# Transfer Learning-Based Interpretable Soil Lead Prediction in the Gejiu Mining Area, Yunnan

## TL;DR

This study uses transfer learning and SHAP analysis to accurately predict soil lead content in a mining area with limited data.

## Contribution

A novel transfer learning framework with SHAP interpretability for soil Pb prediction under small sample constraints.

## Key findings

- The ResNet-pH-Pb model achieved an R2 of 0.77, outperforming traditional methods like PLS-Pb and SVM-Pb.
- SHAP analysis identified key wavelengths retained for pH and optimized for Pb prediction.
- The approach provides a theoretical basis for understanding spectral prediction mechanisms.

## Abstract

Accurate prediction of soil lead (Pb) content in small sample scenarios is often limited by data scarcity and variability in soil properties, with traditional spectral modeling methods yielding suboptimal precision. To address this, we propose a transfer learning-based framework integrated with SHAP analysis for predicting soil Pb content in the Gejiu mining area, Yunnan. Using pH data from the European LUCAS soil database as the source domain, spectral features were extracted via a 1D-ResNet model and transferred to the target domain (130 soil samples from Gejiu) for Pb prediction. SHAP analysis was applied to clarify the role of spectral characteristics in cross-component transfer learning, uncovering shared and adaptive features between pH and Pb predictions. The transfer learning model (ResNet-pH-Pb) significantly outperformed direct modeling methods (PLS-Pb, SVM-Pb, and ResNet-Pb), with an R2 of 0.77, demonstrating superior accuracy. SHAP analysis showed that the model retained key pH-related wavelengths (550–750 nm and 1600–1700 nm) while optimizing Pb-related wavelengths (e.g., 919 nm and 959 nm). This study offers a novel approach for soil heavy metal prediction under small sample constraints and provides a theoretical basis for understanding spectral prediction mechanisms through interpretability analysis.