Leap-frogging the digital divide
There’s power in mapping. Maps mean recognition – an acknowledgment that communities exist and have needs. To be on the map is to be counted for support and input and partnership and investment. Open and accessible maps are mission critical for governments and humanitarians to get much needed relief and development assistance to every community in need. With recent breakthroughs in cloud computing and computer vision alongside increasing availability of high-resolution satellite imagery, it is possible to map every household remotely and deploy such a capability quickly to keep datasets up to date. These emerging technologies offer significant potential for humanitarian purposes – especially during a crisis. Beyond the technological capabilities, though, is an important question of who. Who should have access and own these tools? Who is building them and tailoring them for specific country contexts? Who is deploying these tools? Who is making decisions based on this data? Whose lives are affected by this technology?
Democratizing Artificial Intelligence
With sub meter resolution satellite imagery, it is possible to accurately delineate a building. Manual digitization of satellite imagery has long supported humanitarian missions and such approaches can empower communities to produce their own maps. However, a labor-intensive approach like that does not scale quickly, and during an emergency response, manual digitization also requires people to coordinate and manage those campaigns, diverting key resources to solve for data gaps. Accessing timely, accurate data at a household level is still a challenge in many low-and-middle-income countries. In many cases, such data gaps are never addressed, and humanitarian decisions are made with major information asymmetries across communities.
Our team aspires to turn over control of the data value chain to users in-country along with their in-country humanitarian partners. Our Replicable AI for Microplanning (ramp) project is producing an open-source deep learning model to accurately digitize buildings in low-and-middle-income countries using satellite imagery as well as enable in-country users to build their own deep learning models for their regions of interest. These digital microplans are detailed maps depicting primary health centre catchment areas for service delivery planning.
What are the primary use-cases for this AI model and the resulting building footprints?
- Provision of goods and services includes our microplanning use case and the delivery of vaccines for the ongoing pandemic response but also extends to other health programs as well as planning of rural electrification or roads or cash assistance and much more. Building-level datasets are an important input for planning and delivery of services to every household.
- Risk exposure. Knowing where people live and work is critical to assessing current and future risk. Having data on our human footprint is necessary to truly understand our vulnerabilities and risks and possible scenarios.
- Validation of existing data. Building footprints complement other datasets in many ways, including the ability to validate locations and improve existing data to make it more interoperable and analyzable with other datasets.
- Population density is one of the most important statistics for development efforts across many sectors; however, many countries still lack complete, up-to-date census data. Building counts and locations allow modelers and statisticians to accurately estimate and distribute populations.
- Sampling for household surveys and mobile data collection campaigns. Especially in rural areas where obtaining information on household location is difficult, individual building footprints are valuable, and given how quickly communities are growing, being able to update those buildings data layers with an open-source model is a sustainable solution.
While technological advances have opened new windows of opportunity to scale AI-driven applications, the ongoing pandemic is an urgent reminder of the need for equitable health outcomes. In partnership with WHO, ramp is producing an open-source deep learning model to accurately map buildings – buildings that represent people who need vaccines and access to clinics. As another tool in our emergency management repertoire, the ramp project will hopefully accelerate decisions and improve health outcomes from mitigation to preparedness to response to recovery.
Want to learn more about the ramp project? Visit the RAMP website and stay tuned for future blog posts.
Read the next blog in this series: “Creating our on-ramp: how to train a hungry AI model“>>>
Ravi Shankar supports the WHO GIS Center for Health in the Data, Analytics, and Impact for Delivery unit of the World Health Organization after serving for many years as the GIS Technical Office of the Global Polio Eradication Initiative (GPEI). Previously, he was involved in the Ebola response where he played a key role in the creation of a Global Mapping platform for WHO to portray the situational update of the outbreak. Before joining WHO, as a GIS Analyst in UNOSAT, he was involved in Emergency Response mapping, situational awareness, capacity building & training. He also designed a Master’s level Course on GIS for the Disaster Management Degree Programme at Copenhagen University. The Haiti earthquake, the Thailand floods, the Syrian Crisis, and the Libyan War are a few of the projects he worked on during his career. He started his career as an Architect-Urban Planner involved in the creation of the master plan of Libya and Port Blair
Rhiannan Price is a Principal Consultant and Managing Director of Inclusive and Sustainable Development at DevGlobal Partners. Rhiannan has over 15 years’ experience working at the intersection of technology and development, leveraging Artificial Intelligence, very high-resolution satellite imagery, crowdsourcing, and other digital tools in support of the UN Sustainable Development Goals. She’s passionate about the potential for technology to break down our siloes and help us leapfrog to a more resilient, sustainable world.