Invited by SafeGraph, Zhenlong Li will be giving a presentation to the SafeGraph/Placekey Slack community — a community of over 8000 researchers and data scientists on Tuesday, June 22 at 1:00 PM – 1:45 PM EDT.

Place connectivity – shaped by human movement – is quantified by the strength of spatial interactions among locations. Using social media data, they introduce a global multi-scale place connectivity index (PCI) based on spatial interactions among places that have been geotagged in tweets. This analysis can enable modeling the spread of COVID-19 and hurricane evacuation destination choices, helping with future policy and planning procedures.

Paper entitled “Social Distance Integrated Gravity Model for Evacuation Destination Choice” authored by Yuqin Jiang, Zhenlong Li, and Susan L. Cutter, is published in the International Journal of Digital Earth.

Abstract: Evacuation is an effective and commonly taken strategy to minimize death and injuries from an incoming hurricane. For decades, interdisciplinary research has contributed to a better understanding of evacuation behavior. Evacuation destination choice modeling is an essential step for hurricane evacuation transportation planning. Multiple factors are identified associated with evacuation destination choices, in which long-term social factors have been found essential, yet neglected, in most studies due to difficulty in data collection. This study utilized long-term human movement records retrieved from Twitter to (1) reinforce the importance of social factors in evacuation destination choices, (2) quantify individual-level familiarity measurement and its relationship with an individual’s destination choice, (3) develop a big data approach for aggregated county-level social distance measurement, and (4) demonstrate how gravity models can be improved by including both social distance and physical distance for evacuation destination choice modeling.

Full text: https://www.tandfonline.com/doi/full/10.1080/17538947.2021.1915396 

Our new paper entitled “Spatial-temporal relationship between population mobility and COVID-19 outbreaks in South Carolina: A time series forecasting analysis”, co-authored by Chengbo Zeng, Jiajia Zhang, Zhenlong Li, Xiaowen Sun, Bankole Olatosi, Sharon Weissman, Xiaoming Li, has been accepted for publication by JMIR .

Read the preprint version here: https://www.medrxiv.org/content/10.1101/2021.01.02.21249119v2.full

Zhenlong Li was invited to give a talk this Thursday (03/25) at 9:00 – 10:00 PM (EDT) on measuring global multi-scale human mobility and place connectivity using big social media data. Dr. Tao Hu from Harvard University will demo how to use ODT Flow APIs and KNIME workflow to access and analyze the derived mobility flows.

—-Update—

The recording and power point slides are available for download at Harvard Dataverse (see links below).

CPGIS Educational Webinars on Spatiotemporal Study of Urban Dynamics (3)

9:00 PM-10:00 PM, Thursday, Mar 25, 2021 (US EDT)

“Measuring place connectivity using big social media data”, Dr. Zhenlong Li, University of South Carolina

Chair:   Song Gao, University of Wisconsin-Madison

Recording: https://doi.org/10.7910/DVN/XJIZJG

PPT: https://doi.org/10.7910/DVN/XJIZJG

For future events of this series, check here:

https://www.eventbrite.com/e/cpgis-educational-webinars-on-spatiotemporal-study-of-urban-dynamics-tickets-141192579807

https://www.geospatialworld.net/news/geospatial-media-unveils-its-inaugural-list-of-geospatial-world-50-rising-stars/https://geospatialmedia.net/rising-stars/2021/

Shaped by human movement, place connectivity is quantified by the strength of spatial interactions among locations. For decades, spatial scientists have researched place connectivity, applications, and metrics. The growing popularity of social media provides a new data stream where spatial social interaction measures are largely devoid of privacy issues, easily assessable, and harmonized. In this study, we introduced a place connectivity index (PCI) based on spatial interactions among places revealed by geotagged tweets as a multiscale, spatiotemporal-continuous, and easy-to-implement measurement. The proposed PCI, established and demonstrated at the US county level, exhibits a strong positive association with SafeGraph population movement records (10% penetration in the US population) and Facebook’s social connectedness index (SCI), a popular connectivity index based on social networks. We found that PCI has a strong state boundary effect and that it generally follows the distance decay effect, although this force is weaker in more urbanized counties with a denser population. Our investigation further suggests that PCI has great potential in addressing real-world problems that require place connectivity knowledge, exemplified with two applications: 1) modeling the spatial spread of a contagious disease (e.g., COVID-19), and 2) modeling hurricane evacuation destination choices. The methodological and contextual knowledge of PCI, together with the launched visualization platform and data sharing capability, is expected to support research fields requiring knowledge in human spatial interactions.

The interactive web portal for visualizing the PCI and relevant datasets can be accessed at http://gis.cas.sc.edu/GeoAnalytics/pci.html.

Download PCI and relevant datasets at https://github.com/GIBDUSC/Place-Connectivity-Index

Read the preprint article…

Figure below shows the interactive web portal for PCI visualization. The map shows the PCI for Cook County (Chicago), Illinois, to all other counties.

PCI from England, UK to other world first-level subdivisions.

Our article titled “The characteristics of multi-source mobility datasets and how they reveal the luxury nature of social distancing in the U.S. during the COVID-19 pandemic”, authored by Xiao Huang, Zhenlong Li, Yuqin Jiang, Xinyue Ye, Chengbin Deng, Jiajia Zhang, and Xiaoming Li, is accepted for publication in the International Journal of Digital Earth.

Abstract:  This study reveals the human mobility from various sources and the luxury nature of social distancing in the U.S during the COVID-19 pandemic by highlighting the disparities in mobility dynamics from lower-income and upper-income counties. We collect, process, and compute mobility data from four sources: 1) Apple mobility trend reports, 2) Google community mobility reports, 3) mobility data from Descartes Labs, and 4) Twitter mobility calculated via weighted distance. We further design a Responsive Index (RI) based on the time series of mobility change percentages to quantify the general degree of mobility-based responsiveness to COVID-19 at the U.S. county level. We find statistically significant positive correlations in the RI between either two data sources, revealing their general similarity, albeit with varying Pearson’s r coefficients. Despite the similarity, however, mobility from each source presents unique and even contrasting characteristics, in part demonstrating the multifaceted nature of human mobility. The positive correlation between RI and income at the county level is significant in all mobility datasets, suggesting that counties with higher income tend to react more aggressively in terms of reducing more mobility in response to the COVID-19 pandemic. Most states present a positive difference in RI between their upper-income and lower-income counties, where diverging patterns in time series of mobility changes percentages can be found. To our best knowledge, this is the first study that cross-compares multi-source mobility datasets. The findings shed light on not only the characteristics of multi-source mobility data but also the mobility patterns in tandem with the economic disparity.

Read a preprint version of the article here.

Check out the Chinese version here: https://mp.weixin.qq.com/s/iGisPEoHheLJEdswHF1Gaw   . Original paper can be downloaded at https://arxiv.org/abs/2011.12958

Our new book, edited by Zhenlong Li, Qunying Huang, and Chris Emrich is published by Routledge. The book is published from a very successful special issue in the International Journal of Digital Earth.

https://www.routledge.com/Social-Sensing-and-Big-Data-Computing-for-Disaster-Management/Li-Huang-T-Emrich/p/book/9780367617653

Register the conference at https://www.sc-bdhs-conference.org/

We invite you to submit your abstract to our session, Social Media and Big Data for Disasters, at the upcoming virtual American Association of Geographers Annual Meeting, April 7-11, 2021. The session will bring together basic and empirical research that advances existing understanding and techniques to address the issue of big data quality and its impact on applications pertaining to human dynamics, built environments and hazards. Potential research topics include, but are not limited to:

• Quality issues in big data
• Calibration and validation techniques/approaches in big data
• Data integration of multi-source and/or heterogenous datasets
• Big data analytics in hazards and built environment
• Big data analytics in human movements and behaviors
• Big data quality and its impact in decision making
• Challenges in collecting, processing and analyzing big data for real-time applications
• Geo-visualization techniques to analyze and visualize social media data
• Privacy and big data management

If you would like to be included in the session, please submit your abstract here by Thursday, November 19^th and send a copy of your abstract and PIN to Dr. Bandana Kar (karb@ornl.gov). Let us know if you have any questions – we look forward to receiving your submissions!

Sincerely,

Bandana Kar
Research Scientist, Oak Ridge National Laboratory

Edwin T. Chow
Associate Professor, Texas State University

Zhenlong Li
Associate Professor, University of South Carolina

Qunying Huang
Associate Professor, University of Wisconsin

The Big Data Health Science Center (BDHSC) at University of South Carolina (UofSC) Arnold School of Public Health invites applications for two post-doctoral research fellow positions. The qualified candidates will be expected to participate in funded Big Data projects in HIV and COVID-19 research. The primary responsibilities of the post-doctoral fellows may include, but are not limited to, literature review, data management and analysis, preparation of manuscripts, grant writing, and other related tasks. We are seeking highly motivated candidates with long-term interest in a research career in an academic setting. The applicants must have a doctoral degree in a health data-related field (e.g., public health, statistics, biostatistics, or quantitative psychology), by the time of appointment. Other qualifications include expertise in quantitative methodology and statistics, strong analytic skills, ability to take initiative and work independently, high standard of work ethic, effective oral and written communication skills, and proficiency in SPSS, SAS, STATA, R, or other statistical programming. Previous research experiences in HIV, COVID-19, or data analytics are preferred. The initial appointment for the positions will be one year but renewable contingent upon job performance and the availability of funding. For prompt consideration, please submit your application at the UofSC Human Resources web site uscjobs.sc.edu/postings/89660 (Posting # STA00678PO20). For inquires please contact Dr. Xiaoming Li at XIAOMING@mailbox.sc.edu. Review of applications will begin immediately but the positions will remain open until filled.

In this study, we investigate the potential driving factors that lead to the disparity in the time-series of home dwell time, aiming to provide fundamental knowledge that benefits policy-making for better mitigation strategies of future pandemics. Taking Metro Atlanta as a study case, we perform a trend-driven analysis by conducting Kmeans time-series clustering using fine-grained home dwell time records from SafeGraph, and further assess the statistical significance of sixteen demographic/socioeconomic variables from five major categories. We find that demographic/socioeconomic variables can explain the disparity in home dwell time in response to the stay-at-home order, which potentially leads to disparate exposures to the risk from the COVID-19. The results further suggest that socially disadvantaged groups are less likely to follow the order to stay at home, pointing out the extensive gaps in the effectiveness of social distancing measures exist between socially disadvantaged groups and others. Our study reveals that the long-standing inequity issue in the U.S. stands in the way of the effective implementation of social distancing measures. Policymakers need to carefully evaluate the inevitable trade-off among different groups, making sure the outcomes of their policies reflect interests of the socially disadvantaged groups.

Read full article…

Check out our new article published in International Journal of Digital Earth (IJDE) “Taking the pulse of COVID-19: a spatiotemporal perspective”

Full paper

Check out our new preprint paper (link to full text) for the analysis of characteristics of multi-source mobility datasets and how they reveal the luxury nature of social distancing in the U.S. during the COVID-19 pandemic.

Abstract: This study reveals the human mobility from various sources and the luxury nature of social distancing in the U.S during the COVID-19 pandemic by highlighting the disparities in mobility dynamics from lower-income and upper-income counties. We collect, process, and compute mobility data from four sources: 1) Apple mobility trend reports, 2) Google community mobility reports, 3) mobility data from Descartes Labs, and 4) Twitter mobility calculated via weighted distance. We further design a Responsive Index ( ) based on the time series of mobility change percentages to quantify the general degree of mobility-based responsiveness to COVID-19 at the U.S. county level. We find statistically significant positive correlations in the  between either two data sources, revealing their general similarity, albeit with varying Pearson’s  coefficients. Despite the similarity, however, mobility from each source presents unique and even contrasting characteristics, in part demonstrating the multifaceted nature of human mobility. The positive correlation between RI and income at the county level is significant in all mobility datasets, suggesting that counties with higher income tend to react more aggressively in terms of reducing more mobility in response to the COVID-19 pandemic. Most states present a positive difference in between their upper-income and lower-income counties, where diverging patterns in time series of mobility changes percentages can be found. To our best knowledge, this is the first study that cross-compares multi-source mobility datasets. The findings shed light on not only the characteristics of multi-source mobility data but also the mobility patterns in tandem with the economic disparity.

https://www.nytimes.com/2020/07/01/us/coronavirus-myrtle-beach.html

Xiaoming Li (Department of Health Promotion, Education, and Behavior, Arnold School of Public Health) and Bankole Olatosi (Department of Health Services Policy and Management, Arnold School of Public Health), in collaboration with BDHSC faculty members from the Arnold School of Public Health (Jiajia Zhang), College of Arts and Sciences (Zhenlong Li), College of Engineering and Computing (Neset Hikmet and Jianjun Hu), and School of Medicine-Columbia (Sharon Weissman), have been awarded a $1,252,550 grant from the National Institute of Allergy and Infectious Diseases to develop a state-wide data-driven system to fight COVID-19 in South Carolina.

Read the story…

Zhenlong Li, in collaboration with Dwayne Porter and Xiaoming Li, received an NSF award “Monitoring the Spatial Spread of COVID-19 through the Lens of Human Movement using Big Social Media Data”. This project aims to provide enhanced situation awareness and offer valuable contributions to building collective public awareness of the role people play in the evolution of the COVID-19 pandemic.

Some preliminary findings: https://lnkd.in/ebr-rab

Dr. Zhenlong Li, teamed with public health colleagues Drs. Xiaoming Li and Bankole Olatosi, receives funds from the USC Office of the Vice President for Research COVID-19 Internal Funding Initiative to conduct preliminary study of a big data approach for better understanding the spatial propagation of the novel coronavirus.

https://www.sc.edu/about/offices_and_divisions/research/news_and_pubs/news/2020/20200427_covid-19_initiative_recipients.php 

Check out our new web app showing near-real time population movement through the lens of social media (twitter) data during the COVID-19 Crisis (more statistical analyses will follow).  http://gis.cas.sc.edu/GeoAnalytics/COVID19.html

And our new post for some comparison analysis: http://gis.cas.sc.edu/gibd/how-our-collective-efforts-of-fighting-the-virus-are-reflected-on-maps/

Dr. Zhenlong Li has been selected to receive the Breakthrough Star Award from the University of South Carolina for his considerable research contributions.

 ” ‘This year, we are proud to announce five Breakthrough Leadership in Research awardees, 11 Breakthrough Stars and 14 Breakthrough Graduate Scholars.’  Vice President for Research, Prakash Nagarkatti said, ‘This group of 2020 Breakthrough awardees is extremely impressive. It speaks so highly of our amazing research enterprise at the University of South Carolina that we have Breakthrough recipients representing departments ranging from music to mechanical engineering, across eight UofSC colleges spanning three campuses. The faculty and doctoral students receiving Breakthrough awards this year are emblematic of the excellence that characterizes our university. It is my pleasure to thank and congratulate all of this year’s Breakthrough recipients.’ ” (https://www.sc.edu/about/offices_and_divisions/research/news_and_pubs/news/2020/20200113_breakthrough_awards_announced.php)

The UofSC Big Data Health Science Conference is a signature annual event of the UofSC Big Data Health Science Center (BDHSC). Highlights of the conference include world renowned keynote speakers in the field from the health industry, academia and government. Leadership and Program officers from NIH will also be present to provide comments on future funding directions. Unlike other conferences, there will also be hands-on learning workshop training on Big Data methods (limited space). Other workshops and thematic sessions will span electronic health records, geospatial, social media, genomics and nano-biomaterial. Detailed information on the conference can be found at the conference webpage: https://www.sc-bdhs-conference.org/

Conference registration link: https://www.sc-bdhs-conference.org/registration-information

The article Detecting New Building Construction in Urban Areas Based on Images of Small Unmanned Aerial System authored by Huan Ning, Xiao Huang, Zhenlong Li, Cuizhen Wang, and Duowen Xiang, is accepted for publication in the journal Papers in Applied Geography.

Abstract: The small Unmanned Aerial System (sUAS) is an emerging approach to monitor new buildings. sUAS acquires ultra-high-resolution imagery which provides visual evidence and reduces the necessity of in-situ investigation. It offers greater potential for building change detection when two epochs of images of the place of interest are captured. This study takes the entire urban area of Longfeng Town, Hubei Province, China as a test site, where two sets of 0.05 m resolution sUAS images were acquired on March 23, 2017 and June 6, 2017, respectively. In this short time interval, the heightened structures of the existing buildings consist of most changes. This study proposes a sensitive building change detection method by integrating the visual and elevation information from sUAS images. Dense point clouds were generated using sUAS images without control points. Two Digital Surface Models (DSM) are generated based on point clouds to detect elevation changes between two epochs. With true-color images, the improved Triangle Greenness Index (TGI) is used to mask out the natural changes caused by seasonal vegetation growth. Lastly, multiple criteria are utilized to identify changes in buildings including new buildings on the ground and new stories atop current buildings. The experimental result reveals that over 93.3% of building changes, including 3 new buildings and 25 stories and structures added to existing buildings are detected, which proves the validity of the proposed method for local land-use enforcement. The proposed method takes 5 minutes to extract changes from orthoimages and DSMs of 2 km2, while manual monitoring is more than 40 times slower.

The article Evacuation Departure Timing during Hurricane Matthew authored by Erika O. Pham, Christopher T. Emrich, Zhenlong Li, Jamie Mitchem, and Susan L. Cutter has been accepted for publication in the Weather, Climate, and Society.

ABSTRACT: This study investigates evacuation behaviors associated with Hurricane Matthew in October of 2016. It assesses factors influencing evacuation decisions and evacuation departure times for Florida, Georgia, and South Carolina from an online survey of respondents. Approximately 62% of the Florida sample, 77% of the Georgia sample, and 67% of the South Carolina sample evacuated. Logistic regression analysis of the departures in the overall time period identified variability in evacuation timing, dependent on prior experience, receipt of an evacuation order, talking with others about the evacuation order, spatial awareness or lack thereof, pets in the household, and household income in 2015. However, using four logistic regressions to analyze differences in departure times by day shows the only significant variable across all four regressions was our proxy variable for evacuation order times. Depending on the day, other significant variables include number of household vehicles, previous hurricane experience, and receipt of an evacuation order. Descriptive results show that many variables are considered in the decision to evacuate, but results from subsequent analyses, and respondents’ comments about their experiences, highlight that evacuation orders are the primary triggering variable for when residents left.

Welcome to check out the 2019 newsletter of the Cyberinfrastructure Specialty Group (CISG) of the American Association of Geographers! Following
our successful inaugural newsletter published in Fall 2018, the CISG board has decided to continue our effort in publishing the newsletter on an annual basis to further foster information sharing and collaborations within the cyberinfrastructure and relevant communities.

Download the newsletter here:  http://gis.cas.sc.edu/gibd/wp-content/uploads/2019/12/CISG_newsletter_2019.pdf

Dr. Zhenlong Li has co-organized a series of sessions on big data computing, smart cities and urban computing, and social sensing and disaster management at the 2019 American Association of Geographers (AAG) Annual Meeting, to be held at Washington DC, April 3-7, 2019. You are welcome to join us if you are around at this year’s AAG.

Paper Sessions

Symposium on Frontiers in Geospatial Data Science: Big Data Computing for Geospatial Applications

GeoAI and Deep Learning Symposium: Big data and GeoAI for Natural Hazards

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing II

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing III

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing IV

AAG Cyberinfrastructure Specialty Group 2019 Robert Raskin Student Competition

Panel Session

Social Sensing and Big Data Computing for Disaster Management

Presentations

Zhenlong Li*, University of South Carolina, Huan Ning, University of South Carolina, Using existing data to build customized deep learning training datasets for remote sensing image classification

Yuqin Jiang*, University of South Carolina, Zhenlong Li, University of South Carolina, Analyzing Human Mobility Patterns during Hurricane Matthew Evacuation using Twitter

Xiao Huang*, University of South Carolina, Zhenlong Li, University of South Carolina, Cuizhen Wang, University of South Carolina, Identifying disaster related social media for rapid response: a visual-textual fused approach

Michael Hodgson*, University of South Carolina, Zhenlong Li, University of South Carolina, Silvia Elena Piovan, University of Padova-Italy, Caglar Koylu, University of Iowa, Language and Twitter-based Social Media During Disaster Events

Zhenlong Li, Panelist, Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Social Media Analytics Tool Development

Dear colleagues,

After successfully launching the first CISG newsletter last year, we are welcoming your contributions to this year’s edition. We anticipate publication in December and ask you to submit newsworthy items by Friday, 11/18/2019.

The newsletter potentially reaches more than 140 readers and serves as an excellent venue for getting the word out on community news, departmental events, research findings, media appearances, book publications, and so on. We also invite you to share commentaries or features of broad interests with CISG specialty group members. You are welcome to post calls for papers, proposals, awards, grants, fellowships, and jobs of potential interest.

The newsletter relies greatly on your contributions, so please take a moment to send along relevant items. Please send your submissions to Alexander Hohl (alexander.hohl@geog.utah.edu) in text format by Friday, 11/18/2019. Photos, maps, graphics or drawings with captions, are especially welcome (GIF, JPG, or PNG).

Thank you,

Your CISG board members

https://www.linkedin.com/pulse/call-newsletter-items-aag-cisg/

AAG 2020 CFP: Social Media Big Data and Uncertainties in Disaster Research

The growth of information and communication technologies (ICT) has enabled citizen participation in scientific investigation (a.k.a. citizen science), and sharing of data and information via social media (e.g. Twitter) and social networking sites (e.g. Facebook). The advancements in Internet of Things (IoTs) and connected devices including drones and aerial robotics have enabled the use of social media generated big data to understand human dynamics, and their interaction with the built environments. Significant advancements have been made to collect and analyze these data for emergency response, risk communication, mobility studies among others.

The big data derived from citizen sensors tend to suffer from a myriad of uncertainties in terms of positional accuracy, context ambiguity, credibility, reliability, representativeness and completeness. Moreover, there are also serious concerns about data provenance and privacy. While there is no shortage in big data applications, the quality issue of these data remains an intellectual and practical challenge. A lack of data provenance for these data combined with unavailability of high-quality reference data appropriate to its enormous volume, heterogeneous structure in near real-time make it difficult to evaluate the quality of these data. Moreover, the notion of “ground truth” in social science research is subjected to the discourse of space-place dichotomy, the spatial and contextual randomness in human behaviors. The heterogeneous nature of these data in terms of data structure and content requires tremendous amount of processing at various stages of analytics before the data could be integrated with other geospatial datasets for decision-making purposes. Privacy awareness is of increasing importance to data management, dissemination and distribution in many research projects. Although aggregation, permutation or masking techniques can be used to protect data privacy without compromising the overall quality of data, its effectiveness depends on the degree of distribution heterogeneity of the geographic phenomenon. This session welcomes basic and empirical research that advances existing understanding and techniques to address the quality issue of big data generated from social media and its impact on applications pertaining to human dynamics, built environments and hazards. Possible topics may include but are not limited to:

* Quality issues in social media big data

* Challenges in collecting, processing and analyzing big data for real-time applications

* Big data quality and its impact in decision making

* Calibration and validation techniques/approaches in big data

* Data fusion of multi-source and/or heterogeneous datasets

* Big data analytics in hazards and built-environment

* Big data analytics in human movements and behaviors during disasters

* Geo-visualization techniques to analyze and visualize social media data

* Privacy and big data management

* Provenance and metadata generation

* Applications of machine-learning and computer vision in disaster research

* New methods to measure social media credibility of social media content and users

* Influential social media user detection

Organizers

• Bandana Kar, Oak Ridge National Laboratory, karb@ornl.gov
• Edwin Chow, Texas State University, chow@txstate.edu
• Zhenlong Li, University of South Carolina, zhenlong@sc.edu
• Qunying Huang, University of Wisconsin, qhuang46@wisc.edu

If you would like to participate, please send us your abstract PIN and your abstract (250 words max) before October 25^th, 2019.

Where/When: Association of American Geographers Annual Meeting, April 6-10, 2020, Denver, CO. Additional information regarding the conference could be found at: www2.aag.org/aagannualmeeting.

Just wanted to share this tweet on Twitter about our Twitter data analytics research.

American Association of Geographers’ Annual Meeting, April 6-10, 2020, Denver

Aims and Scope:

“Human mobility” is a commonly used but loosely defined term which represents the concept about people’s spatiotemporal occupation and involves interaction among human, society, and surrounding physical environment. Human activities currently are generating massive amount of geospatial data. Recent technology advancements further pushed volume, variety, and velocity of big human mobility to an unprecedented level. Better understanding human mobility is essential to understand human interactions with surrounding environment and the usage of geographic space. It can benefit transportation and urban planning, political decision making, economic development, emergency management, and many other fields.

However, how to efficiently and effectively process and analyze massive human movement data remains challenging given current data generating speed, especially within dynamic spatial and temporal context. This session aims to capture the latest efforts in analyzing human movement data and revealing human movement patterns that contributes to better understanding about human activities and surrounding environment under difference circumstances and within different domains, such as transportation, social network, public health, urban analysis, and emergency management.

Potential topics include, but not limited to, the following:

• Human mobility data capturing, storing, processing and analyzing
• Methodological improvements in human movement data mining, pattern analysis, and visualization
• Identifying abnormality in human mobility patterns
• Quantifying human mobility pattern changes
• Modeling human mobility during different events, for instance, hurricane evacuation
• Interdisciplinary applications with spatiotemporal human mobility data

To present a paper in this session, you will register and submit your abstract online (www2.aag.org/aagannualmeeting). Then email your presenter identification number (PIN) to one of the following organizers by October 28^th, 2019.

Organizers:

Yuqin Jiang, Department of Geography, University of South Carolina. yuqin@email.sc.edu

Zhenlong Li, Department of Geography, University of South Carolina. zhenlong@sc.edu

Xinyue Ye, Department of Informatics, New Jersey Institute of Technology. xye@njit.edu

Yuqin Jiang successfully defended her proposal yesterday titled “Quantifying Human Mobility Patterns during Disruptive Events: A Big Data Approach”. Many thanks to her committee members Drs. Susan Cutter, Michael Hodgson, and Qunying Huang (from the University of Wisconsin-Madison) for their great help! Also many thanks to those who attended and provided great questions.  Congratulations to Yuqin!

USA: Disaster research: Learning from past devastation helps prepare for future events

SOURCE(S):  UNIVERSITY OF SOUTH CAROLINA

Read more here:

https://www.sc.edu/uofsc/posts/2019/07/disaster_flood_research.php

https://www.preventionweb.net/news/view/66940

Yuqin Jiang won 2019 NSF travel award to attend AAG-UCGIS Summer School on Reproducible Problem Solving with CyberGIS and Geospatial Data Science in July.

We had another very successful American Association of Geographers (AAG) Annual Meeting at Washington DC, April 3-7, 2019.

Sessions successfully organized on big data computing, urban computing, social sensing, and disaster management: 

Symposium on Frontiers in Geospatial Data Science: Big Data Computing for Geospatial Applications

GeoAI and Deep Learning Symposium: Big data and GeoAI for Natural Hazards

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing II

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing III

Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Smart Cities and Urban Computing IV

AAG Cyberinfrastructure Specialty Group 2019 Robert Raskin Student Competition

Panel Session: Social Sensing and Big Data Computing for Disaster Management

Presentations

Zhenlong Li*, University of South Carolina, Huan Ning, University of South Carolina, Using existing data to build customized deep learning training datasets for remote sensing image classification

Yuqin Jiang*, University of South Carolina, Zhenlong Li, University of South Carolina, Analyzing Human Mobility Patterns during Hurricane Matthew Evacuation using Twitter

Xiao Huang*, University of South Carolina, Zhenlong Li, University of South Carolina, Cuizhen Wang, University of South Carolina, Identifying disaster related social media for rapid response: a visual-textual fused approach

Michael Hodgson*, University of South Carolina, Zhenlong Li, University of South Carolina, Silvia Elena Piovan, University of Padova-Italy, Caglar Koylu, University of Iowa, Language and Twitter-based Social Media During Disaster Events

Zhenlong Li, Panelist, Symposium on Human Dynamics Research in the Age of Smart/Intelligent Systems: Social Media Analytics Tool Development

Martin Y., Cutter S.L., Li Z., Emrich C., Mitchell J., Tracking The Disruption Of Hurricane Maria On Population Movements In Puerto Rico Through Geotagged Tweets, AAG Annual Meeting

Some photos

Yuqin Jiang was elected as the Student Board Director of the AAG Cyberinfrastructure Specialty Group.

Xiao Huang was selected as the second place winner of the 2019 AAG Robert Raskin Student Competition sponsored by the AAG Cyberinfrastructure Specialty Group. His paper title is “Identifying disaster related social media for rapid response: a visual-textual fusion approach” .

Dear All:

The Cyberinfrastructure Specialty Group (CISG) is seeking nominations for the following positions:

Open Positions:

Vice Chairperson (Faculty only): The vice chairperson will be elected for a two-year term. The first year he/she will be vice chairperson and the second year he/she shall become and assume the duties of the chairperson.

Directors (two): The two Directors will be elected for a two-year term.

Student Directors (Student only, two):  The student Directors will be elected for a one-year term.

Self-nominations are welcomed and encouraged. Nominators should confirm that nominees are willing to serve if appointed. Please send your nomination, along with a brief description of the nominee to Dr. Jing Li (Jing.Li145@du.edu) or Dr. Zhenlong Li (zhenlong@sc.edu) by March 19, 2019.

Online voting for new officers will be open after March 20, 2019 and before the CISG Business Meeting (scheduled on Friday, 4/4/2019, 11:45AM – 1:00 PM in Madison B, Marriott, Mezzanine Level).

For more information about the positions, please check: gis.cas.sc.edu/cisg/cisg-bylaws

Thank you.

——————————
Jing Li
Department of Geography and the Environment
University of Denver
Jing.Li145@du.edu

“Social network, activity space, sentiment and evacuation: what can social media tell us?” authored by  Yuqin Jiang, Zhenlong Li, and Susan L. Cutter has been accepted by the Annals of the American Association of Geographers!

Abstract: Hurricanes are one of the most common natural hazards in the United States. To reduce fatalities and economic losses, coastal states and counties take protective actions including sheltering in place and evacuation away from the coast. Not everyone adheres to hurricane evacuation warnings or orders. In reality evacuation rates are far less than 100 percent and are estimated using post-hurricane questionnaire surveys to residents in the affected area. To overcome limitations of traditional data collection methods that are costly in time and resources, an increasing number of natural hazard studies have used social media data as a data source. To better understand social media users’ evacuation behavior, this paper investigates whether activity space, social network, and long-term sentiment trends are associated with individual’s evacuation decision by measuring and comparing Twitter user’s evacuation decision during Hurricane Matthew in 2016. We find that 1) evacuated people have larger long-term activity spaces than non-evacuated people, 2) people in the same social network tend to make the same evacuation decision, and 3) evacuated people have smaller long-term sentimental variances than non-evacuated people. These results are consistent with previous studies based on questionnaire and survey data, and thus provide researchers a new method to study human behavior during disasters. 

Full paper can be accessed here.

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.

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

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

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.

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.

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.

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).

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?”