DigitalGlobe, a Maxar Technologies company, with support from Amazon Web Services, is pleased to announce the winners of the GBDX for Sustainability Challenge. From over 70 submissions, these are the top five teams proposing bold ideas using geospatial big data in support of the Sustainable Development Goals. Each team will have two months to build out their respective projects, and our judges will select an overall winner in April. Maxar and its four industry-leading space technology businesses—DigitalGlobe, SSL, MDA and Radiant Solutions—are committed to fulfilling our purpose by accelerating innovation that has the potential to address global challenges and creating the connections and intelligence that power a better world.
Mapping Schools to reduce the Digital Divide in Education
UNICEF, Big Pixel Initiative at UC San Diego, Development Seed
UNICEF is mapping every school in the world and building a visualization tool to show their connectivity in real-time (www.projectconnect.world). Having this base layer of information allows us to know what are the connectivity and infrastructure gaps that we need to address in order to improve children’s access to information and education. It also allows us to do many other things such as measuring vulnerabilities and improving our emergency response and resilience against natural disasters and crises.
Partnering with Development Seed and UC San Diego's Big Pixel Initiative, we are developing Convolutional Neural Network-based classification algorithms which take advantage of underlying patterns recognized from the very high resolution satellite imagery to extract school locations. The results of this project including the classification algorithms and analysis based on the data product will be shared through our open-source data platform, Magic Box.
------------------------------------------------------------------------------------------------------------------------------
Using high-resolution satellite imagery and computer vision to build an open database of global power plants
World Resources Institute, Duke University
Providing clean, affordable energy is one of the most important challenges the world faces today, as highlighted in Sustainable Development Goal 7 (Affordable and Clean Energy). Achieving it will require a range of actions, many of which depend on a detailed analysis of the electric power sector. Unfortunately, data about the power sector is limited or lacking in many countries, or only available in proprietary formats. The World Resources Institute (WRI) and Duke University will apply computer vision algorithms to high-resolution satellite imagery provided by DigitalGlobe to geo-locate and characterize wind and solar power generation facilities around the world. Information about these power plants is especially important to show how rapidly the power sector is changing. The data will be aggregated and released in open format, to support applications including energy sector transition planning, grid integration of renewable power, and clean energy public education.
------------------------------------------------------------------------------------------------------------------------------
Global Green City Watch
Ernst & Young, Cornell University, Metabolic, Geodan, Trinity College Dublin, University College Dublin, University of Amsterdam, University of Toronto
Urban green space is the backbone of a sustainable city and a widely cited indicator to assess urban environments. Greenery helps restore mental and physical well being and offers vital ecosystem services such as improving air quality, reducing urban temperatures, sequestering carbon, and storing excess rain water. The challenges of rapid urbanization can easily be addressed by adding green space in cities, but quantity does not necessarily translate to quality. Global Green City Watch (GGCW) combines computer vision and object-based image analysis on high resolution satellite imagery to enable citizens and local governments to understand the quality of urban green space across the world ‒ empowering them to make evidence-based decisions about and improve the functioning of critical green space.
------------------------------------------------------------------------------------------------------------------------------
Monitoring Economic Activity in Large-Scale Industrial Areas
London School of Economics, University of Oxford
The ‘Monitoring Economic Activity in Large-scale Industrial Areas’ project will identify, characterize and quantify large-scale industrial infrastructure in Africa to help inform and monitor their economic activity, and contribute towards UN SD Goal 9 (Industry, Innovation and Infrastructure). The team, led by Neeraj Garg Baruah (LSE) and Julia Bird (Oxford), proposes to build on the mapping of African urban industrial areas in the ‘Urbanisation in Developing Countries’ project based at the London School of Economics and Oxford University in two ways: characterize the different industrial areas (functional expansion), and GBDX platform would help apply this to all African cities and also rural areas (geographic expansion). The intended outcomes include a spatial mapping data layer of where industrial infrastructure are located in Africa and a spatial decision support system to help policy-makers monitor the functional and economic health of these areas.
------------------------------------------------------------------------------------------------------------------------------
Deforestation Intelligence for Cerrado
20tree.ai
20tree.ai is a Portuguese planet tech startup that provides forest intelligence. In the GBDX for Sustainability Challenge, 20tree.ai will use DigitalGlobe's very high resolution satellite imagery and SAR data to train AI models. These models will be used to detect deforestation, for instance illegal logging and expansion of agriculture. Their project will publish actionable forest insights, trends and predictions on one of the most threatened regions of Brazil: the Cerrado. The project aims to contribute to the Sustainable Development Goals of the United Nations: life on land, no poverty and climate action