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

TL;DR

This paper introduces a machine learning-enhanced multi-criteria decision-making framework for optimal sawmill site selection, validated through a case study in Mississippi, highlighting key influencing factors and suitability mapping.

Contribution

It presents a novel integrated ML and GIS-based decision model for sawmill location, demonstrating its effectiveness with multiple algorithms and a real-world case study.

Findings

Random Forest achieved the highest accuracy among tested models.

Supply-Demand Ratio was identified as the most influential criterion.

Approximately 10-11% of Mississippi landscape is highly suitable for sawmills.

Abstract

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.