We describe a computational approach to remote sensing image analysis that addresses many of the classic problems associated with storage, search, and query. This process starts by automatically annotating the fundamental objects in the image data set that will be used as a basis for an ontology, including both the objects (such as building, road, water, etc.) and their spatial and temporal relationships (is within 100 m of, is surrounded by, has changed in the past year, etc.). Data sets that can include multiple time slices of the same area are then processed using automated tools that reduce the images to the objects and relationships defined in an ontology based on the primitive objects, and this representation is stored in a geospatial-temporal semantic graph. Image searches are then defined in terms of the ontology (e.g. find a building greater than 103 m2 that borders a body of water), and the graph is searched for such relationships. This approach also enables the incorporation of non-image data that is related to the ontology. We demonstrate through an initial implementation of the entire system on large data sets (109 - 1011 pixels) that this system is robust against variations in di?erent image collection parameters, provides a way for analysts to query data sets in a more natural way, and can greatly reduce the memory footprint of the search.
As Sandia National Laboratories serves its mission to provide support for the security-related interests of the United States, it is faced with considering the behavioral responses that drive problems, mitigate interventions, or lead to unintended consequences. The effort described here expands earlier works in using healthcare simulation to develop behavior-aware decision support systems. This report focuses on using qualitative choice techniques and enhancing two analysis models developed in a sister project.
This is the final report for a LDRD effort to address human behavior in decision support systems. One sister LDRD effort reports the extension of this work to include actual human choices and additional simulation analyses. Another provides the background for this effort and the programmatic directions for future work. This specific effort considered the feasibility of five aspects of model development required for analysis viability. To avoid the use of classified information, healthcare decisions and the system embedding them became the illustrative example for assessment.
The need to anticipate the consequences of policy decisions becomes ever more important as the magnitude of the potential consequences grows. The multiplicity of connections between the components of society and the economy makes intuitive assessments extremely unreliable. Agent-based modeling has the potential to be a powerful tool in modeling policy impacts. The direct mapping between agents and elements of society and the economy simplify the mapping of real world functions into the world of computation assessment. Our modeling initiative is motivated by the desire to facilitate informed public debate on alternative policies for how we, as a nation, provide healthcare to our population. We explore the implications of this motivation on the design and implementation of a model. We discuss the choice of an agent-based modeling approach and contrast it to micro-simulation and systems dynamics approaches.