Diagnostic study of nitrogen nutrition in cotton based on unmanned aerial vehicle RGB images

Abstract

Nitrogen fertilizer levels significantly affect crop growth and development, necessitating precision management. Most studies focus on nitrogen nutrient estimation using vegetation indices and textural features, overlooking the diagnostic potential of color features. Hence, we investigated cotton nitrogen nutrition status using unmanned aerial vehicle (UAV) image features and the nitrogen nutrient index (NNI). Random frog algorithm - and random forest-screened image feature sets significantly correlated with the NNI, which were substituted into four machine learning algorithms for NNI estimation modeling. The composite scores (F) of optimal image feature sets were calculated using the coefficient of variation method for comprehensive cotton nitrogen nutrient diagnosis. Validation of the model for determining the critical nitrogen concentration in cotton yielded a coefficient of determination R2 = 0.89, root mean square error RMSE = 0.50 g (100 g)-1, and mean absolute error MAE = 0.44, demonstrating improved performance. Additionally, our novel NNI estimation model constructed based on the optimal image feature sets exhibited R2c = 0.97, RMSEc = 0.02, MAEc = 0.02, R2v = 0.85, RMSEv = 0.05, and MAEv = 0.04. Polynomial fitting of the composite index with NNI indicated that the model was reliable and yielded the following diagnostic criterion: 0.48 0.67 indicated nitrogen deficiency. This study demonstrates the superior effectiveness of using UAV RGB image feature sets for NNI estimation and the quick, accurate diagnosis of cotton nitrogen levels, which will help guide nitrogen fertilizer application.

Keywords

• composite score
• image features
• machine learning
• nitrogen nutrition index