Learning-Based Multi-Criteria Decision Making Model for Sawmill Location Problems

Strategically locating a sawmill is vital for enhancing the efficiency, profitability, and sustainability of timber supply chains. Our study proposes a Learning-Based Multi-Criteria Decision-Making (LB-MCDM) framework that integrates machine learning (ML) with GIS-based spatial location analysis via MCDM. The proposed framework provides a data-driven, unbiased, and replicable approach to assessing site suitability. We demonstrate the utility of the proposed model through a case study in Mississippi (MS). We apply five ML algorithms (Random Forest Classifier, Support Vector Classifier, XGBoost Classifier, Logistic Regression, and K-Nearest Neighbors Classifier) to identify the most suitable sawmill locations in Mississippi. Among these models, the Random Forest Classifier achieved the highest performance. We use the SHAP (SHapley Additive exPlanations) technique to determine the relative importance of each criterion, revealing the Supply-Demand Ratio, a composite feature that reflects local market competition dynamics, as the most influential factor, followed by Road, Rail Line and Urban Area Distance. The validation of suitability maps generated by our LB-MCDM model suggests that 10-11% of the MS landscape is highly suitable for sawmill location.

Learning-Based Multi-Criteria Decision Model for Site Selection Problems

Strategically locating sawmills is critical for the efficiency, profitability, and sustainability of timber supply chains, yet it involves a series of complex decision-making affected by various factors, such as proximity to resources and markets, proximity to roads and rail lines, distance from the urban area, slope, labor market, and existing sawmill data. Although conventional Multi-Criteria Decision-Making (MCDM) approaches utilize these factors while locating facilities, they are susceptible to bias since they rely heavily on expert opinions to determine the relative factor weights. Machine learning (ML) models provide an objective, data-driven alternative for site selection that derives these weights directly from the patterns in large datasets without requiring subjective weighting. Additionally, ML models autonomously identify critical features, eliminating the need for subjective feature selection. In this study, we propose integrated ML and MCDM methods and showcase the utility of this integrated model to improve sawmill location decisions via a case study in Mississippi. This integrated model is flexible and applicable to site selection problems across various industries.