COMMODITY BASED FREIGHT DEMAND MODELING FRAMEWORK USING STRUCTURAL REGRESSION MODEL (SRM)
Among all the freight modeling approaches, commodity-based model provides concerns on all travel modes and can capture the economic mechanisms driving freight movements. However, there are still challenges on how to effectively use public freight data and reflect the supply chain relations of various commodities. In this research, a commodity-based framework for freight demand forecasting using Structural Regression Model (SRM) is proposed and applied in California Statewide Freight Forecasting Model (CSFFM) using Freight Analysis Framework 4 data.
The framework developed in this study contains four innovative components: (1) mathematical approach for determining freight economic centroids; (2) aggregation of commodities using Fuzzy C-means clustering algorithm; (3) employing average travel distance by commodity group instead of highway skim to accurately represent real condition; (4) forecasting freight demand using Structural Regression Modeling method to comprehensively consider the direct effect, indirect effect and latent variable. The SRM is adopted in both total generation model and domestic direct demand model which combines the traditional generation and distribution steps. The application results are further compared with old CSFFM 1.0’s forecasts in 2012 to illustrate the advantages of proposed framework.