Result of ablation experiment.

Petroleum hydrocarbon pollution causes significant damage to soil, so accurate prediction and early intervention are crucial for sustainable soil management. However, traditional soil analysis methods often rely on statistical methods, which means they always rely on specific assumptions and are sensitive to outliers. Existing machine learning based methods convert features containing spatial information into one-dimensional vectors, resulting in the loss of some spatial features of the data. This study explores the application of Three-Dimensional Convolutional Neural Networks (3DCNN) in spatial interpolation to evaluate soil pollution. By introducing Channel Attention Mechanism (CAM), the model assigns different weights to auxiliary variables, improving the prediction accuracy of soil hydrocarbon content. We collected soil pollution data and validated the spatial distribution map generated using this method based on the drilling dataset. The results indicate that compared with traditional Kriging3D methods (R2 = 0.318) and other machine learning methods such as support vector regression (R2 = 0.582), the proposed 3DCNN based method can achieve better accuracy (R2 = 0.954). This approach provides a sustainable tool for soil pollution management, supports decision-makers in developing effective remediation strategies, and promotes the sustainable development of spatial interpolation techniques in environmental science.石油烃污染会对土壤造成严重破坏，因此精准预测与早期干预对于土壤可持续管理至关重要。然而，传统土壤分析方法多依赖统计建模思路，这类方法往往需依托特定预设假设，且对异常值较为敏感。现有的基于机器学习的方法会将包含空间信息的特征转换为一维向量，导致数据的部分空间特征丢失。本研究探究了三维卷积神经网络（Three-Dimensional Convolutional Neural Networks, 3DCNN）在空间插值领域的应用，以开展土壤污染评估。通过引入通道注意力机制（Channel Attention Mechanism, CAM），模型可为辅助变量分配差异化权重，进而提升土壤烃类含量的预测精度。本研究收集了土壤污染数据集，并基于钻孔数据集对该方法生成的空间分布预测图进行了验证。实验结果表明，相较于传统三维克里金法（R²=0.318）以及支持向量回归等其他机器学习方法（R²=0.582），本研究提出的基于3DCNN的方法可实现更优的预测精度（R²=0.954）。该方法可为土壤污染管理提供可持续的技术工具，辅助决策者制定高效的修复策略，并推动空间插值技术在环境科学领域的可持续发展。