Radiant Earth Foundation Presents at IMED
Open Source Geospatial Data, Analysis Tools and The Art of the Possible & Open Source Satellite Imagery and Machine Learning Tools to Inform Infectious Disease Research
By Victoria M. Gammino, Chief Science Officer, Radiant Earth Foundation
The Radiant Earth Foundation had the privilege of participating in the 2018 International Meeting on Emerging Diseases (IMED), a biennial conference hosted by the International Society for Infectious Diseases, November 9–12th in Vienna, Austria.
The IMED conferences bring leading scientists, clinicians and policy makers to Vienna to present new knowledge and breakthroughs and discuss how to discover, detect, monitor, understand, prevent, and respond to outbreaks of emerging pathogens. Since its inception, IMED has been a summit that unifies public health practitioners’ approach to pathogens in the broadest ecological context. Drawing together human, veterinary, and environmental health specialists, IMED serves as a true One Health forum where those working in diverse specialties and diverse regions can meet, discuss, present and challenge one another with findings and new ideas.
Radiant Earth Foundation’s Chief Science Officer, Dr. Victoria M. Gammino, organized a symposium entitled Open Source Geospatial Data, Analysis Tools and The Art of the Possible. Radiant Earth Foundation also hosted a workshop led by our Lead Geospatial Data Scientist, Dr. Hamed Alemohammad on Open Source Satellite Imagery and Machine Learning Tools to Inform Infectious Disease Research. This workshop aimed to introduce participants to remote-sensing capabilities that support disease surveillance, program planning, evaluation, research design, and modeling.
The presentations for both the symposium and workshop can be found below:
Symposium: Open Source Geospatial Data, Analysis Tools and The Art of the Possible.
Four speakers examined how remotely sensed Earth observation data and machine learning tools can help researchers detect, monitor, understand, predict, prevent, and respond to diseases. These included:
- Victoria M Gammino, Ph.D., MPH, Radiant Earth Foundation: Innovations and Challenges in the Use of Open-source Remote Sensing Data and Tools.
- Kebede Deribe, Ph.D., MPH, Wellcome Trust Brighton and Sussex Centre for Global Health Research, Brighton and Sussex Medical School, Brighton, UK and School of Public Health, Addis Ababa University, Addis Ababa, Ethiopia: The use of remote sensing, geostatistical and machine learning methods in neglected tropical diseases surveillance — the case of podoconiosis and lymphatic filariasis.
- Yoshinori Nakazawa, Ph.D., Poxvirus Branch, US Centers for Disease Control and Prevention: Mapping Monkeypox risk in the Congo Basin using Remote Sensing and Ecological Niche Models.
- RajReni Kaul, Doctoral candidate, Odum School of Ecology, University of Georgia: Predicting spatiotemporal risk of yellow fever using a machine learning approach.
Workshop: Open Source Satellite Imagery and Machine Learning Tools to Inform Infectious Disease Research
The four speakers of the workshop addressed the role of topical, relevant, and quality geospatial data; the tools and knowledge required to deploy fundamental geospatial processes; the role of machine learning (ML) in analyzing remotely-sensed data. Topics included population estimation using building footprints derived from satellite imagery, machine-learning tools, and strategies such as automated change detection for land cover analysis/ habitat change. The instructor presentations can be found below.
- Hamed Alemohammad, Ph.D., Lead Geospatial Data Scientist, Radiant Earth Foundation: An intro to Remote Sensing and Machine Learning.
- Yoshinori Nakazawa, Ph.D., Poxvirus Branch, US Centers for Disease Control and Prevention: Landcover/habitat.
- Kebede Deribe, Ph.D., MPH, Brighton, and Sussex Medical School, and, School of Public Health, Addis Ababa University: Predicting the environmental suitability of podoconiosis in Ethiopia.
- Vincent Seaman Ph.D., Senior Program Officer, Polio Eradication Program, Bill and Melinda Gates Foundation: Modeled Population Estimates from Satellite Imagery and Microcensus Data.