A cotton leaf nitrogen monitoring model based on spectral-fluorescence data fusion

In the present study, hyperspectral imaging and remote sensing of fluorescence were integrated to monitor nitrogen content in leaves drip-irrigated cotton at different growth periods northern Xinjiang, China. Based on spectrum chlorophyll parameters obtained through shuffled frog-leaping algorithm (SFLA), successive projection (SPA), grey relational analysis (GRA), competitive adaptive reweighted sampling (CARS), a monitoring model was established via imaging, parameters, spectral-fluorescence data fusion. The results showed that: (1) there significant positive correlations between Fv'/Fm', Fv/Fm, Yield, Fm, NPQ, each period. (2) effectiveness inversion highest budding period blooming period, coefficients determination (R2) validation sets 0.745 0.709, respectively. (3) for leaf that based decision-level fusion, R2 value training set reached 0.961, 0.828. conclusion, findings this study suggest feature-level fusion algorithms can effectively improve accuracy reliability monitoring.