Data farming and defense applications

Abstract

Data farming uses simulation modeling, high performance computing, experimental design, and analysis to examine questions of interest with large possibility spaces. This methodology allows for the examination of whole landscapes of potential outcomes and provides the capability of executing enough experiments so that outliers might be captured and examined for insights. It can be used to conduct sensitivity studies, to support validation and verification of models, to iteratively optimize outputs using heuristic search and discovery, and as an aid to decision-makers in understanding complex relationships of factors. In this paper we will describe efforts at the Naval Postgraduate School in developing these new and emerging tools. We will also illustrate data farming in the context of application to questions inherent in military decision-making. The particular application we present here is social network modeling to support the countering of improvised explosive devices.