Electronic Thesis/Dissertation


A Predictive Analytical Model for Predicting Munitions Surface Clearance Decontamination Activities Open Access

Downloadable Content

Download PDF

Abstract of PraxisA Predictive Analytical Model for Predicting Munitions Surface Clearance Decontamination Activities Unexploded ordnance contamination in the United States and its Territories has emerged as one of the nation's most significant environmental problems in 2001 and remains a serious environmental concern today. The locations, quantities, depths, and types of munitions remaining and areal extent of contamination at former live-fire training sites are currently unknown and unaccounted for. Site decontamination cleanup often takes longer to complete, necessitates more regulatory attention, and requires significantly more financial investment than anticipated.The objective of this praxis was to develop a predictive analytics model using multiple regression techniques as a tool for project managers, program managers, field supervisors, and decision makers engaged in munitions response action planning, estimating, and field operations. The application to assist project and program managers in predicting munitions surface clearance rates for the clearance and decontamination of munitions items and munitions-related debris is aimed to support pre-bid decision making in acquisition opportunities, resource and operations planning, and management of ongoing field operations for surface decontamination activities. A forecasting tool will provide for additional risk management oversight to help minimize estimating and operational risks. The model examines the munitions response predictor variables that are significant or not significant in predicting the weekly number of surface acres decontaminated of munitions and munitions-related contamination. Model fitting procedures converged upon a final model able to be used to predict surface acre clearance.

Author Language Keyword Date created Type of Work Rights statement GW Unit Degree Advisor Committee Member(s) Persistent URL