World Modelers

Funding Agency:
Defense Advanced Research Projects Agency

DARPA is soliciting innovative research proposals in the area of causal modeling, forecasting, and analysis techniques.  Proposed research should investigate innovative approaches that enable revolutionary advances in science, mathematics, or technology.  Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice.

The purpose of the World Modelers program is to develop technology that will enable analysts to rapidly build models to analyze questions relevant to national and global security. Questions for analysis will typically be framed at subnational scales and look one to five years into the future, although the factors that influence outcomes of interest might operate on larger spatial and temporal scales. 

Food insecurity is a growing problem in many parts of the world where societies struggle to feed growing populations.  Food insecurity has both humanitarian challenges and regional security ramifications, as food shortages can result in migration/displacement and conflict between peoples.  Food insecurity will be the initial use case for the World Modelers program, and World Modelers technologies will enable researchers to efficiently and rigorously perform analytic tasks such as “Analyze food insecurity in each district of South Sudan two years into the future.”   World Modelers technologies will be applied to additional (and increasingly varied) use cases as they mature through a sequence of program phases.

The subnational focus of World Modelers reflects the changing nature of conflict and security, which, increasingly, plays out in cities and districts.  Analysis at larger scales produces generalities (e.g., Sub-Saharan Africa is likely to go hungry) rather than targeted recommendations (e.g., increasing security in South Sudan will allow internally displaced farmers to return to their fields).  As to temporal scale, World Modelers is committed to evaluating the accuracy of its forecasts, so use cases that forecast one to five years into the future are preferred.

Proposal Due Date:  May 11, 2017

Agency Website

Areas of Interest

The five technical areas for the World Modelers solicitation are:

  • TA1:  Build Qualitative Models from Online Sources.  Machine-assisted construction of comprehensive, targeted, causal, qualitative, analysis graphs.  "Which factors should be in a particular analysis and how are they related?"
  • TA2:  Workflow Compiler (for Integration of Quantitative Models).  Machine-assisted marriage of qualitative with quantitative analysis.  "Which quantitative models should be in the analysis and how do they connect to each other and run in a common computational environment?"
  • TA3:  Parameterize Models.  Machine-assisted foraging for data from multiple sources, machine-assisted translation of available data into proxies for required parameters. "Where are the data to parameterize quantitative models, and what are the mappings between available data and required parameters?"
  • TA4:  From Scenarios to Actions.  Interfaces for humans to specify scenarios, machine-assisted recommendation and testing of interventions. "What will be the effects of particular actions under particular conditions?"
  • TA5:  Uncertainty Reports.  Machine-assisted, thorough analysis of sources of uncertainty and efforts to reduce it. "Can the analysis be trusted, and what can be done to improve it?"

Eligibility Requirements

DARPA welcomes engagement from all responsible sources capable of satisfying the Government's needs, including academia (colleges and universities); businesses (large, small, small disadvantaged, etc.); other organizations (including non-profit); entities (foreign, domestic, and government); FFRDCs; minority institutions; and others.  

Funding Type

Grant

Eligibility

Faculty

Category

Engineering and Physical Sciences
International Opportunities
Social Sciences

External Deadline

May 11, 2017