Chasing the Timber Trail: Machine Learning to Reveal Harvest Location Misrepresentation

TL;DR

Illegal logging and misrepresentation of timber origin threaten biodiversity and climate stability. The authors propose an end-to-end ML pipeline that fuses stable isotope ratios (SIRA) with atmospheric data through a multi-task Gaussian process framework to infer harvest location with uncertainty estimates. Comparative results show improved accuracy and credible uncertainty handling over baselines, and deployment to European enforcement agencies demonstrates practical impact for origin verification and sanctions compliance. The approach yields interpretable feature importance and isoscape-based insights, with potential to generalize to other organic products under regulatory regimes like the EU Deforestation Regulation.

Abstract

Illegal logging poses a significant threat to global biodiversity, climate stability, and depresses international prices for legal wood harvesting and responsible forest products trade, affecting livelihoods and communities across the globe. Stable isotope ratio analysis (SIRA) is rapidly becoming an important tool for determining the harvest location of traded, organic, products. The spatial pattern in stable isotope ratio values depends on factors such as atmospheric and environmental conditions and can thus be used for geographic origin identification. We present here the results of a deployed machine learning pipeline where we leverage both isotope values and atmospheric variables to determine timber harvest location. Additionally, the pipeline incorporates uncertainty estimation to facilitate the interpretation of harvest location determination for analysts. We present our experiments on a collection of oak (Quercus spp.) tree samples from its global range. Our pipeline outperforms comparable state-of-the-art models determining geographic harvest origin of commercially traded wood products, and has been used by European enforcement agencies to identify harvest location misrepresentation. We also identify opportunities for further advancement of our framework and how it can be generalized to help identify the origin of falsely labeled organic products throughout the supply chain.

Figures (5)

• Figure 1: ML Pipeline for SIRA
• Figure 2: Atmospheric Feature Importance
• Figure 3: Inter-task Dependency
• Figure 4: Success Rate of identifying false claim vs distance from true origin
• Figure 5: Case Study: Isoscapes for Eastern European Region-Ukraine/Russia Border for timber