.
Dr. Zhenlong Li gave a colloquium talk on “Geospatial Big Data Analytics with High Performance Computing”at the Department of Geography & Earth Sciences, University of North Carolina Charlotte.
Join us for a conversation with Distinguished Emeritus Professor David Cowen and campus GIS practitioners on the use of geospatial technologies in teaching and research. To be followed by a Mapathon and GIS poster displays.
When: November 14, 2018; Where: Hollings Program Room, Thomas Cooper Library, USC


GeoAI and Deep Learning Symposium: Big data and GeoAI for natural hazards
Recently, we have unfortunately witnessed a series of deadly hurricane events (e.g., Harvey, and Florence) and Northern California wildfires. Such events claim many lives, cause billions of dollars of damage to properties, and severely impact the environment. When a natural hazard occurs, managers and responders need timely and accurate information on damages and resources to make effective response decisions and improve management strategies. This information is referred to as “Situational Awareness” (SA), i.e., an individually as well as socially cognitive state of understanding “the big picture” during critical situations. Fortunately, the popularity and advancement of social and physical sensor networks offer various real-time big data streams for establishing SA. For example, sharing information such as texts, images, and videos through social media platforms enables all citizens to become part of a large sensor network and a homegrown disaster response team. The use of Unmanned Aerial Vehicle (UAVs) images is offering increasing opportunities in disaster-related situations. However, such massive and rapidly changing data streams present new grand challenges to mine actionable data and extract critical validated information for various disaster management activities.
This session explores and captures the innovative machine learning and data mining algorithms, techniques and approaches to generate various useful information and products (e.g., hazard maps), which in turn can assist in disaster management during a natural hazard. Topics of particular interest are, but are not restricted to:
1. Mining and extracting actionable information for rapid emergency response and relief coordination
2. Integrating data mining (machines) and crowdsourcing (human) to support decision-making
3. Topic modeling and event detection
4. Physical infrastructure (e.g., roads, bridges and buildings) feature extraction with deep learning
5. Damage assessment using very high-resolution images or/and social media data
6. Coding/classifying text messages during a natural hazard
7. Identifying or/and matching the needs of people in impacted communities
8. Spatiotemporal mining of social media data to gain geographic situational awareness during a disaster
9. Mining, mapping and visualizing public’s behaviors, opinions or sentiments towards a disaster event
10. Innovative approaches to synthesizing and mining multi-sourced social and physical sensing data for disaster management
Qunying Huang, qhuang46@wisc.edu;
Zhenlong Li, zhenlong@sc.edu;
Xinyue Ye, xinyue.ye@njit.edu
American Association of Geographers’ Annual Meeting, April 3-7, 2019, Washington, DC
Aims and Scope:
- Multi-scale modeling of human mobility
- Urban disaster and emergency
- Indoors GIS and smart buildings
- CyberGIS analytics for urban big data
- Spatial theories of smart cities
- Urban safety, security, and privacy
- Transportation and mobility data analysis
- Urban data fusion
- Urban data mining
- Xinyue Ye, College of Computing, New Jersey Institute of Technology (xye@njit.edu)
- Bandana Kar, Urban Dynamics Institute, Oak Ridge National Laboratory (karb@ornl.gov)
- Shaowen Wang, Department of Geography & Geographic Information Science, University of Illinois at Urbana-Champaign (shaowen@illinois.edu)
- Zhenlong Li, Department of Geography, University of South Carolina (zhenlong@sc.edu)
Dr. Zhenlong Li gave a presentation “Social Sensing and Big Data Computing for Disaster Management: What can social media tell us about Hurricane evacuation?” at the New Generation GIS workshop. The workshop was organized by the NSF Spatiotemporal Innovation Center (STC) and hosted by Harvard University Center for Geographical Analyses on Oct 11, 2018.
More about the workshop: https://cga-download.hmdc.harvard.edu/publish_web/website_files/PDF_MISC/NGIS-newsletter-20181031.pdf
- Geo-cyberinfrastructure integrating spatiotemporal principles and advanced computational technologies (e.g., high-performance computing, cloud computing, and deep learning/AI).
- New computing and programming frameworks and architecture or parallel computing algorithms for geospatial applications.
- New geospatial data management strategies and data storage models coupled with high-performance computing for efficient data query, retrieval, and processing (e.g. new spatiotemporal indexing mechanisms).
- New computing methods considering spatiotemporal collocation (locations and relationships) of users, data, and computing resources.
- Geospatial big data processing, mining and visualization methods using high-performance computing and artificial intelligence.
- Integrating scientific workflows in cloud computing and/or high performance computing environment.
- Any other research, development, education, and visions related to geospatial big data computing.
- Zhenlong Li, Department of Geography, University of South Carolina, US. zhenlong@sc.edu
- Qunying Huang, Department of Geography, University of Wisconsin-Madison, Madison, US. qhuang46@wisc.edu
- Wenwu Tang, Department of Geography and Earth Sciences, University of North Carolina at Charlotte,US. wenwutang@uncc.edu
- Eric Shook, Department of Geography, Environment, and Society, University of Minnesota, US. eshook@umn.edu
- Qingfeng Guan, School of Information Engineering, China University of Geosciences, China. guanqf@cug.edu.cn
Our paper Measuring Inter-City Network Using Digital Footprints from Twitter Users has been accepted by the ACM SIGSPATIAL Workshop on Prediction of Human Mobility (PredictGIS), which will be held in Seattle, WA, November, 2018.
In this paper, a new method that uses Twitter users’ movement as measurement to measure hierarchical city connectivity and build directional information flow. This method integrates human movements in the physical world and the digital movements in the virtual world. Using human mobility as measurement, flows go beyond administrative boundaries and connect counties which are not physically neighbors to each other.
AAG CISG 2019 Robert Raskin Student Competition | ||
|
Our paper entitled “A visual-textual fused approach to automated tagging of flood-related tweets during a flood event” has been accepted by the International Journal of Digital Earth.
Taking the Houston Flood in 2017 as a study case, this paper presents an automated flood tweets extraction approach by mining both visual and textual information a tweet contains. A CNN architecture was designed to classify the visual content of flood pictures during the Houston Flood. A sensitivity test was then applied to extract flood sensitive keywords that were further used to refine the CNN classified results. A duplication test was finally performed to trim the database by removing the duplicated pictures to create the flood tweets pool for the flood event. The results indicated that coupling CNN classification results with flood sensitive words in tweets allows a significant increase in precision while keeps the recall rate in a high level. The elimination of tweets containing duplicated pictures greatly contributes to higher spatio-temporal relevance to the flood.
Call for papers
A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).
Deadline for manuscript submissions: 30 June 2019
More Information:
http://www.mdpi.com/journal/ijgi/special_issues/Big_Data_Geospatial_Applications
Our paper entitled “A graph-based approach to detect the tourist movement pattern using social media data” has been accepted by Cartography and Geographic Information Science.
This paper introduces a graph-based approach to detect the tourist movement patterns from massive and noisy social media(Twitter) data, and an object-based model is designed to represent the tourist’s spatiotemporal movement trajectory. To build the tourist graph, we first utilize the DBSCAN-based method to cluster the tourist trajectories to identify the vertices in the graph and then connect the vertices by using the tourist trajectories to generate the edges of the graph. Once the tourist graph is constructed, a set of graph-based network analysis methods is introduced to detect the tourist movement patterns.
New York City is used as the study area to demonstrate and evaluate the proposed approach. Based on the results of the case study, we reveal the tourist movement patterns by detecting the popular attractions, centric attraction, popular point-to-point routes, popular tour routes from the tourist graph. These results demonstrate that the proposed methodologies provide a feasible and effective way to build a graph-based network model for tourists from big social media data to analyse their movement patterns.
Yuqin Jiang received the 2018 Department of Geography Teaching Assistant Award for her TA work in Fall 2017 semester.
Yuqin worked for Dr. Cuizhen (Susan) Wang as lab instructor for GEOG 345 Aerial Photo Interpretation and worked for Dr. Michael Hodgson as lab instructor for GEOG 363 Introduction to GIS and GEOG 564 GIS-based Modeling.
Paper authored by Xiao Huang, Cuizhen (Susan) Wang, and Zhenlong Li entitled Reconstructing Flood Inundation Probability by Enhancing Near Real-Time Imagery with Real-Time Gauges and Tweets has been accepted for publication by the IEEE Transactions on Geoscience and Remote Sensing (Impact Factor: 4.942).
Dr. Zhenlong Li co-organized a series of sessions at AAG 2018 Annual Meeting (with Drs. Qunying Huang, Xinyue Ye, Shaowen Wang, Wenwu Tang, and Eric Shook). These sessions aimed to capture and discuss the latest advancements of big data computing, artificial intelligence and deep learning for supporting natural disaster management, geospatial applications, smart cities. Details can be found below:
-
Spatiotemporal Symposium: Social Sesing and Big Data Computing for Disaster Management (Panel)
-
Artificial Intelligence and Deep Learning Symposium: Big Data and Mining for Natural Hazards
-
Spatiotemporal Symposium: Big Data Computing for Geospatial Applications
-
Symposium on New Horizons if Human Dynamics Research: Smart Cities and Urban Computing I
-
Symposium on New Horizons if Human Dynamics Research: Smart Cities and Urban Computing III


Yuqin Jiang won 3rd place in the 2018 AAG Robert Raskin Student Paper Competition Award among a group of highly competitive students for her paper titled “Social Network, Activity Space, Sentiment, and Evacuation: What Can Social Media Tell Us?”
Dr. Zhenlong Li is elected as the Vice Chair of the Cyberinfrastructure Specialty Group(CISG) of the Association of American Geographers(AAG) for year of 2018-2019. He will assume the Chair role for the second year.
The AAG CISG strives to enhance geographic research and scholarship on matters relating to cyberinfrastructure. For more information about CISG, visit: http://gis.cas.sc.edu/cisg
Organized by the US Geospatial Intelligence Foundation and open to the 14 GEOINT accredited universities, the challenge asked applicants to describe which problem they would choose to solve if given access to to an NVIDIA GPU-powered supercomputer. Ning’s winning essay, submitted with USC Geography professors Zhenlong Li and Cuizhen “Susan” Wang, was titled “Tagging the Earth with High Resolution Imagery and Deep Learning.”
In announcing the winners, Dr. Camelia Kantor, USGIF’s Director of Academic Programs, noted that the winning entries “stood out because they made a strong case for using the GPUs for the benefit of their students.”
Open Call for Submissions
Special Issue on “Social Sensing and Big Data Computing for Disaster Management” in International Journal of Digital Earth(IJDE)
http://explore.tandfonline.com/cfp/est/ijde/si-5
Guest Editors
Zhenlong Li, Department of Geography, University of South Carolina, SC 29208, USA zhenlong@sc.edu
Qunying Huang, Department of Geography, University of Wisconsin-Madison, WI 53706, USA qhuang46@wisc.edu
Christopher Emrich, School of Public Administration, University of Central Florida, FL 32816, USA christopher.emrich@ucf.edu
Submission Deadline: March 1st, 2018
Aims and Scope
Rapid onset disasters, often difficult to prepare for and respond to, make disaster management a challenging task worldwide. Disaster and emergency management effectiveness depends heavily on making good decisions in near-real time under extreme duress. These key, often life-saving, decisions are possible only with real-time data sources and the ability to timely collect, process, synthesize, and analyze these multi-sourced data. Traditional data collection practices such as remote sensing and field surveying often fail to offer timely information during or immediately following damaging events. For example, stream gauges are only useful for flood mapping while the stations are functioning properly and before they are overtopped by floodwaters and rendered inoperable.
Fortunately, sharing information such as texts, images, and videos through social media platforms enables all citizens to become part of a large sensor network and a homegrown disaster response team. Compared to traditional physical sensors, such a citizen-sensor network (social sensing) is low cost, more comprehensive, and always broadcasting situational awareness information. For example, with social sensing, massive amounts of micro-level disaster information (e.g. site specific damage) can be captured in real-time through social media platforms (e.g. Twitter, Facebook) and voluntarily reported via dedicated crowdsourcing applications (volunteered geographic information, VGI), enabling rapid assessment of evolving disaster situations.
On the other hand, data collected with social sensing is often massive, heterogeneous, noisy, unreliable, and comes in continuous streams. This is inherent “Big Data”, for example, millions of microblog posts from different social media platforms can be generated in a short time right after an impactful disaster. Hence, Big Data computing methods and technologies such as cloud computing, distributed geo-information processing, spatial statistics/modeling, data mining, spatial database, and multi-source data fusion become critical components of using social sensing to understand the impact of and response to the disaster events in a timely fashion.
Along these lines, this special issue on “Social Sensing and Big Data Computing for Disaster Management” by the International Journal of Digital Earth aims to capture recent advancements in leveraging social sensing and big data computing for supporting disaster management in one or more disaster phases (mitigation, preparedness, response, and recovery). Specifically, we solicit original unpublished research articles that can shed light on the opportunities, challenges, and solutions of leveraging social sensing and big data computing for supporting disaster management.
Potential topics include (but are not limited to) the following:
- Innovative approaches to synthesize multi-sourced social sensing data and/or traditional data (e.g. remote sensing) for disaster management
- Analyzing and visualizing human movement patterns before, during, and after disaster events
- Disaster event detection, early warning, and impact/damage assessment with social sensing
- Mining and extracting actionable information for rapid emergency response and relief coordination
- Geovisual analytics of social sensing data during a disaster
- Integrating data mining (machines) and crowdsourcing (human) to support decision-making
- New tools and solutions for real-time big social sensing data collecting, processing, analyzing, and visualizing
- Exploring public perception, sentiments, and understanding towards disaster events
- Novel social engagement approaches to effectively link the public in an organized way toward contributing to emergency response, recovery
- Data quality, reliability, and privacy issues of social sensing for disaster management
- Leveraging big social sensing data to enhance social resilience
Important Dates
November 15, 2017, 800-word abstract submission to guest editors
December 1, 2017, full paper submission invited
March 1, 2018, full paper submission online
May 1, 2018, revision/rejection notification
August 1, 2018, paper acceptance notification
About the journal
The International Journal of Digital Earth is an international peer-reviewed academic journal (SCI-E with a 2016 impact factor 2.292) focusing on the theories, technologies, applications, and societal implications of Digital Earth and those visionary concepts that will enable a modeled virtual world.
Submission Guidelines
Submissions must follow the instructions to authors outlined on the Taylor & Francis web page for the International Journal of Digital Earth found: here. Word templates are available on the web site and papers are typically 5000‐8000 words in length.
Papers should be submitted online at the International Journal of Digital Earth’s Manuscript Central Site: here. New users should first create an account. Once a user is logged onto the site submissions should be made via the Author Centre. Please indicate the paper is submitted to Special Issue on “Social Sensing and Big Data Computing for Disaster Management” in the cover letter.
Each paper will receive comments from at least three reviewers. The special issue will include a maximum of 8 papers.
We look forward to your contributions. Please do not hesitate to contact the Guest Editors in case of questions.
Dr. Zhenlong Li’s research on using social media for flood mapping is highlighted in Charleston City Paper. Full story can be found here:
Dr. Zhenlong Li and his student Yuqin Jiang’s research on the use of Twitter data to track solar-eclipse viewing in South Carolina was featured on the local ABC broadcast affiliate.

Dr. Zhenlong Li’s research on using social media for flood mapping is highlighted in Charleston City Paper. Full story can be found here:
“Researchers also looked at the use of social media during and after the floods. Zhenlong Li studied the use of Twitter for quickly mapping the flood based on what people were tweeting and from where. He found a high correspondence between the number of tweets from a specific location and the level of flooding.

https://www.wsav.com/news/usc-researchers-who-studied-sc-flood-share-findings/amp/