Rapid Situational Awareness Research Articles

Population displacement after earthquakes: benchmarking predictions based on housing damage

In the aftermath of an earthquake, the number of residents whose housing was destroyed is often used to approximate the number of people displaced (i.e., rendered homeless) after the event. While this metric can provide rapid situational awareness regarding potential long-term housing needs, more recent research highlights the importance of additional factors beyond housing damage within the scope of household displacement and return (e.g., utility disruption, tenure, place attachment). This study benchmarks population displacement estimates using this simplified conventional approach (i.e., only considering housing destruction) through three scenario models for recent earthquakes in Haiti, Japan, and Nepal. These model predictions are compared with officially reported values and alternate mobile location data-based estimates from the literature. The results highlight the promise of scenario models to realistically estimate population displacement and potential long-term housing needs after earthquakes, but also highlight a large range of uncertainty in the predicted values. Furthermore, purely basing displacement estimates on housing damage offers no view on how the displaced population counts vary with time as compared to more comprehensive models that include other factors influencing population return or alternative approaches, such as using mobile location data.

딥러닝을 이용한 도심지침수 위기관리방안에 대한 연구

Recently, climate change has caused a lot of damage worldwide. Existing rainfall patterns on the Korean Peninsula could predict long-term rainfall patterns and periods, but changes in rainfall patterns due to climate change made crisis response measures useless. Due to heavy rain in August 2022, 10 local governments, including Seoul, Gyeonggi, Gangwon, and Chungnam, were declared as special disaster areas for the first time. As the impermeable area increases due to urbanization and the use of the underground space of buildings increases, the design capacity of sewage pipes is often exceeded, and the scope is local but the damage scale is increasing. Urban floods require rapid situational awareness and crisis response. To this end, it is necessary to establish a system that can monitor the flood situation at all times using CCTV distributed across the country through AI-based image analysis technology, and a new type of urban flood monitoring technology that analyzes and links it based on standardized IoT unstructured data such as real-time measurement sensor data and CCTV images is required.

Learnings from rapid response efforts to remotely detect landslides triggered by the August 2021 Nippes earthquake and Tropical Storm Grace in Haiti

AbstractOn August 14, 2021, a Mw 7.2 earthquake struck the Tiburon Peninsula of western Haiti triggering thousands of landslides. Three days after the earthquake on August 17, 2021, Tropical Storm Grace crossed shallow waters offshore of southern Haiti triggering more landslides worsening the situation. In the aftermath of these events, several organizations with disaster response capabilities or programs activated to provide information on the location of landslides to first responders on the ground. Utilizing remote sensing to support rapid response, one organization manually mapped initiation point of landslides and three automatically detected landslides. The 2021 Haiti event also provided a unique opportunity to test different automated landslide detection methods that utilized both SAR and optical data in a rapid response scenario where rapid situational awareness was critical. As the methods used are highly replicable, the main goal of this study is to summarize the landslide rapid response products released by the organizations, detection methods, quantify accuracy and provide guidelines on how some of the shortcomings encountered in this effort might be addressed in the future. To support this validation, a manually mapped polygon-based landslide inventory covering the entire affected area was created and is also released through this effort.

Towards Automated Situational Awareness Reporting for Disaster Management—A Case Study

Disasters do not follow a predictable timetable. Rapid situational awareness is essential for disaster management. People witnessing a disaster in the same area and beyond often use social media to report, inform, summarize, update, or warn each other. These warnings and recommendations are faster than traditional news and mainstream media. However, due to the massive amount of raw and unfiltered information, the data cannot be managed by humans in time. Automated situational awareness reporting could significantly and sustainably improve disaster management and save lives by quickly filtering, detecting, and summarizing important information. In this work, we aim to provide a novel approach towards automated situational awareness reporting using microblogging data through event detection and summarization. Therefore, we combine an event detection algorithm with different summarization libraries. We test the proposed approach against data from the Russo-Ukrainian war to evaluate its real-time capabilities and determine how many of the events that occurred could be highlighted. The results reveal that the proposed approach can outline significant events. Further research can be carried out to improve short-text summarization and filtering.

Distribution Network Security Situation Awareness Method Based on the Distribution Network Topology Layered Model

Distribution network security situation awareness refers to the process of perception, understanding, and state projection of systems, elements, and environmental factors within a certain space-time volume. Security situation awareness is an important part of the security assessment of the distribution network. In response to the rapid and accurate distribution network security situation awareness requirements, this paper proposes a distribution network security situation awareness method based the distribution network topology layered model. First, a hierarchical model of the distribution network topology under the premise of optimizing the location of the synchronous phasor measuring device is constructed. This model can quickly capture the system security situation elements. Then, a support vector data description algorithm fused with information entropy is used to realize the identification and understanding of abnormal information in the security situation elements of the distribution network. The long- and short-term memory network is then used to predict the operation trend of the distribution network under normal operation and fault disturbance. Finally, a simulation is established, and the IEEE-33 distribution network model is used to verify the effectiveness of the method proposed in this paper. The results show that the method of this paper improves the speed and accuracy of obtaining the security situation elements of the distribution network, shortens the identification time of the security situation elements, and realizes the security situation awareness of the nodes of the distribution network.

Study on Cyber Common Operational Picture Framework for Cyber Situational Awareness

The remarkable development of the Internet has made our lives very convenient, such as through the ability to instantaneously transmit individual pictures. As a result, cyber-attacks are also being developed and increasing, and the computer/mobile devices we use can become infected with viruses in an instant. Rapid cyber situational awareness is essential to prepare for such cyber-attacks. Accelerating cyber situational awareness requires Cyber Common Operational Pictures, which integrate and contextualize numerous data streams and data points. Therefore, we propose a Cyber Common Operational Pictures framework and criteria for rapid cyber situation awareness. First, the system reaction speed based on the user’s request and the standard for easily recognizing the object shown on the screen are presented. Second, standards and frameworks for five types of visualization screens that can directly recognize and respond to cyber-attacks are presented. Third, we show how a system was constructed based on the proposed framework, as well as the results of an experiment on the response time of each visualization screen. As a result of the experiment, the response speed of the 5 visualization screens was about 0.11 s on average for inquiry (simple) and 1.07 s on average for inquiry (complex). This is consistent with the typical response times of the studies investigated in this paper. If CyCOP is developed in compliance with the framework items (UI, object symbol, object size, response speed) presented in this paper, rapid situational awareness is possible. This research can be used in cyber-attack and defense training in the military field. In the private sector, it can be used in cyber and network control.

Rapid Public Information and Situational Awareness After the November 26, 2019, Albania Earthquake: Lessons Learned From the LastQuake System

Rapid Public Information and Situational Awareness After the November 26, 2019, Albania Earthquake: Lessons Learned From the LastQuake System

Investigation of social media representation bias in disasters: Towards a systematic framework

Due to its real-time and human-centered nature, social media posts have been widely applied to provide rapid situational awareness in disasters, particularly from a human-centered perspective. To generalize social media-derived insights on a population, a pre-requisite is that the employed social media posts are capable of revealing the information of disaster-affected population without bias. Such wide application and pre-requisite underscore the importance of investigating social media bias for deriving reliable decision support insights in disaster management. However, a systematic framework that streamlines the investigation of social media representation bias is still missing. To address the research gap, we propose a framework comprising (1) the setting of an appropriate representation bias benchmark; (2) the modeling of the sampling uncertainty of social media-derived insights; and (3) the derivation and quantification of representation bias distribution across races/ethnicities. Public transit amid COVID-19 in the United States is studied for illustration purposes. Nation-level results show that the White group is over-represented, the Asian group is slightly over-represented, and the Hispanic and Black groups are under-represented throughout the studied period. The level of social media representation bias varies across the states of California, New York, Texas, and Florida, and it is inversely correlated with population ratios. Such findings are beneficial for decision-makers to use social media to derive reliable insights into disaster-affected population, thereby making informed operational decisions accordingly.

인공지능을 활용한 디지털 트윈 기반 ESS 최적 운영 계획 모델 수립에 관한 연구

Recently, due to the digitalization of power systems, the convergence technology of power systems and ICT has become important, and with the development of operational technologies, the importance of intelligent energy management is increasing. The importance of energy management through intelligent operating technology is emerging. In this paper, a digital twin model simulated by empirical simulation was constructed using the empirical ESS measurement data information collected from the power system. An optimal operation plan model for ESS was established by simulating the state and environment of the system in the virtual space of the digital twin similar to the actual system. It aims to improve the stable operation and efficiency of ESS through rapid situational awareness and correct decision-making by applying a data-based machine learning model rather than an existing optimization-based operation model.

Transient Stability Margin Prediction Under the Concept of Security Region of Power Systems Based on the Long Short-Term Memory Network and Attention Mechanism

Transient stability prediction under the concept of security region of a power system can be used to identify potential unstable states of the system and ensure its secure operation. In this paper, we propose a method to predict the transient stability margin under the concept of security region based on the long short-term memory (LSTM) network and attention mechanism (AM). This method can ensure rapid and accurate situational awareness of operators in terms of transient stability. The LSTM layer reduces the dimension of the historical steady-state power flow data, and the temporal characteristics are extracted from the data. Subsequently, the AM is introduced to differentiate the characteristics and historical transient stability margin data for the models to identify the information associated with stability. Finally, the LSTM and fully connected layers are used to predict the transient stability margin, providing up-to-date situational awareness of the power system to operators. We performed simulations on the IEEE 39-bus system, and the simulated results validated the effectiveness of the proposed method.

Key technologies and combat pattern analysis of autonomous flight sonobuoy

Launched from a sonobuoy tube and capable of autonomous flight, the autonomous sonobuoy frees the traditional sonobuoy from dependence on costly aerial delivery platforms. It can be installed on various small and medium-sized surface ships and unmanned vehicles to support the operational needs of long-distance and rapid situation awareness regarding underwater battlefields. By introducing the development of in-tube launch and sonobuoy technology, this paper proposes the design method of the autonomous sonobuoy and summarizes the key technologies of autonomous sonobuoy cluster operations, including cluster control, intelligent decision-making, network detection and so on. Furthermore, the battle modes of autonomous sonobuoy clusters in wide-area cooperative detection, precise location and effect evaluation are analyzed. The results can provide references for the demand analysis, design and application of autonomous sonobuoy clusters.

Exploring human-nature interactions in national parks with social media photographs and computer vision.

Understanding the activities and preferences of visitors is crucial for managing protected areas and planning conservation strategies. Conservation culturomics promotes the use of user-generated online content in conservation science. Geotagged social media content is a unique source of in situ information on human presence and activities in nature. Photographs posted on social media platforms are a promising source of information, but analyzing large volumes of photographs manually remains laborious. We examined the application of state-of-the-art computer-vision methods to studying human-nature interactions. We used semantic clustering, scene classification, and object detection to automatically analyze photographs taken in Finnish national parks by domestic and international visitors. Our results showed that human-nature interactions can be extracted from user-generated photographs with computer vision. The different methods complemented each other by revealing broad visual themes related to level of the data set, landscape photogeneity, and human activities. Geotagged photographs revealed distinct regional profiles for national parks (e.g., preferences in landscapes and activities), which are potentially useful in park management. Photographic content differed between domestic and international visitors, which indicates differences in activities and preferences. Information extracted automatically from photographs can help identify preferences among diverse visitor groups, which can be used to create profiles of national parks for conservation marketing and to support conservation strategies that rely on public acceptance. The application of computer-vision methods to automatic content analysis of photographs should be explored further in conservation culturomics, particularly in combination with rich metadata available on social media platforms.

Rapid Public Information and Situational Awareness After the November 26, 2019, Albania Earthquake: Lessons Learned From the LastQuake System

The use of LastQuake information system, its app, the associated Twitter account and to a lesser extent the EMSC’s websites have been analysed for the 7-days following the Nov. 26, 2019 M6.4 Albania destructive earthquake to evaluate what can be improved and how crowdsourcing of information and monitoring of both use and absence of use of the app can contribute to rapid situational awareness. The mainshock and its numerous felt aftershocks triggered a strong public desire for information which in turn led to rapid and massive adoption of the LastQuake app by up to 5% of the country’s population. The constant flow of new app users created a stress test of the app’s crowdsourcing features and led to errors in the association of felt reports with their appropriate earthquake. However these errors had no identifiable impact supporting the conclusion that the curation mechanisms currently in place are efficient. The rapid succession of felt aftershocks contributed to these errors by making information related to the mainshock difficult to access within hours of its occurrence, especially for new users who were not attuned to the app. This revealed that prioritization of information within the app layout is lacking and is an important requirement during these kinds of events. LastQuake has been shown to be a powerful tool for rapid situational awareness. The possibility of damage was detected within 8 min of the mainshock earthquake by a lack of LastQuake app activity close to the epicenter. This possibility was then gradually strengthened as new data became available and was finally confirmed by the reception of the first geo-located pictures of structural damage and building collapse within 60-70 min. Direct exchanges on Twitter were appreciated by eyewitnesses and were reported to reduce their anxiety. Questions mainly focused on the possible evolution of the seismicity. Attempts to debunk prediction claims were difficult and we report on how this could be eased and possibly made more efficient by the use of a clear concise, pre-prepared statement in the local language explaining the state of scientific knowledge and the difference between prediction, early warning or forecasts.

A Hybrid Machine Learning Pipeline for Automated Mapping of Events and Locations From Social Media in Disasters

The objective of this study is to propose and test a hybrid machine learning pipeline to uncover the unfolding of disaster events corresponding to different locations from social media posts during disasters. Effective disaster response and recovery require a comprehensive understanding of disaster situations, i.e., unfolding of disaster events and geographic distribution of the disruptions. Existing studies have employed machine learning methods to conduct coarse-grained event detection and analyze the geographical location information from geotagged social media data. However, only a very small fraction of the entire set of social media data includes geotagged information, which may not directly correspond to events described in the content of posts. In addition, the coarse-grained information detected by existing approaches is token-based, which does not provide sufficient information for situation awareness. Hence, the detection of location and finer-grained event information could significantly improve the utility, credibility, and interpretability of social media data for situation awareness. To address these limitations, this study proposed a hybrid machine learning pipeline that makes use of all relevant tweets to uncover the evolution of disaster events across different locations. The pipeline integrates Named Entity Recognition for detecting locations mentioned in the posts, location fusion approach to extract coordinates of the locations and remove noise information, fine-tuned BERT model for classifying posts with humanitarian categories, and graph-based clustering to identify credible situational information. The application of the study is demonstrated using the data set collected from Twitter during the 2017 Hurricane Harvey in Houston. The results show the capability of the proposed hybrid pipeline for automated mapping of events across time and space from social media posts with considerable accuracy. The findings also suggest that the potential for forensic analysis of disasters using mapped events and their evolution, and based on the variation of social media attention to different locations in disasters. Hence, this method could provide a useful tool to support emergency managers, public officials, residents, first responders, and other stakeholders in rapid situation awareness across time and space.

Interactive Learning for Identifying Relevant Tweets to Support Real-time Situational Awareness.

Various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. However, due to the high noise in the deluge of data, effectively determining semantically relevant information can be difficult, further complicated by the changing definition of relevancy by each end user for different events. The majority of existing methods for short text relevance classification fail to incorporate users' knowledge into the classification process. Existing methods that incorporate interactive user feedback focus on historical datasets. Therefore, classifiers cannot be interactively retrained for specific events or user-dependent needs in real-time. This limits real-time situational awareness, as streaming data that is incorrectly classified cannot be corrected immediately, permitting the possibility for important incoming data to be incorrectly classified as well. We present a novel interactive learning framework to improve the classification process in which the user iteratively corrects the relevancy of tweets in real-time to train the classification model on-the-fly for immediate predictive improvements. We computationally evaluate our classification model adapted to learn at interactive rates. Our results show that our approach outperforms state-of-the-art machine learning models. In addition, we integrate our framework with the extended Social Media Analytics and Reporting Toolkit (SMART) 2.0 system, allowing the use of our interactive learning framework within a visual analytics system tailored for real-time situational awareness. To demonstrate our framework's effectiveness, we provide domain expert feedback from first responders who used the extended SMART 2.0 system.

MANAGING HUMAN INDUCED CRISIS WITH BIG DATA INFRASTRUCTURE

This paper presents human induced crisis management system using big data infrastructure. This approach was motivated by the already established fact that human induced crisis are characterized by velocity, variety and volume. This paper therefore employed Hadoop big data stack, web technology to design and implement a crisis management model. The resulting system comprises analytical engine, custom website and a desktop application called “Channel”. The Hadoop distributed file system was used for data storage in the analytical engine, crisis data were collected via Twitter API and web service generated by the project website using Apache Flume and Channel respectively. Apache Hive was used to analyse the collected data and the analysed result were posted back to custom website using Channel. The system was evaluated using Mean Opinion Score (MOS) to test for its applicability, usability and reliability. The perceived applicability rating of 74%, usability rating of 73% and reliability rating of 57% were obtained. The resulting system provides insight into crisis situation; promote rapid situational awareness, aid policy formulation and monitoring.

No more pediatric code blues on the floor: evolution of pediatric rapid response teams and situational awareness plans.

Reducing or eliminating code blues that occur on the inpatient, noncritical care units of children's hospitals is a challenging yet achievable goal. The mechanism to accomplish this involves several levels of effort. The implementation of effective pediatric rapid response teams is a well identified part of the process. Rapid response teams can allow for appropriate clinical interventions for deteriorating patients and may ultimately result in a reduction in hospital-wide mortality as well as efficient transfer to the pediatric intensive care unit (PICU) when necessary. The timely deployment of rapid response teams is dependent upon the appropriate recognition of patients at risk for deterioration. This recognition can be optimized by relying on assessments as simple as utilization of parental intuition to those as complex as big data models which utilize multiple predictor variables extracted from the electronic medical record. Ultimately, the goal to proactively identify patients at risk of deterioration may allow for prevention of clinical decline via appropriate and timely interventions, and if unsuccessful at that level, may allow for improved outcomes via optimized resuscitation care in the PICU.

Surveillance of a Synthetic Cannabinoid Overdose Outbreak using Syndromic & EMS Data

Objective: The aim of this project was to investigate anecdotal reports of an increase in synthetic cannabinoid (SynCan) overdoses in Lexington-Fayette County area of Kentucky, using rapid surveillance systems including emergency department (ED) syndromic surveillance (SyS) and emergency medical services (EMS) data.Introduction: In mid-2017, the Kentucky Injury Prevention and Research Center (a bonafide agent of Kentucky Department for Public Health-KDPH) was alerted by members of KDPH to anecdotal evidence of a possible increase of SynCan (primarily “Serenity”) overdoses. The situation presented an opportunity to demonstrate the capabilities of syndromic surveillance and emergency medical services (EMS) data systems to provide rapid situational awareness about SynCan overdoses.Methods: SynCan cases were identified based on EMS emergency runs with narratives including mentions of ‘serenity|K2|spice’ and occurred in the Lexington-Fayette County. In ED SyS, SynCan cases were identified for Lexington-Fayette County area ED visits with a chief complaints of ‘serenity|K2|spice’ or diagnosis code of T40.7X[1-4]A. The ICD code was included after analysis of diagnosis codes in positive cases from a chief complaint only query revealed T40.7X[1-4]A as a primary code assigned in these cases. Trends for Lexington-Fayette County area were compared to state-wide total to determine if the trend is unique or related to system-wide pattern changes. EMS and ED SyS trend results were compared for internal validity. EMS incident addresses were geocoded to point-level to enable more granular analysis of geospatial patterns over time for identification of hotspots/clustering.Results: ED SyS and EMS results demonstrated a clear temporal increase in SynCan overdoses beginning around March of 2017[Fig 1]. Further analysis indicated that this increase was most dramatically centered in the Lexington-Fayette County area [Fig 2]. The vast majority of those overdosing were males (SyS: 88.1%) with average age 37 compared to 11.9% and 36.0 for females, respectively. These demographics are similar to those reported by the New York City Department of Health and Mental Hygiene for a K2 outbreak in New York City in 20141. Kernel density mapping demonstrated a strong clustering in a specific area of downtown Lexington. Additionally, analysis of EMS data revealed that a large portion of these overdoses were being admitted for observational care and thus not being captured in SyS data (based on the primary hospital’s submission types).From a practical standpoint, the rapid surveillance results only took 1-2 days to complete and highlight the utility of these data systems in preparing rapid data products. The results of the analysis were shared with local and state health department authorities, including the local Emergency Medical Advisory Board. The geospatial analysis provided local authorities with information to enable precise targeting of public health and public safety messaging.Conclusions: By analyzing data from these systems, we were able to quickly identify the geographic areas and demographic groups that were most affected, and to describe trends in SynCan overdoses over time. As a result, we were able to provide highly-detailed data to local public health and public safety authorities to inform their response.

LastQuake: From rapid information to global seismic risk reduction

The European Mediterranean Seismological Centre (EMSC), one of the top global earthquake information centers, has been empirically developing a multichannel rapid information system comprising websites, a Twitter quakebot, and a smartphone app for global earthquake eyewitnesses. At the intersection between seismology, citizen science, and digital communication, its aim is twofold: to offer timely, appropriate information in regions where an earthquake is felt and to collect high numbers of eyewitnesses’ direct and indirect observations about the degree of shaking being felt and possible damage incurred. This, in turn, will improve rapid situation awareness and augment data at a relatively low cost. Engagement with eyewitnesses is based on the rapid provision of tremor detection (between few tens of seconds to a couple of minutes from when the earthquake strikes) which is derived from the analysis of indirect information, i.e., digital footprints of Internet and social media searches by eyewitnesses eager to find out the cause of the tremor. This detection generally precedes detection by seismic networks. Eyewitness’ behavior is comparable to real-time seismic sensors when using EMSC websites or LastQuake smartphone app. The hit times on our websites and launch times of our app closely follow seismic wave propagation. Crowdsourced data (felt reports, geo-located pictures, and open comments) is then fed back into the ongoing information product improvement and situation awareness which, in turn, attracts more eyewitnesses through a viral spread, thus creating a positive feedback loop. The use of visual communication for felt report collection, where traditional online questionnaires have been replaced by cartoons depicting different degrees of shaking and damage levels, has proven to be fast and efficient on a global scale with, on average, half of the felt reports being collected within 10 min. Following requests by Nepalese users after the devastating 2015 Gorkha, Nepal earthquake, the LastQuake app now includes timely geo-targeted safety checks to inform loved ones that one is safe and safety tips communicated using cartoons to describe behaviors to be encouraged or avoided after violent tremors. We argue that this simple and affordable system, based on standard Internet technologies and social media, can reduce anxiety by offering timely information and services to eyewitnesses and possibly contribute to immediate global seismic risk reduction by complementing well-established long-term strategies built around improving the seismic performance of the existing buildings by raising situation awareness and limiting potentially dangerous behaviors after violent ground shaking. Short abstractThe EMSC, one of the top global earthquake information centers, has been empirically developing a multichannel rapid information system comprising websites, a Twitter quakebot and a smartphone app for global earthquake eyewitnesses. At the intersection between seismology, citizen science, and digital communication, its aim is twofold: to offer timely, appropriate information in regions where an earthquake is felt and to collect high numbers of eyewitnesses’ direct and indirect observations to improve rapid situation awareness. Engagement with eyewitnesses is based on the rapid provision of tremor detection (between few tens of seconds to a couple of minutes) which is derived from the analysis of indirect information, i.e., Internet and social media searches by eyewitnesses eager to find out the cause of the tremor. Eyewitness’ behavior is comparable to real-time seismic sensors when using EMSC websites or LastQuake smartphone app. Crowdsourced data is then fed back into the ongoing information product improvement and situation awareness which, in turn, attracts more eyewitnesses through a viral spread. The use of visual communication for felt report collection has proven to be fast and efficient on a global scale with, on average, 50% of felt reports being collected within 10 min. The LastQuake app now includes timely geo-targeted safety checks and safety tips to describe behaviors to be encouraged or avoided after violent tremors. We argue that this simple,affordable system, based on Internet technologies and social media, can reduce anxiety by offering timely information to eyewitnesses and possibly contribute to immediate global seismic risk reduction.

Incident-Supporting Visual Cloud Computing Utilizing Software-Defined Networking

In the event of natural or man-made disasters, providing rapid situational awareness through video/image data collected at salient incident scenes is often critical to the first responders. However, computer vision techniques that can process the media-rich and data-intensive content obtained from civilian smartphones or surveillance cameras require large amounts of computational resources or ancillary data sources that may not be available at the geographical location of the incident. In this paper, we propose an incident-supporting visual cloud computing solution by defining a collection, computation, and consumption (3C) architecture supporting fog computing at the network edge close to the collection/consumption sites, which is coupled with cloud offloading to a core computation, utilizing software-defined networking (SDN). We evaluate our 3C architecture and algorithms using realistic virtual environment test beds. We also describe our insights in preparing the cloud provisioning and thin-client desktop fogs to handle the elasticity and user mobility demands in a theater-scale application. In addition, we demonstrate the use of SDN for on-demand compute offload with congestion-avoiding traffic steering to enhance remote user quality of experience in a regional-scale application. The optimization between fogs computing at the network edge with core cloud computing for managing visual analytics reduces latency, congestion, and increases throughput.