A prediction model for soil heavy metal content based on improved tensor completion

As socio-economic activities intensify, soil heavy metal pollution increasingly threatens both the environment and human health. This paper presents a novel method for predicting soil heavy metal content using an advanced tensor completion algorithm. The proposed method estimates heavy metal concentrations at unsampled locations by constructing a prediction model within the Coarse-to-Fine (C2F) framework, leveraging data from sampled points. To enhance prediction accuracy, the method incorporates total variation as a complementary regularization technique alongside low-rank constraints, addressing limitations in traditional tensor completion approaches. The improved algorithm is seamlessly integrated into both the coarse and fine stages of the C2F framework, effectively balancing the recovery of low-rank and high-rank components, and significantly improving the accuracy of heavy metal content predictions.