Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 11, 2026Land Degradation and Development

Unveiling the Advantages of UV −Vis/ NIR − pXRF Data Fusion for Precise Estimation of Soil Heavy Metals in Farmland

View Full Paper
Ask AI
Bookmark
Share

Authors

SGSusu GaoXinjiang UniversityXLXiaofeng LiChangchun University of Science and TechnologyJDJianli DINGXinjiang Institute of Engineering

Discussion

Loading...

Member takes

Implication

The study investigates data fusion techniques to enhance soil heavy metal estimation accuracy in farmland, indicating significant implications for environmental safety.

Key Points

  • The research aims to enhance the estimation accuracy of soil heavy metal concentrations using integrated spectral data from different sources.
  • Analyzed soil samples using UV, Vis-NIR, and pXRF technologies.
  • Employed seven preprocessing methods to improve spectral data quality.
  • Applied principal component analysis for feature dimension reduction.
  • Implemented three fusion strategies and four machine learning models for prediction.
  • The best-performing fusion strategy was PCFMS-SAM for modeling heavy metals.
  • Random Forests achieved R²=0.92 for arsenic, R²=0.79 for cadmium with VPPSO-SVM, and R²=0.84 for lead using RF-XGB.
  • All optimal models showed strong consistency with correlation coefficients above 0.8.

Cite This Study

Gao et al. (2026) studied this question.

synapsesocial.com/papers/698c1cd3267fb587c655f8b6https://doi.org/10.1002/ldr.70488
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched one closely related paper. Consider it for comparative context:

  1. 1Computer Aided Design of Experiments1969 · 3,492 citations