Predictive Modeling of Dining Facility Waste by Material Type Across Time and Geography

Abstract

Abstract Solid waste generation is increasing at alarming rates, globally, with widespread challenges to decreasing generation and landfill disposal. U.S. Army installations are a unique basis for providing qualitative and quantitative data from a breadth of geographical locations. Modeling prediction capability of dining facility (DFAC) solid waste streams using data from 11 Army installations was investigated to demonstrate aggregate building and material type generation forecasting. Solid waste generation data was collected by quantifying potentially divertible materials (e.g., source reduction, reuse, recycling, composting, etc.) that are currently being landfilled. Over one week, samples from one day of DFAC operations were obtained for each installation. Materials were separated into 22 categories, weighed, and recorded. Results identified many materials with diversion potential in the solid waste stream. Five material types were down selected for model construction and validation based on robustness of data available and applicability outside military contexts. Models were constructed for each material type combination to avoid multiplication factor errors of coefficients for each independent variable. Results showed statistical significance (p-value ≤ 0.05) for 4 of 5 modeling combination predictions, indicating that these 4 models for each material type are uniquely capable of predicting solid waste generation. Each of the 4 statistically significant models differed in adjusted R-squared values, ranging from 0.988 to 0.996. This study provides models with predictive power that could reduce the labor- and cost-intensive process of characterizing waste streams while increasing data availability across the continental U.S. to focus targeted source reduction efforts for dining settings. CLASSIFICATION CODE MSC: 62, 92 JEL: I28, Q01, Q20, Q28, Q53