Prof. Gao receives a new geospatial data science research grant

The American Family Insurance Data Science Institute (AFIDSI) is honored to announce the results of the new round of the American Family Funding Initiative, a research competition for data science projects. American Family Insurance has partnered with UW–Madison through the Institute to offer “mini grants” of $75k-to-150k per year for data science research. This is the second installation of a $10 million research agreement.

The goal of the American Family Funding Initiative is to stimulate and support highly innovative research. The successful projects, reviewed by faculty and staff from across UW-Madison campus, were evaluated based on their potential contributions to the field of data science, practical use and the novelty of their approaches.

AFIDSI brings people together to launch new research in data science and apply findings to solve problems. In collaboration with researchers across campus and beyond, AFIDSI focuses on the fundamentals of data science research and on translating that research into practice.

New projects funded in the second round of the American Family Funding Initiative include:

A Deep Learning Approach to User Location Privacy Protection
Principal Investigator: Song Gao, Assistant Professor of Geography.
Co-Principal Investigator: Jerry Zhu, Computer Sciences.

Location information is among the most sensitive data being collected by mobile apps, and users increasingly raise privacy concerns. The proposed research aims to develop a deep learning architecture that will protect users’ location privacy while keeping the capability for location-based business recommendations such as usage-based insurance (UBI).

Machine Learning Approaches for Metadata Standardization
Principal investigator: Colin Dewey, Professor of Biostatistics and Medical Informatics.
Co-Principal Investigator: Mark Craven, Biostatistics and Medical Informatics.

The need to manually standardize metadata describing records in large data sets, compiled from many sources, is a major bottleneck in both research and business. This project will develop machine learning approaches for automating metadata standardization and identifying records that would most benefit from expert human input.

Adaptive Operations Research and Data Modeling for Insurance Applications
Principal Investigator: Michael Ferris, Professor of Computer Sciences.

Insurance claims applications must be operated efficiently under normal conditions and allow for rapid reconfiguration in crisis situations. The proposed work will develop optimization models, data and solution processes to schedule resources over time, servicing normal workloads, while creating resilience to abrupt changes from random disturbances.

GAN-mixup: A New Approach to Improve Generalization in Machine Learning
Principal Investigator: Kangwook Lee, Assistant Professor of Electrical and Computer Engineering.
Co-Principal Investigator: Dimitris Papailiopoulos, Electrical and Computer Engineering.

Recent machine learning successes rely on predictive models that adapt to previously unseen data. This research will provide a new approach to improve such generalization, with provable performance guarantees.

Integer Programming for Mixture Matrix Completion
Principal Investigator: Jeff Linderoth, Professor of Industrial and Systems Engineering.
Co-Principal Investigators: Jim Luedtke, Industrial and Systems Engineering; Daniel Pimentel-Alarcon, Biostatistics and Medical Informatics.

Matrix completion, or filling in the unknown entities in a matrix, is used in applications such as recommender systems and systems for analyzing visual images. This project will apply integer programming techniques to develop algorithms for solving a mixture matrix completion problem, paving the way towards applying this method to large-scale data science problems.

Developing a State-of-the-Science Regional Weather Forecasting System
Principal Investigator: Michael Morgan, Professor of Atmospheric and Oceanic Sciences.
Co-Principal Investigator: Brett Hoover, Space Science and Engineering Center.

This project will develop a weather prediction system for American Family Insurance, run entirely in cloud computing infrastructure, that will improve the accuracy of forecasting hazards such as hail and hurricanes. The probabilistic system will also estimate the uncertainty associated with the predictability of hazardous weather.

Model Recycling: Accelerating Machine Learning by Re-using Past Completions
Principal Investigator: Shivaram Venkataraman, Assistant Professor of Computer Sciences.
Co-Principal Investigator: Dimitris Papailiopoulos, Electrical and Computer Engineering.

Training machine learning models that are used in a wide range of domains, from drug discovery to recommendation engines, takes significant time and resources. This project will automate and accelerate this process of fine-tuning by reusing and sharing past computations from prior training jobs, using a technique called model recycling.

Additionally, two projects from the first round received continued funding:

Question Asking with Differing Knowledge and Goals
Principal investigator: Joe Austerweil, Assistant Professor of Psychology.

Despite tremendous progress in machine learning, automated answers to questions are still inferior to answers from humans. This project investigates whether incorporating psycholinguistic factors that influence how people respond to language can improve automated question-answering methods.

Lightweight Natural Language and Vision Algorithms for Data Analysis
Principal investigator: Vikas Singh, Professor of Biostatistics and Medical Informatics. Collaborators: Zhanpeng Zeng, Computer Sciences; Shailesh Acharya and Glenn Fung, American Family Insurance.

Natural language processing is a form of artificial intelligence that helps computers read and understand human language. The overarching goal of this project is to accelerate the time it takes to train and test efficient, accurate natural language processing models.

National Fellowships Engage Geospatial Research And Education On COVID-19

Projects address human mobility patterns, access to health care and food systems, racial and disability disparities during the pandemic.

The Geospatial Software Institute (GSI) Conceptualization Project has announced 16 fellowships to researchers at 13 institutions to tackle COVID-19 challenges using geospatial software and advanced capabilities in cyberinfrastructure and data science. Prof. Song Gao was selected as one of the geospatial fellows. A full list of the fellows, with biographies and project information, is at https://gsi.cigi.illinois.edu/geospatial-fellows-members/.

The GSI Conceptualization Project is supported by the National Science Foundation (NSF), and carried out in partnership with the American Association of Geographers (AAG), Consortium of Universities for the Advancement of Hydrologic Science, Inc. (CUAHSI), the National Opinion Research Center (NORC) at the University of Chicago, Open Geospatial Consortium (OGC), and University Consortium for Geographic Information Science (UCGIS). Technical and cyberinfrastructure support are provided by the CyberGIS Center for Advanced Digital and Spatial Studies (CyberGIS Center)  at the University of Illinois at Urbana-Champaign. 

“The COVID-19 crisis has shown how critical it is to have cutting-edge geospatial software and cyberinfrastructure to tackle the pandemic’s many challenges,” said Shaowen Wang, the principal investigator of the NSF project and founding director of the CyberGIS Center. “We are extremely grateful for NSF’s support to fund this talented group of researchers, whose work is so diverse yet complementary.”

Michael Goodchild, chair of the NSF project advisory committee and professor emeritus in geography at UC-Santa Barbara, agreed. “Geospatial data and tools have enormous potential for helping us address the challenges of COVID-19, and these 16 Fellows have exactly the right qualifications and experience. I’m very excited to see what they are able to achieve.”

The Fellows come from varied professional, cultural, and institutional backgrounds, representing many disciplinary areas, including public health, food access, emergency management, housing and neighborhood change, and community-based mapping. The fellowship projects represent frontiers of emerging geospatial data science, including for example geospatial AI and deep learning, geovisualization, and advanced approaches to gathering and analyzing geospatial data.

Pioneered by multi-million dollar research funded by NSF, cyberGIS (i.e., cyber geographic information science and systems based on advanced computing and cyberinfrastructure) has emerged as a new generation of GIS, comprising a seamless integration of advanced cyberinfrastructure, GIS, and spatial analysis and modeling capabilities while leading to widespread research advances and broad societal impacts. Built on the progress made by cyberGIS-related communities, the GSI conceptualization project is charged with developing a strategic plan for a long-term hub of excellence in geospatial software infrastructure, one that can better address emergent issues of food security, ecology, emergency management, environmental research and stewardship, national security, public health, and more.

The Geospatial Fellows program will enable diverse researchers and educators to harness geospatial software and data at scale, in reproducible and transparent ways; and will contribute to the nation’s workforce capability and capacity to utilize geospatial big data and software for knowledge discovery. With a particular focus on COVID-19, the combined research findings of the Fellows will offer insight on how to make geospatial research computationally reproducible and transparent, while also developing novel methods, including analysis, simulation, and modeling, to study the spread and impacts of the virus. The Fellows’ research will substantially add to public understanding of the societal impacts of COVID-19 on different communities, assessing the social and spatial disparities of COVID-19 among vulnerable populations.

“I look forward to seeing the results of these projects, particularly as FAIR and open datasets, software, and models that others can then build on,” says Daniel S. Katz, Assistant Director for Scientific Software and Applications at the National Center for Supercomputing Applications (NCSA), the University of Illinois.

For more information about the GSI conceptualization project, see their website: https://gsi.cigi.illinois.edu/.

For a list of Geospatial Fellows and their projects, visit https://gsi.cigi.illinois.edu/geospatial-fellows-members/.

Prof. Gao received the 2020 Distinguished Honors Faculty Award

Each year, the University of Wisconsin-Madison College of Letters & Science Honors Program solicits student nominations of faculty members (or instructional academic staff) who have had a special impact as teachers of Honors courses, as supervisors of Honors theses, or as teachers and mentors of Honors students. The Faculty Honors Committee reviews these nominations and votes to confer Distinguished Honors Faculty status on the strongest nominees for these awards each spring. Below, we recognize each of these incredible educators and thank them for their contributions to the lives of all students, but particularly those in the Honors program.

This year, Prof. Song Gao received the 2020 Distinguished Honors Faculty Award along with five other faculty members on campus.

Also, congrats to Timothy Prestby for finishing his L&S undergraduate honor thesis “Understanding Neighborhood Isolation Through Big Data Human Mobility Analytics”. Best wishes to his graduate school life at PSU Geography!

GeoDS Lab members won multiple awards in the AAG 2020 Annual Meeting

Due to the COVID-19 pandemic, The American Association of Geographers (AAG)  2020 Annual Conference was held online virtually. GeoDS Lab members participated the meeting and fortunately won several awards as follows.

Congratulations to Yuhao Kang who won the 1st place in the 2020 AAG GIS Specialty Group Annual Best Student Paper Competition and the 2020 AAG Cartography Specialty Group Master’s Thesis Research Grant.
http://aag-giss.org/2020-aag-geographic-information-science-and-systems-specialty-group-annual-student-paper-competition-winners/

https://aagcartography.wordpress.com/awards-competitions/masters-thesis-research-grant/

In addition, GeoDS Lab’s recent COVID-19 mapping work was awarded the winner of static mapping group for the “AAG Health and Medical Geography Health Data Visualization Contest”.

Also, GeoDS Lab’s recent COVID-19 work was featured by the AAG Newsletter:

http://news.aag.org/2020/03/geographers-act-on-covid19/

County-to-County- Spring Travel Flow Tracking

Prof. Gao received a NSF RAPID grant in response to COVID-19

Recently, a multidisciplinary research team led by Prof. Song Gao (Geography) who serves as the Principal Investigator (PI) and collaborates with three other Co-PIs at UW-Madison: Prof. Kaiping Chen (Life Sciences Communication), Prof. Qin Li (Mathematics), and Prof. Jonathan Patz (Population Health Sciences), was awarded a new NSF RAPID grant in response to the COVID-19 pandemic. The project title is: “Geospatial Modeling of COVID-19 Spread and Risk Communication by Integrating Human Mobility and Social Media Big Data”.

This project will investigate the gap between the science of epidemic modeling and risk communication to the general public in response to the COVID-19 pandemic. With the rapid development of information, communication, and technologies, new data acquisition and assessment methods are needed to evaluate the risk of epidemic transmission and geographic spreading from the community perspective, to help effectively monitor social distancing policies, and to understand social disparities and environmental contexts in risk communication. This project will make theoretical, methodological, and practical contributions that advance the understanding of the COVID-19 spread across both time and space. The communication aspects of this research will serve to educate communities about the science, timing, and geography of virus transmission in order to enhance actions for addressing such global health challenges. This project explores the capabilities and potential of integrating social media big data and geospatial artificial intelligence (GeoAI) technologies to enable and transform spatial epidemiology research and risk communication. Results will be disseminated broadly to multiple stakeholder groups. Further, this project will support both researchers and students from underrepresented groups, broadening participation in STEM fields. Lastly, the Web platform developed in this project will serve as an education tool for students in geography, communication, mathematics, and public health, as well as for effectively engaging with communities about the science of COVID-19.

Past health research mainly focuses on quantitative modeling of human transmission using various epidemic models. How to effectively communicate the science of an epidemic outbreak to the general public remains a challenge. When an epidemic outbreak occurs without specific controls in place, it can be particularly challenging to improve community risk awareness and action. The research team, composed of experts from geography, mathematics, public health and life sciences communication will (1) develop innovative mathematical predictive models that integrate spatio-temporal-social network information and community-centered approaches; (2) integrate census statistics, human mobility and social media big data, as well as policy controls to conduct data-synthesis-driven and epidemiology-guided risk analysis; And (3) utilize panel surveys and text mining techniques on social media data for better understanding public awareness of COVID-19 and for investigating various instant message and visual image strategies to effectively communicate about risks to the public. The results of this project will lead to a better understanding of the geography and spread of COVID-19. Additionally, it is expected that the methods developed in this project can be applied to mitigate the outbreak risks of future epidemics.

The research team will also collaborate with The Wisconsin State Cartographer’s Office (SCO), The Wisconsin Department of Health Services (DHS), The American Family Insurance Data Science Institute (DSI), and The Global Health Institute (GHI).

Read our recent work: Mobile location big data can help predict the potential infected areas as coronavirus spreads


Call for papers: GIScience 2020 International Conference

11th International Conference on Geographic Information Science (GIScience 2020)

http://www.giscience.org

Poznań, Poland, 15-18 September, 2020

The 11th International Conference on Geographic Information Science will be held in Poznań, Poland, 15-18 September 2020. Hosted by Adam Mickiewicz University, GIScience 2020 continues the long tradition of the series as a flagship conference for researchers in geographic information science and related disciplines that are interested in spatial and temporal information.

The biennial conference series typically attracts over 300 international participants from academia, industry, and government to advance the state-of-the-art in geographic information science. The first conference day (September 15, 2020) will be dedicated to workshops and tutorials, while the main conference will be taking place on September 16-18, 2020. The conference offers two separate paper tracks, one for full papers and the other for short papers, both of which will undergo full peer-review. Authors of accepted papers will be given the opportunity to present their work at the conference in an oral presentation or as a poster.

The GIScience conference series is deeply interdisciplinary with contributions frequently involving domains such as geography, earth science, cognitive science, information science, computer science, linguistics, mathematics, philosophy, life sciences, and social science. It attracts contributions from experts in geo-visualization, geographic information retrieval, geostatistics, geo-semantics, geosimulation, spatial optimization, transportation, computational geometry, and data structures. Topics of interest are not restricted to the geo-spatial realm but involve spatial and temporal information more broadly.

Since 2018, GIScience proceedings are published in LIPIcs, the Leibniz International Proceedings in Informatics series (https://www.dagstuhl.de/en/publications/lipics). LIPIcs volumes are peer-reviewed and published according to the principle of open access, i.e., they are available online and free of charge. Each article is published under a Creative Commons CC BY license (http://creativecommons.org/licenses/by/3.0/), where the authors retain their copyright. Also, each article is assigned a DOI and a URN. The digital archiving of each volume is done in cooperation with the Deutsche Nationalbibliothek/German National Library. A number of other high-standing international conferences have already made the move to LIPIcs.

CONFERENCE TOPICS

Contributions are invited from a wide range of disciplines related to geographic information science, such as geography, earth science, cognitive science, information science, computer science, linguistics, mathematics, philosophy, life sciences, and social science. Topics of interest include (but are not limited to):

  • Agent-based modeling
  • Computational geometry
  • Events and processes
  • GeoAI
  • Geo-APIs
  • Geo-knowledge graphs
  • Geo-semantics
  • Geographic information observatories
  • Geographic information retrieval
  • Geosimulation and spatio-temporal modelling
  • Geovisualization and visual analytics
  • High-performance computing algorithms for spatial-temporal data
  • Human-Computer Interaction (with mobile devices)
  • Image classification methods
  • Internet of Things
  • Location privacy
  • Location-Based Services
  • Navigation
  • Replicability and reproducibility in GIScience
  • Scene recognition
  • Sensitivity analysis for spatial-temporal models
  • Spatial and spatio-temporal statistics
  • Spatial and temporal language
  • Spatial aspects of social computing
  • Spatial data infrastructures
  • Spatial data structures and algorithms
  • Spatially-explicit decision support
  • Spatially-explicit machine learning
  • Standardization and interoperability
  • Time series analysis
  • Trajectory and movement analysis
  • Uncertainty quantification and error propagation
  • Virtual reality


INFORMATION FOR AUTHORS

Full Paper Track

Full research papers will be thoroughly reviewed by at least three members of the international program committee. For this edition of the GIScience series, we will include an optional rebuttal phase during which authors can respond to the (initial) reviews. The rebuttal phase provides an opportunity to address misunderstandings, answer questions, or provide further details on issues that remained unclear to the reviewers. The reviewers will be able to react to these rebuttals by adjusting their review scores, if appropriate. Review criteria include novelty, significance of results as compared to previous work, the quality of the presented evaluations (if applicable), the clarity of the research statement, as well as the quality of writing and supporting illustrations. High-quality submissions will be accepted for presentation at the conference and published in LIPIcs, the Leibniz International Proceedings in Informatics series. Manuscripts must describe original work that has neither been published before, nor is currently under review elsewhere. Papers must be written in English and should not exceed fifteen pages (including title, figures, and references) in the required layout (see below). 

Short Paper Track

Short papers can report on the latest breaking results, present visions for the future of the field, or describe early work and experiments, as well as novel application areas. Short papers will also be reviewed by at least three reviewers. Review criteria include novelty, expected impact of early results, evaluation or evaluation plans for the future, plausibility of presented visions, as well as the quality of writing and supporting illustrations. Accepted papers in this track will be selected for either oral or poster presentations. Short papers must be written in English and should not exceed six pages (including title, figures, and references) in the requested LIPIcs layout. In addition, each submission must include Short Paper as a subtitle. 

The submission Web page for both tracks of GIScience 2020 is: https://easychair.org/conferences/?conf=giscience2020.


IMPORTANT DATES 

  • FULL PAPER TRACK
    • Full paper submissions: March 16, 2020
    • Full paper rebuttal phase: April 24-30, 2020
    • Full paper notification: May 15, 2020
    • Camera-ready papers: June 1, 2020
    • Full paper author registration deadline: June 1, 2020
       
  • SHORT PAPER TRACK
    • Short paper submission: May 25, 2020
    • Short paper notification: July 3, 2020
    • Camera-ready papers: July 15, 2020
    • Short paper author registration deadline: July 15, 2020
FORMATTING INSTRUCTIONS (all tracks)

The layout of any PDF submission to GIScience, whether full paper or short paper, should follow the 2019 template provided by LIPIcs (http://drops.dagstuhl.de/styles/lipics-v2019/lipics-v2019-authors.tgz). LIPIcs also provides a LaTeX class and template for papers. Authors unfamiliar with LaTeX, but keen to try, are highly encouraged to use Overleaf (http://www.overleaf.com), an online LaTeX editor that is easy to use and does not require any local installation. Overleaf comes with the LIPIcs class and template pre-loaded. Authors who want to use other word processors or text editors should stay close to the sample article’s layout for their paper submitted for review. Should their papers be accepted for publication, they will have to be converted to LaTeX using the LIPIcs LaTeX class and template. Authors are responsible for the conversion of their papers to LaTeX. There are also commercial conversion services such as http://wordtolatex.com/upload providing a one-step solution in case you do not want to do the conversion yourself. 

GeoDS Lab at the Emerging Technology Leadership Summit 2019

Hyper Innovation is working with the Wisconsin Institutes for Discovery to establish the Emerging Tech Hub@UW-Madison to highlight applications for emerging technologies (e.g., VR/AR), create inspiration for innovation, and provide collaboration opportunities for startups, universities, and corporations.

GeoDS Lab among other campus teams were invited to show the Augmented Reality Beacons demo at the Innovation and Emerging Technology Leadership Summit – November 14, 2019.

VR Playground
AR SandBox

GeoDS Lab at ACM SIGSPATIAL’19

During November 5 – 8, 2019, GeoDS lab members presented at the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2019) held in Chicago. We had two presentations and got one “Best Poster Award” in the Workshop on Ride-hailing Algorithms, Applications, and Systems (RAAS 2019)

  1. Analyzing the Gap Between Ride-hailing Location and Pick-up Location with Geographical Contexts (Best Poster Award). Yunlei Liang, Song Gao, Mingxiao Li, Yuhao Kang, and Jinmeng Rao (2019). In Proceedings of 1st ACM SIGSPATIAL International Workshop on Ride-hailing Algorithms, Applications, and Systems (RAAS’19) DOI: 10.1145/3357140.3365493 [PDF]
  2. A Data-Driven Approach to Understanding and Predicting the Spatiotemporal Availability of Street Parking (Short Paper). Mingxiao Li, Song Gao, Yunlei Liang, Joseph Marks, Yuhao Kang, and Moyin Li (2019). In Proceedings of 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems(SIGSPATIAL’19) DOI: 10.1145/3347146.3359366 [PDF]

As the General Chairs, Professor Song Gao co-organized the 3rd ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI 2019). There are two keynotes from both industry and academia and 17 oral presentations in the GeoAI workshop. The proceedings of the GeoAI’19 workshop is available at the ACM Digital Library (Table of Contents): https://dl.acm.org/citation.cfm?id=3356471

GeoAI’19
SIGSPATIAL’19

A roundtable discussion: defining urban data science

Reference: Wei Kang, Taylor Oshan, Levi J Wolf, Geoff Boeing, Vanessa Frias-Martinez, Song Gao, Ate Poorthuis, Wenfei Xu. (2019) A roundtable discussion: defining urban data science. Environment and Planning B: Urban Analytics and City Science. 46(9), 1756-1768.  DOI: 10.1177/2399808319882826 [PDF]

Abstract:

The field of urban analytics and city science has seen significant growth and development in the past 20 years. The rise of data science, both in industry and academia, has put new pressures on urban research, but has also allowed for new analytical possibilities. Because of the rapid growth and change in the field, terminology in urban analytics can be vague and unclear. This paper, an abridged synthesis of a panel discussion among scholars in Urban Data Science held at the 2019 American Association of Geographers Conference in Washington, D.C., outlines one discussion seeking a better sense of the conceptual, terminological, social, and ethical challenges faced by researchers in this emergent field. The panel outlines the difficulties of defining what is or is not urban data science, finding that good urban data science must have an expansive role in a successful discipline of “city science.” It suggests that “data science” has value as a “signaling” term in industrial or popular science applications, but which may not necessarily be well-understood within purely academic circles. The panel also discusses the normative value of doing urban data science, linking successful practice back to urban life. Overall, this panel report contributes to the wider discussion around urban analytics and city science and about the role of data science in this domain.