Understanding where people live is fundamental to understanding what people do and what their social needs are with respect to energy security; policy and urban development; resiliency; disaster and emergency response; intelligence and security; humanitarian support, as well as understanding the behavioral social dynamics. This allocation supports computational research driven by ongoing efforts where initial investigations have been conducted to explore the application of machine learning — including deep learning — toward global scale human settlement detection from high resolution satellite imagery. Several use cases including support for Federal Emergency Management Agency (FEMA)’s disaster response in the western United States, to meet specific needs of the intelligence community, and strategic resourcing for polio and malaria eradication in sub Saharan Africa by the Gates Foundation are benefiting from this work. Thus far, the approaches undertaken run well on single Graphics Processing Unit (GPU)s and small clusters, and are well positioned to exploit a resource such as OLCF’s Titan. The high resolution determination of settlements necessitates being able to dynamically produce very large datasets with fine temporal resolutions to adequately capture changes and fluxes. This problem is multi-petascale computationally and multi-petabytes in imagery data size. The successful completion of this research will produce a repeatable machine learning and image-processing pipeline that runs at continental to global scales at high resolutions and for the purposes of project sponsors, produces high resolution human settlement maps that are unprecedented in resolution and accuracy.
|Source||Hours||Start Date||End Date|