Anticipating Future Events in a Multi-Threat Environment by Expanding the Capabilities of Flow Field Forecasting
Abstract
Flow field forecasting (FFF), a statistical learning methodology introduced by Kyle Caudle and Michael Frey in 2011, has a mix of technical capabilities—model independence, autonomous operation, computational efficiency—that no standard general-purpose forecasting tool can match. The principle investigator, Kyle Caudle, provides combined expertise in mathematics, statistics and computer science. He also has experience as a naval leader and as a military consultant. In today’s battle space, incoming threats are very often difficult to ascertain. Additionally, these threats are continually evolving at such a high rate of speed that allocation of assets by military leaders is exceedingly challenging. In such situations forecasting can reduce uncertainty and dramatically enhance the mission-effectiveness of resource allocation. We are proposing to expand the current capabilities of FFF. This project will continue the work that was started last year under this same grant opportunity. Our focus will be to systematically tackle the multivariate forecasting problem by enhancing the automatic history selection feature. We are proposing to meet this objective through the use of classification and regression trees (CART). This enhanced capability will give flow field forecasting the ability to more readily adapt to the changing structure of the data stream. Meeting this objective will provide the U.S. Navy a more complete understanding of the battle space environment, and thus it will provide significant improvement to both Maritime Mission Planning and Sensor Management and Allocation. Beyond the Navy and defense applications, FFF’s potential can be realized throughout many public sectors – including network communications, agriculture, safety, and energy.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 11, 2016
- Source ID
- N002441610016
Entities
People
- Kyle Caudle
Organizations
- South Dakota School of Mines and Technology