Spatial Data Science Institute
The Spatial Data Science Institute at the University of Maine is engaged in research on the spatial and temporal aspects of data science research and incorporation of multidisciplinary aspects of data science research. It incorporates conceptual foundations drawn from spatial informatics and geographic information science and explores them in the context of data science generally.
The Institute’s goals are to advance spatial and data science theories and to develop new spatial information approaches and technologies that help humans in their everyday lives, in their interaction with the environment, with each other, with computers, and generally to advance our understanding of spatial and temporal phenomena in our geographic surroundings.
Centered within the School of Computing and Information Science, faculty members include an interdisciplinary group with expertise in Computer Science, Law, Cognitive Psychology, and Environmental Science. It reaches beyond the School and University to include data science researchers with internationally recognized expertise in these and closely related disciplinary domains.
The Spatial Data Science Institute is the successor to the National Center for Geographic Information and Analysis (NCGIA) at the University of Maine.
Organized research laboratories affiliated with Spatial Data Science Institute faculty members and focused on spatial data science topics include:
- Geosensor Networks Lab
- Multisensory Interactive Media Lab (MIM Lab)
- Spatial Knowledge and Artificial Intelligence Lab (SKAI Lab)
- Virtual Environmental and Multimodal Interaction Laboratory (VEMI Lab)
Collaborators across Disciplinary Domains, Universities, and Nations
Ongoing Funded Research Projects
Active collaborative, multidisciplinary, and cross-domain research led by Spatial Data Science Institute researchers includes the following. Graduate students are funded as active participants in most of these projects.
- Improving User Trust of Autonomous Vehicles through Human-Vehicle Collaboration
- Leveraging Intelligent Informatics and Smart Data for Improved Understanding of Northern Forest Ecosystem Resiliency
- Empowering Multi-Conceptual Spatial Reasoning with a Repository of Qualitative and Quantitative Spatial Ontologies
- The Maine Environmental DNA (Maine-eDNA) Program
- The Urban Flooding Open Knowledge Network
- Credentialing Maine Adults for Transition into Careers in Information Systems and Spatial Informatics
- Integrating Computing into Science Teaching and Learning in Grades 6-8
- A Remote Multimodal Learning Environment to Increase Graphical Information Access for Blind and Visually Impaired Students
- Development of a Multimodal Interface for Improving Independence of Blind and Visually-Impaired People
- Preservation and Access Research and Development
As indicated below, spatial informatics faculty members currently serve as PI or Co-PI on over $30,185,000 of active externally funded research projects. These projects involve a broad range of research collaborators across the university, the state, and the nation.
Improving User Trust of Autonomous Vehicles through Human-Vehicle Collaboration
Led by Principal Investigator Dr. Nicholas Giudice and Co-PI Dr. Richard Corey, the VEMI Lab (https://umaine.edu/vemi/) recently received a $500,000 National Science Foundation grant to study self-driving vehicles. A primary goal of the research is to make transportation of the future more accessible, usable and trustworthy.
This innovative University of Maine project is designed to improve user trust of fully autonomous vehicles. It will explore new ways of sharing how decisions are made and information is communicated between the human passenger and the artificial intelligence “driver,” thereby addressing the key human factors of perceived loss of control over driving activities and fear of not “knowing” what the vehicle is doing during autonomous operation.
Human vehicle collaboration, the focus of the new project, represents the science of identifying the best ways for people to interact with and partner with vehicles of the future.
For more information on the research, consult the full UMaine News Release and the NSF Award announcement.
Leveraging Intelligent Informatics and Smart Data for Improved Understanding of Northern Forest Ecosystem Resiliency (INSPIRES)
Dr. Kate Beard-Tisdale, Spatial Informatics Professor in the School of Computing and Information Science, is among five lead investigators recently receiving a $3 million NSF grant for Leveraging Intelligent Informatics and Smart Data for Improved Understanding of Northern Forest Ecosystem Resiliency. The four-year, multidisciplinary regional project is led by the University of Maine. The project was actually awarded $6 million from the National Science Foundation, with $3 million contingent on project progress and availability of funds. The project brings together researchers from UMaine, the University of New Hampshire, and the University of Vermont to advance fundamental knowledge of forest ecosystem resilience through integration, analysis and visualization of complex data streams and models covering the region’s northern forest. Drs. Torsten Hahmann and Silvia Nittel with the Spatial Data Science Institute are also participating as senior research investigators. For further information, consult the full campus news release, the Center for Research on Sustainable Forests, and NSF’s EPSCoR Research Infrastructure Improvement program.
Empowering Multi-Conceptual Spatial Reasoning with a Repository of Qualitative and Quantitative Spatial Ontologies
Dr. Torsten Hahmann, Associate Professor in Spatial Informatics and Computer Science, received support on a $175,000 NSF grant on “Empowering Multi-Conceptual Spatial Reasoning with a Repository of Qualitative and Quantitative Spatial Ontologies”. Extending from this research Shirly Stephen, PhD student in the Spatial Information Science and Engineering program at UMaine, presented the paper “Formal Qualitative Spatial Augmentation of the Simple Feature Access Model” in Regensburg, Germany at the 14th International Conference on Spatial Information Theory. The work was selected as one of only eight papers from 30 submissions to be published in full length in the conference proceedings. For more information, see the Publication and the NSF award announcement.
The Maine Environmental DNA (Maine-eDNA) Program
A $20 million grant from the National Science Foundation EPSCoR program will fund a five-year initiative that aims to revolutionize environmental monitoring, ecological understanding and sustainability of coastal ecosystems. Dr. Kate Beard-Tisdale is among the four Co-Principal Investigators leading the project.
Environmental DNA (eDNA) is like a genetic fingerprint of a marine ecosystem. Organisms leave traces of DNA, the universal code for life, wherever they go — in the water, air or soil. These traces can be collected, identified and linked back to those species, much like evidence at a crime scene. The resulting data can show where, when and how species and groups of organisms have interacted with each other and their coastal habitats. Collected eDNA can also be combined into larger and more comprehensive data sets that scientists can reanalyze to answer ever-evolving questions about how coastal systems work — and what makes them resilient or susceptible to change.
For more information on this research project titled Molecule to Ecosystem: Environmental DNA as a Nexus of Coastal Ecosystem Sustainability for Maine (Maine-eDNA), consult the Maine-eDNA web site, the full UMaine News Release, and the NSF Award announcement.
The Urban Flooding Open Knowledge Network
NSF has awarded a multi-disciplinary research team involving the University of Cinncinati, North Carolina State University, the University of Illinois at Urbana-Champaign, Purdue University, and the University of Maine a $1,000,000 grant to develop “The Urban Flooding Open Knowledge Network” to improve prediction, risk analysis and mitigation of flooding in urban areas. The open knowledge network will connect public data and knowledge about the natural environment, such as from weather forecasts or terrain and elevation maps, with information about the water, sewer and energy infrastructure that are often affected during severe weather events.
Dr. Torsten Hahmann, Associate Professor in Spatial Informatics and Computer Science at UMaine, is a co-PI of the research team. He will contribute his expertise in data semantics and artificial intelligence to intelligently connect and integrate data from partners and government agencies with different disciplinary backgrounds and different data standards. For more information, consult the NSF press release and the Award abstract.
Credentialing Maine Adults for Transition into Careers in Information Systems and Spatial Informatics
The University of Maine System (UMS) has declared workforce development for Maine’s existing businesses and citizens a high priority. Among initiatives supported is one to expand the information system, computing, and computer science skills of employees working for Maine companies and organizations. Through a proposal submitted by Professor Harlan Onsrud, UMS is funding tuition grants/scholarships for up to twenty newly admitted graduate students living in Maine for one online course each semester in Fall 2019 and Spring 2020. Almost all of the slots were filled for the Fall semester in this critical-needs area. The slots were filled primarily by Maine school teachers desiring advanced computing skills to better teach coding to middle and high school students and by persons employed in Maine desiring to advance their abilities to serve better their companies or agencies.
Several additional tuition grants are likely to be available starting in January 2020 for persons applying to the online Graduate Certificate Programs in Information Systems or Geographic Information systems or the online MS Information Systems or MS Spatial Informatics programs. These programs have been designed to accommodate college graduates from wide-ranging academic backgrounds. The distance courses allow students to view lectures and complete assignments each week on their own schedule.
For more information, consult the Maine Workforce Flier, the Maine Teachers Flier, or contact Professor Onsrud directly.
Integrating Computing into Science Teaching and Learning in Grades 6-8
This exploratory integration project is an interdisciplinary partnership among teachers, administrators, education researchers, and UMaine STEM and STEM Education faculty, including those from the School of Computing and Information Science. This group will develop, implement, investigate, and refine a model to integrate computing into middle school science and study the essential elements of teacher professional learning and curricular support needed for successful integration. Future teachers from UMaine’s Master of Science in Teaching (MST) Program will work with the partnership on the develop of a comprehensive module for each of grades 6-8 aligned with Computer Science Teachers Association Standards and tied to the use of real, relevant data for students at the middle level in rural communities. Teachers, and then their students, will experience, first-hand, how computing skills and computational thinking enable them to tackle new types of important, complex problems and develop more realistic models of significant phenomena.
Rigorous research and evaluation will contribute to broader knowledge of how to support teachers as computing is integrated into STEM teaching and learning. Findings will be presented and published for the research and practitioner communities and will also be disseminated to community members in partnering districts and other stakeholders. The classroom implementation will be studied to understand the contributions that the integration of computing with STEM makes to students’ learning of science and computing and their attitudes toward STEM careers, with particular attention to gender and engaging students from economically challenged communities.
The Principal Investigator for the $1,250,000 NSF project is Susan R. McKay, Professor of Physics and Director of the Maine Center for Research in STEM Education (RiSE Center), University of Maine. Professor Harlan Onsrud serves as Co-PI along with 3 others. Additional investigators affiliated with SCIS funded by the project include professors Torsten Hahmann , Nimesha Ranasinghe, and Constance Holden. Dr. Penny Rheingans serves on the Advisory Board.
A Remote Multimodal Learning Environment to Increase Graphical Information Access for Blind and Visually Impaired Students
Dr. Nicholas Giudice serves as Principal Investigator with Co-PIs including Dr. Justin Dimmel, UMaine, and Dr. Stacy Doore, Bowdoin College who received a $747,894 National Science Foundation grant to assist students who are blind or visually impaired (BVI) in accessing complex STEM graphical information in the classroom or workplace.
To address these issues, this project will investigate the development and evaluation of an innovative remote learning system based on the use of multiple sensory channels to strategically present information from auditory, linguistic, touch, and enhanced visual sensing. The research will focus specifically on the optimization of multimodal information presentation and perception, separating sensory output based on its unique information processing characteristics for conveying different types of stimuli.
The first project goal is to increase the quality of STEM instruction for BVI students by determining perceptually motivated learning supports that promote non-visual knowledge acquisition of STEM graphical and spatial information (learning goal). The second project goal is to increase access to graphical and spatial STEM content through creation of an innovative remote multimodal interface for communicating the conceptual meaning of visual information (technology goal).
The project outcomes will contribute to theories of non-visual learning and multisensory processing, and a clear translational path to development of more efficient, intuitive, and usable multimodal interfaces for both blind and sighted users. The application of the results will help to address the severe under-representation of BVI individuals in STEM-related disciplines, and the 70% unemployment rate of this demographic, by providing a new, low-cost, and accessible technology platform for communicating non-visual graphical STEM materials.
Development of a Multimodal Interface for Improving Independence of Blind and Visually-Impaired People
Dr. Richard Corey (https://umaine.edu/vemi/people/richard-corey/) serving as the UMaine Principal Investigator with Hari Palani as the (Unar Labs) Principal Investigator, receive $225,000 National Science Foundation grant to develop a multimodal interface to improve independence of Blind and Visually-Impaired people.
The broader impact/commercial potential of this project will be to promote empowerment of millions of blind and visually-impaired (BVI) people by enabling greater independence, supporting increased educational attainment, proliferation of vocational opportunities, and enhancing their overall quality of life. There are currently no commercial solutions for providing BVI users with an assistive technology (AT) solution that allows BVI users to seamlessly access textual and graphical information via a unified system. Towards meeting this greater goal, this Phase I SBIR project addresses key challenges relating to technical feasibility in creating the core algorithms of Midlina and the functional viability proving that BVI users will find practical utility in its application.
Given that vision loss is expected to double in the next 20 years owing to age-related eye diseases experienced by the rapidly aging population, this project will have significant economic benefits for the State/Federal agencies providing support services to BVI and aging population.
For more information on the research, consult the VEMI Lab website.
Preservation and Access Research and Development
Dr. Nicholas Giudice serves as Principal Investigator with Dr. Richard Corey, UMaine, and Mark Williams, and
John Bell, Dartmouth College, receive a $277,439 National Endowment for the Humanities grant to develop processes and guidelines supporting the delivery of annotated archival video to the higher education community with a particular focus on blind and visually impaired (BVI) users.
The Accessible Civil Rights Heritage (ACRH) Tier II project will research the creation, curation, and consumption of online humanities collections by developing a test corpus of culturally significant newsfilm on American civil rights, dating from the 1950s to the 1980s. ACRH will then combine the deep knowledge of experts on the era with the work of archivists and human-cognition researchers to develop new cataloging and access procedures that deliver high-quality, meaningful experiences to BVI users about culturally significant material. The team will produce evidence-based accessibility guidelines and software that will be published as open resources for use by educators and archivists.
For more information on the research, consult the VEMI Lab website.