|Acquisition Program: || Objective: ||Develop a methodology to ‘stack’ a variety of data sources that can be related to a region of interest to extract structural/functional items of interest to military tactical/strategic decision making. Through the use of multiple data sources, develop a means by which sources of bias in each dataset can be mitigated.
|| Description: ||Today, successful military operations require operational decision-making that is sensitive to the socio-cultural characteristics of the local population. Such strategic decision-making, however, has been limited due to the lack of readily available population profile maps customized for the specific characteristics critical to the success
Of the mission. Adapting methodologies originally developed for advanced signal data processing, we present a revolutionary methodology for developing custom socio-cultural terrain maps optimized for specific military objectives. Using examples from Sub-Saharan Africa, Afghanistan, and Pakistan, we show that our approach of integrating
multi-disciplinary data and intelligence provides an enhanced ability to detect and amplify "weak signals" – socio-cultural characteristics of a population that may not be readily observable in any single set of observations. Such socio-cultural terrain maps
can be generated at the local and regional scales and overlain with potential military
operations to predict outcomes. They can also be used to identify areas that are becoming potential breeding grounds for extremism and conflict (Van derv ink, G., 2011)
|| ||PHASE I: Complete a literature review, feasibility study and research plan that establishes the proof of principle of the approach for improving information quality in the data stacking problem. Place this problem in the military decision making domain through selection of a suitable dataset that includes both machine and human data inputs.
Identify the critical technology issues that must be overcome to achieve success. Clearly demonstrate how subjective and objective reports can be correlated and provide methods to establish the means by which bias has been addressed and the manner in which they have been incorporated into the solution.
|| ||PHASE II: Produce a prototype method/tool/algorithm(s) capable of producing meaningful information quality advances to a problem set and that addresses sources of bias that are likely to exist in the data. Demonstrate the capability with a relevant dataset in a relevant environment that includes military subject matter experts. Develop a set of metrics that can be used to measure the improvements of this capability over standard fusion tools.
|| ||PHASE III: Produce a system capable of deployment in an operational setting of interest. Test the system in an operational setting in a stand-alone mode or as a component of larger system. The work should focus on capability required to achieve transition to program of record of one or more of the military Services. The system should provide metrics for performance assessment.
|| References: ||
Gregory E. van der Vink, Ph.D., email to Elizabeth Bowman.|
|Keywords: ||sociocultural terrain, data bias, information fusion, subjective sensor reports, objective sensor reports|
Questions and Answers:
Q:  Has a program of record been identified as a transition target? If so, what is it?
 Has phase II funding already been identified or allocated?
 Regarding the insufficiency of traditional physics based sensors as mentioned in the description, are there specific capability gaps that a successful proposal should address?
 Given that "open source data is available and plentiful," is there a particular set of data sources that are of interest? Are there any that must be included?
 One of the challenges mentions is to develop "a weighting scale ... sufficient to provide representational and inferential capabilities to the reasoning tool." Who or what is envisioned to be the provider and what requirements are there for use of the scale developed?
A: 1. Potential programs of record for transition include DCGS-A, TIGR, CPOF, and the Company Intel Support Team (COIST).
3. How to correlate various types of socio-cultural data, such as demographics, education, political, crime stats, infrastructure, agriculture, weather, economic.
4. No and No. the best scenario for one to pick is one where you can get a lot of data. If that is a city in the US, fine. If that is Afghanistan, ok. The challenge in Ph 1 and even Ph 2 is to get the data to tell a story.
5. Two kinds of inferential capabilities come to mind, 1) optimizing resources and 2) forecasting conflict. In 1), you would use data to decide how to expend a finite set of resources...do you build a school, or a hospital, or a new road, and if a road, where should it go? In 2) you might want to predict the impact of a prolonged drought...people will migrate, where will they go and what impact will a large number of people have on that area that also has limited resources?