ABSTRACT
Objective: Precise monitoring of cotton leaves' nitrogen content is important for increasing yield and reducing fertilizer application. Spectra and images are used to monitor crop nitrogen information. However, the information expressed using nitrogen monitoring based on a single data source is limited and cannot consider the expression of various phenotypic and physiological parameters simultaneously, which can affect the accuracy of inversion. Introducing a multi-source data-fusion mechanism can improve the accuracy and stability of cotton nitrogen content monitoring from the perspective of information complementarity. Methods: Five nitrogen treatments were applied to the test crop, Xinluzao No. 53 cotton, grown indoors. Cotton leaf hyperspectral, chlorophyll fluorescence, and digital image data were collected and screened. A multilevel data-fusion model combining multiple machine learning and stacking integration learning was built from three dimensions: feature-level fusion, decision-level fusion, and hybrid fusion. Results: The determination coefficients (R2) of the feature-level fusion, decision-level fusion, and hybrid-fusion models were 0.752, 0.771, and 0.848, and the root-mean-square errors (RMSE) were 3.806, 3.558, and 2.898, respectively. Compared with the nitrogen estimation models of the three single data sources, R2 increased by 5.0%, 6.8%, and 14.6%, and the RMSE decreased by 3.2%, 9.5%, and 26.3%, respectively. Conclusion: The multilevel fusion model can improve accuracy to varying degrees, and the accuracy and stability were highest with the hybrid-fusion model; these results provide theoretical and technical support for optimizing an accurate method of monitoring cotton leaf nitrogen content.
ABSTRACT
In this study, we developed a prussian blue nanoparticles (PBNPs) immunochromatographic assay (ICA) integrated with smartphone-based detection device for ZEN in cereals. PBNPs, as probe labels, were synthesized with properties of controllable structure, environment friendliness, and high affinities to antibody (Ab). PBNPs-ICA quantitative analysis was performed with a hand-held smartphone-based device coupled with a user-friendly and self-programmed detection App. This integrated strategy demonstrated high sensitivity for ZEN with a cut-off value of 10 µg/kg, a detection limit of 0.12 µg/kg, a quantitation limit of 0.27 µg/kg, and recovery rates of 92.0%-105.0% and 88.0%-98.0% for maize and wheat, respectively. The results of 20 naturally contaminated cereal samples showed good correlation (R2ï¼0.99) between LC-MS/MS and developed system. Moreover, the stability experiment revealed that PBNPs-ICA maintained high stability and bioactivity against competitive antigen (Ag). The proposed strategy exhibited great potential for the rapid monitoring of mycotoxins or other small molecule hazards.
