and speed up the linking process. However, kD-STR can sacrifice accuracy in the linked dataset whilst retaining unnecessary information. To overcome this, we propose a preprocessing step that removes unnecessary information and an alternative heuristic for kD-STR that prioritises accuracy in the linked output. These are evaluated in a case study linking a road condition dataset with air temperature, rainfall and road traffic data. In this case study, we found the alternative heuristic achieved a 19% improvement in mean error for the linked air temperature features and an 18% reduction in storage used for the rainfall dataset compared to the original kD-STR heuristic. The results in this paper support our hypothesis that, at worse, our alternative heuristic will yield a similar error and storage overhead for linking scenarios as the original kD-STR heuristic. However, in some cases it can give a reduction that is more accurate when linking the datasets whilst using less storage than the original kD-STR algorithm.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117286514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-supported citizen science to monitor high-tide flooding in Newport Beach, California","authors":"Behzad Golparvar, Ruoqian Wang","doi":"10.1145/3423455.3430315","DOIUrl":"https://doi.org/10.1145/3423455.3430315","url":null,"abstract":"Monitoring High-tide Flooding (HTF) is challenging because HTF usually spreads widely and forms localized water accumulations depending on the natural processes and infrastructure. Stationary monitoring systems and satellite imaging have their certain limitations. To date, citizen science is considered as the most promising means to monitor HTF, which provides wide and continuous coverage of the community and real-time first-hand witness of the flooding event. Here, we present a flexible Artificial Intelligence (AI) -supported citizen science platform for HTF monitoring. Flood extent is identified through standard photogrammetry algorithms and a Computer vision technique called monoplotting, and water depth can be estimated using reference objects. In this paper, monoplotting is employed to establish a correlation between photos and the corresponding digital elevation model (DEM) data, allowing to map the flood extent and water depth to the DEM map to minimize the data uncertainty and enhance the data credibility, resolution, and overall value.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132097935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Green infrastructures and their impact on resilience: spatial interactions in centralized sewer systems","authors":"Mayra Rodríguez, G. Fu, D. Butler","doi":"10.1145/3423455.3430302","DOIUrl":"https://doi.org/10.1145/3423455.3430302","url":null,"abstract":"Resilience in urban drainage infrastructure management has gained traction in the last few years, where systems need to adapt and recover from failure in face of deep uncertain threats. Green infrastructures, on-site nature-based stormwater strategies, are a promising concept that has proven to be effective in increasing the overall resilience performance in sewer systems. However, the improvement is not always significant or guaranteed. There is a lack of understanding of the local effects of these infrastructures and the spatial components of the impact on resilience in the network. In this work, the spatial interactions between GI placement and improvements in the centralized sewer networks resilience were studied, whilst considering a wide range of design storms. Resilience is assessed using two metrics: flood volume and flood duration. The scenarios simulated were baseline scenarios with no green infrastructure for each rainfall (scenarios type 1) and a placement scheme using critical component analysis (scenarios type 2). The spatial interactions were analysed through three main points, the magnitude of the impact, the number of affected nodes and the location of the impact in the network. This analysis was applied in a case-study in the United Kingdom. Regarding the magnitude of the impact, even though at a system level the impact is not high, at a node level the impact can be significant. Also, the impact is higher in shorter duration and lower return period storms. Regarding the number of affected nodes, most of the nodes remain unchanged. When all the scenarios are considered, there are as many nodes with an increase, as there are with a decrease in flooding volume and duration. Regarding the location of the impact, the nearest nodes to the outlet show the highest reduction in flood volume and flood duration. Subcatchments upstream the network and with highest areas seem to be the most impactful in the flood volume change. For flood duration, the subcatchments with smaller areas and generally in a middle region in the network cause the highest changes. This study is a first approximation to understand spatial considerations regarding the impact on resilience based on different green infrastructure location in the network.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115641243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterizing the spread of COVID-19 from human mobility patterns and SocioDemographic indicators","authors":"Avipsa Roy, B. Kar","doi":"10.1145/3423455.3430303","DOIUrl":"https://doi.org/10.1145/3423455.3430303","url":null,"abstract":"Mobility is an indicator of human movement through space and time. With the increasing availability of geolocated data (from GPS, accelerometers, etc.), it is now possible to examine individual as well as group human mobility patterns. Human mobility is influenced by both intrinsic (i.e. personal motivations) and extrinsic (i.e., events like natural hazards or a pandemic like the COVID-19) factors. However, the intricate relationships between human mobility patterns and sociodemographic characteristics in the context of a pandemic are yet to be fully explored. Our goal is to overcome this gap by using human mobility data at the census block group level from mobile phones and combining those with social vulnerability indicators to examine the overall spread of COVID-19 at local spatial scales. We used 585,878 weekly visits to 37,871 points of interests (POIs) from Safegraph to quantify mobility indices and social distancing metrics in 2,820 census block groups in the city of Los Angeles (LA) - before and during lockdown as well as during the phase1 and phase 2 reopening. Finally, using supervised machine learning algorithms, we classified the census block groups in LA into High, Medium and Low categories that represented the vulnerability of these block groups based on the cumulative number of occurrences of COVID-19 cases till July 24, 2020. Our results indicate that the tree-based classifiers performed well in comparison to the Support Vector Machines and Multinomial Logit models. Gradient Boosting had the highest classification accuracy of 97.4% COVID-19 with an AUC score of 0.987. The block groups with high COVID-19 cases also had a high concentration of socially vulnerable populations, high human mobility index and a low social distancing index.","PeriodicalId":320377,"journal":{"name":"Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Advances in Resilient and Intelligent Cities","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115117791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}