Hyperspectral Technology in Agricultural Soil Heavy Metal Detection: Current Applications and Future Directions

Ruiyi Murong

doi:10.54097/1mprcq91

Authors

Ruiyi Murong

DOI:

https://doi.org/10.54097/1mprcq91

Keywords:

Soil heavy metal pollution, Hyperspectral technology, Agricultural soil, Heavy metal element identification, Spectral feature extraction

Abstract

Soil heavy metal pollution has become a global environmental issue, posing serious threats to agricultural productivity, food safety, and human health. The emergence of hyperspectral technology provides new approaches for rapid and non-destructive detection of soil heavy metals. This paper reviews the application of hyperspectral technology in identifying heavy metal elements in agricultural soils. First, it introduces the fundamental principles of hyperspectral technology, including the relationship between soil spectral characteristics and heavy metal elements, hyperspectral data acquisition and processing, as well as spectral feature extraction and analysis methods. Then, the research progress in agricultural soil heavy metal identification using hyperspectral technology is detailed from three aspects: laboratory studies, field applications, and integrated applications with other technologies. Studies demonstrate that hyperspectral technology can achieve high-precision prediction of soil heavy metal content through interactions between soil components and heavy metals, utilizing methods such as Continuous Wavelet Transform (CWT) combined with Radial Basis Function (RBF) models. However, practical applications still face challenges including soil background interference, data complexity, and high operational costs. Finally, the paper discusses the advantages and limitations of hyperspectral technology in agricultural soil heavy metal identification, and prospects future development directions including technological improvements and innovations, expansion of application scopes, and establishment of standardization and normalization. Future research should focus on enhancing sensor resolution, optimizing algorithms, and establishing unified spectral databases to improve model generalizability, while promoting widespread application of hyperspectral technology in agricultural soil heavy metal monitoring through multidisciplinary collaboration.

Downloads

Download data is not yet available.

References

[1] Chen, H. et al. (2018). Contamination features and health risk of soil heavy metals in China. Science of the Total Environment, 512–513, 143–153.

[2] Chen, H. et al. (2022). Hyperspectral sensing of heavy metals in soil by integrating AI and UAV technology. Environmental Monitoring and Assessment, 194(7): 1-19.

[3] Chen, H. et al. (2022). Study on rapid investigation of heavy metal pollution in site soil based on hyperspectral technology. Journal of Environmental Science, 45(6), pp. 206–213. (in Chinese)

[4] Chen, T. et al. (2015). Rapid identification of soil cadmium pollution risk at regional scale based on visible and near-infrared spectroscopy. Environmental Pollution, 206: 217-226.

[5] Chen, Z. et al. (2021). A general framework and practical procedure for improving pXRF measurement accuracy with integrating moisture content and organic matter content parameters. Scientific Reports, 11(1): 5843.

[6] Guo, X. et al. (2021). An Inversion of Soil Nickel Contents with Hyperspectral in Iron Mine Area of Beijing. Chinese Journal of Soil Science, 52(4), pp. 960–967. (in Chinese)

[7] Kemper, T., & Sommer, S. (2002). Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy. Environmental Science & Technology, 36(12), 2742–2747.

[8] Kooistra, L. et al. (2001). Possibilities of visible and near-infrared spectroscopy for assessing soil contamination in river floodplains. Analytica Chimica Acta, 446(1–2), pp. 97–105.

[9] Lei, R. et al. (2018). Advances in rapid detection technologies for soil heavy metals. Environmental Monitoring in China, 34(5), pp. 12–21. (in Chinese)

[10] Liu, P., Liu, Z.H., Hu, Y.M., et al. (2019). Integrating a Hybrid Back Propagation Neural Network and Particle Swarm Optimization for Estimating Soil Heavy Metal Contents Using Hyperspectral Data. Sustainability, 11, 419.

[11] Liu, S., Marinelli, D., Bruzzone, L., & Bovolo, F. (2019). A Review of Change Detection in Multitemporal Hyperspectral Images: Current Techniques, Applications, and Challenges. IEEE Geoscience and Remote Sensing Magazine, 7(2), 140-158.

[12] Liu, Z. et al. (2019). Estimation of Soil Heavy Metal Content Using Hyperspectral Data. Remote Sensing, 11(7): 1464.

[13] Shen, Q. et al. (2019). Hyperspectral inversion of heavy metals in reclaimed soil based on spectral transformation. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 222, pp. 117191.

[14] Shi, T., Wang, J., Chen, Y., & Wu, G. (2016). Improving the prediction of arsenic contents in agricultural soils by combining the reflectance spectroscopy of soils and rice plants. International Journal of Applied Earth Observation and Geoinformation, 52, 95-103.

[15] Tan, K., Ma, W.B., Chen, L.H., et al. (2021). Estimating the distribution trend of soil heavy metals in mining area from HyMap airborne hyperspectral imagery based on ensemble learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 5767-5772.

[16] Wang, C.-C., Zhang, Q.-C., Yan, C.-A., Tang, G.-Y., Zhang, M.-Y., & Ma, L.-Q. (2023). Heavy metal(loid)s in agriculture soils, rice, and wheat across China: Status assessment and spatiotemporal analysis. Science of the Total Environment, 882, 163361.

[17] Wang, F. et al. (2018). Hyperspectral sensing of heavy metals in soil and vegetation: Feasibility and challenges. ISPRS Journal of Photogrammetry and Remote Sensing, 136, 73–84.

[18] Wu, Y.Z., Chen, J., Ji, J.F., Tian, Q.J., & Wu, X.M. (2005). Feasibility of reflectance spectroscopy for the assessment of soil mercury contamination. Environmental Science & Technology, 39(16), 873-878.

[19] Xu, M. et al. (2011). Hyperspectral inversion of heavy metal content in archaeological soils. Journal of Infrared and Millimeter Waves, 30(2), pp. 109–114. (in Chinese)

[20] Zhang, B. et al. (2022). Retrieving soil heavy metals concentrations based on GaoFen-5 hyperspectral satellite image at an opencast coal mine, Inner Mongolia, China. Environmental Pollution, 300: 118982.

[21] Zhang, S. et al. (2019). Hyperspectral inversion of heavy metal content in reclaimed soil from a mining wasteland based on different spectral transformation and modeling methods. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 211, 393–400.

[22] Zhang, X. et al. (2015). Impact of soil heavy metal pollution on food safety in China. PLoS ONE, 10(8), e0135182.

[23] Zhang, X. et al. (2019). Predicting cadmium concentration in soils using laboratory and field reflectance spectroscopy. Science of the Total Environment, 650, pp. 321–334.

[24] Zhao, L. et al. (2018). Estimation Methods for Soil Mercury Content Using Hyperspectral Remote Sensing. Sustainability, 10(7), 2474.

[25] Zhou, W., Yang, H., Xie, L., et al. (2021). Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model. Catena, 202(12), 105222.