Detection of Cadmium Content in Pak Choi Using Hyperspectral Imaging Combined with Feature Selection Algorithms and Multivariate Regression Models
Source abstract
Abstract
Pak choi (Brassica chinensis L.) has a strong adsorption capacity for the heavy metal cadmium (Cd), which is a big threat to human health. Traditional detection methods have drawbacks such as destructiveness, time-consuming processes, and low efficiency. Therefore, this study aimed to construct a non-destructive prediction model for Cd content in pak choi leaves using hyperspectral technology combined with feature selection algorithms and multivariate regression models. Four different cadmium concentration treatments (0 (CK), 25, 50, and 100 mg/L) were established to monitor the apparent characteristics, chlorophyll content, cadmium content, chlorophyll fluorescence parameters, and spectral features of pak choi. Competitive adaptive reweighted sampling (CARS), the successive projections algorithm (SPA), and random frog (RF) were used for feature wavelength selection. Partial least squares regression (PLSR), random forest regression (RFR), the Elman neural network, and bidirectional long short-term memory (BiLSTM) models were established using both full spectra and feature wavelengths. The results showed that high-concentration Cd (100 mg/L) significantly inhibited pak choi growth, leaf Cd content was significantly higher than that in the control group, chlorophyll content decreased by 16.6%, and damage to the PSII reaction centre was aggravated. Among the models, the FD–RF–BiLSTM model demonstrated the best prediction performance, with a determination coefficient of the prediction set (Rp2) of 0.913 and a root mean square error of the prediction set (RMSEP) of 0.032. This study revealed the physiological, ecological, and spectral response characteristics of pak choi under Cd stress. It is feasible to detect leaf Cd content in pak choi using hyperspectral imaging technology, and non-destructive, high-precision detection was achieved by combining chemometric methods. This provides an efficient technical means for the rapid screening of Cd pollution in vegetables and holds important practical significance for ensuring the quality and safety of agricultural products.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Spectroscopy and Chemometric Analyses · Remote Sensing in Agriculture · Remote-Sensing Image Classification
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Digital Agriculture, Fujian Academy of Agricultural Sciences, Fuzhou 350003, China
Fujian Provincial Seed General Station, Fuzhou 350003, China
Faculty of Agriculture, Fujian Agriculture and Forestry University, Fuzhou 350002, China
Funding
the Basic Research Projects of Public Welfare Research Institutes in Fujian Province
References (43)
Show source-provided references
1. Cadmium contamination in agricultural soils of China and the impact on food safety10.1016/j.envpol.2019.03.063 ↗
2. Sun, X., Zhang, L., Gu, Y., Wang, P., Liu, H., Qiang, L., and Huang, Q. (2025). Nutrient-Element-Mediated Alleviation of Cadmium Stress in Plants: Mechanistic Insights and Practical Implications. Plants, 14.10.3390/plants14193081 ↗
3. Global soil pollution by toxic metals threatens agriculture and human health10.1126/science.adr5214 ↗
4. A Meta-Analysis of Heavy Metals Pollution in Farmland and Urban Soils in China over the Past 20 Years10.1016/j.jes.2020.08.013 ↗
5. Genchi, G., Sinicropi, M.S., Lauria, G., Carocci, A., and Catalano, A. (2020). The Effects of Cadmium Toxicity. Int. J. Environ. Res. Public Health, 17.10.3390/ijerph17113782 ↗
6. Zhang, D., Liu, X., Zhang, Y., Ye, J., and Yi, Q. (2025). Effects of Arbuscular Mycorrhizal Fungi on the Physiological Responses and Root Organic Acid Secretion of Tomato (Solanum lycopersicum) Under Cadmium Stress. Horticulturae, 11.10.20944/preprints202509.1192.v1 ↗
7. Zhou, J., Zhu, J.-G., Xiao, P., Wang, K.-L., Xu, Q., Wu, M.-X., and Pan, Y.-Z. (2025). Physiological and Multi-Omics Analysis in Leaves of Solanum americanum in Response to Cd Toxicity. Plants, 14.10.3390/plants14142131 ↗
8. Kim, J., Lee, J., Jang, Y., Lee, S., Lee, W.M., Wi, S., and Yoon, H.I. (2024). Elucidating Genetic Mechanisms of Summer Stress Tolerance in Chinese Cabbage through GWAS and Phenotypic Analysis. Agronomy, 14.10.3390/agronomy14091960 ↗
9. A chromosome-level reference genome of non-heading Chinese cabbage [Brassica campestris (syn. Brassica rapa) ssp. chinensis]10.1038/s41438-020-00449-z ↗
10. Xia, W., Liao, Y., Chen, X., Li, L., Shi, Y., Liu, Y., Zhang, J., and Fu, J. (2025). The Impact of Cd Pollution on Arbuscular Mycorrhizal Fungal Communities in Paddy Fields. Plants, 14.10.3390/plants14162501 ↗
11. (1995). Codex General Standard for Contaminants and Toxins in Food and Feed (Standard No. Codex Standard 193-1995).
12. (2022). National Health Commission of the People’s Republic of China, State Administration for Market Regulation. National Food Safety Standard: Limit of Pollutants in Food (Standard No. GB 2762-2022).
13. Zhang, S., Zhu, Y., Wang, M., and Fei, T. (2019). Selection of the Optimal Spectral Resolution for the Cadmium-Lead Cross Contamination Diagnosing Based on the Hyperspectral Reflectance of Rice Canopy. Sensors, 19.10.3390/s19183889 ↗
14. Retrieving Soil Heavy Metals Concentrations Based on GaoFen-5 Hyperspectral Satellite Image at an Opencast Coal Mine, Inner Mongolia, China10.1016/j.envpol.2022.118981 ↗
15. Wang, Y., Sun, J., Wu, Z., Jia, Y., and Dai, C. (2025). Application of Non-Destructive Technology in Plant Disease Detection: Review. Agriculture, 15.10.3390/agriculture15151670 ↗
16. Non-destructive monitoring of qualitative properties of salted cabbage using hyperspectral image analysis10.1016/j.lwt.2024.116329 ↗
17. Li, L., Huang, G., Wu, J., Yu, Y., Zhang, G., Su, Y., Wang, X., Chen, H., Wang, Y., and Wu, D. (2025). Combine photosynthetic characteristics and leaf hyperspectral reflectance for early detection of water stress. Front. Plant Sci., 16.10.3389/fpls.2025.1520304 ↗
18. Inversion monitoring of heavy metal pollution in corn crops based on ZY-1 02D hyperspectral imaging10.1016/j.microc.2024.112305 ↗
19. Estimating Cadmium Concentration in the Edible Part of Capsicum Annuum Using Hyperspectral Models10.1007/s10661-017-6261-3 ↗
20. Yi, X., Wen, X., Lan, A., Dai, Q., Yan, Y., Zhang, Y., and Yao, Y. (2023). Monitoring Cadmium Content in the Leaves of Field Pepper and Eggplant in a Karst Area Using Hyperspectral Remote Sensing Data. Sustainability, 15.10.3390/su15043508 ↗
21. Estimating Cadmium Content in Lettuce Leaves Based on Deep Brief Network and Hyperspectral Imaging Technology10.1111/jfpe.13293 ↗
22. Shen, T., Zhang, C., Liu, F., Wang, W., Lu, Y., Chen, R., and He, Y. (2020). High-Throughput Screening of Free Proline Content in Rice Leaf under Cadmium Stress Using Hyperspectral Imaging with Chemometrics. Sensors, 20.10.3390/s20113229 ↗
23. Predicting cadmium concentration in soils using laboratory and field reflectance spectroscopy10.1016/j.scitotenv.2018.08.442 ↗
24. Wu, C., Liu, M., Liu, X., Wang, T., and Wang, L. (2019). Developing a New Spectral Index for Detecting Cadmium-Induced Stress in Rice on a Regional Scale. Int. J. Environ. Res. Public Health, 16.10.3390/ijerph16234811 ↗
25. A multi-target regression method to predict element concentrations in tomato leaves using hyperspectral imaging10.34133/plantphenomics.0146 ↗
26. Hyperspectral imaging for trace cadmium prediction in lettuce leaves10.1016/j.saa.2025.126735 ↗
27. Plant chlorophyll content determination:acetone ethanol mixture method
28. Zhang, Y., Wu, W., Zhou, X., and Cheng, J.-H. (2025). Non-Destructive Detection of Soybean Storage Quality Using Hyperspectral Imaging Technology. Molecules, 30.10.3390/molecules30061357 ↗
29. Meng, L., Chen, G., Liu, D., and Tian, N. (2025). Universal Modeling for Non-Destructive Testing of Soluble Solids Content in Multi-Variety Blueberries Based on Hyperspectral Imaging Technology. Appl. Sci., 15.10.3390/app15073888 ↗
30. Li, K., Guo, Y., Zhong, H., Jin, Y., Li, B., Fang, H., Yao, L., and Zhao, C. (2025). Rapid Identification of Dendrobium Species Using Near-Infrared Hyperspectral Imaging Technology. Sensors, 25.10.3390/s25185625 ↗
31. Li, S., Sun, R., Li, X., Li, Y., Zhao, L., Huang, X., and Xu, Y. (2025). Estimation of Amino Acid and Tea Polyphenol Content of Tea Fresh Leaves Based on Fractional-Order Differential Spectroscopy. Appl. Sci., 15.10.3390/app15115792 ↗
32. Park, M.-S., Faqeerzada, M.A., Jang, S.H., Kim, H., Lee, H., Kim, G., Cho, Y.-S., Hwang, W.-H., Kim, M.S., and Baek, I. (2025). Detection of Abiotic Stress in Potato and Sweet Potato Plants Using Hyperspectral Imaging and Machine Learning. Plants, 14.10.3390/plants14193049 ↗
33. Determination of Dry-Matter Content of Kiwifruit before Harvest Based on Hyperspectral Imaging10.3390/agriengineering6010004 ↗
34. Tang, Z., Ma, S., Qi, H., Zhang, X., and Zhang, C. (2025). Nondestructive Detection of Rice Milling Quality Using Hyperspectral Imaging with Machine and Deep Learning Regression. Foods, 14.10.3390/foods14111977 ↗
35. Zhang, L., Liu, C., Han, J., and Yang, Y. (2025). Variety Identification of Corn Seeds Based on Hyperspectral Imaging and Convolutional Neural Network. Foods, 14.10.3390/foods14173052 ↗
36. Lan, T., Shen, S., Yuan, H., Jiang, Y., Tong, H., and Ye, Y. (2022). A Rapid Prediction Method of Moisture Content for Green Tea Fixation Based on WOA-Elman. Foods, 11.10.3390/foods11182928 ↗
37. Yan, X., Liu, S., Wang, S., Cui, J., Wang, Y., Lv, Y., Li, H., Feng, Y., Luo, R., and Zhang, Z. (2024). Predictive Analysis of Linoleic Acid in Red Meat Employing Advanced Ensemble Models of Bayesian and CNN-Bi-LSTM Decision Layer Fusion Based Hyperspectral Imaging. Foods, 13.10.3390/foods13030424 ↗
38. A Transformer-based framework with generative spectral augmentation for online monitoring of hyaluronic acid fermentation10.1016/j.carbpol.2025.124278 ↗
39. Study on phenotypic characteristics, photosynthetic ability, and cadmium enrichment ability of Chinese cabbage under cadmium stress
40. Effects of cadmium stress on growth, physiological characteristics and cadmium enrichment and transport of lettuce
41. Gao, W. (2012). Hyperspectral Characteristics and Simulation of Some Physiological Parameters of Leafyvegetables Under Cd Stress. [Ph.D. Thesis, Southwest University].
42. Estimation models for spectral response and cadmium contents in leaves of Brassica napus L.
43. Establishment of hyperspectral prediction model for cadmium content in flue-curedtobacco leaves