Abstract
Nitrogen is an important indicator for monitoring wheat growth. The rapid development and wide application of non-destructive detection provide many approaches for estimating leaf nitrogen content (LNC) in wheat. Previous studies have shown that better results have been obtained in the estimation of LNC in wheat based on spectral features. However, the lack of automatically extracted features leads to poor universality of the estimation model. Therefore, a feature fusion method for estimating LNC in wheat by combining spectral features with deep features (spatial features) was proposed. The deep features were automatically obtained with a convolutional neural network model based on the PyTorch framework. The spectral features were obtained using spectral information including position features (PFs) and vegetation indices (VIs). Different models based on feature combination for evaluating LNC in wheat were constructed: partial least squares regression (PLS), gradient boosting decision tree (GBDT), and support vector regression (SVR). The results indicate that the model based on the fusion feature from near-ground hyperspectral imagery has good estimation effect. In particular, the estimation accuracy of the GBDT model is the best (R2 = 0.975 for calibration set, R2 = 0.861 for validation set). These findings demonstrate that the approach proposed in this study improved the estimation performance of LNC in wheat, which could provide technical support in wheat growth monitoring.
Highlights
Wheat occupies an important position in agricultural production and strategic food reserves
The purpose of this research was to (1) extract deep features from hyperspectral images to overcome the limitations of feature expression; (2) fuse spectral features and deep features to improve the estimation accuracy of the model; (3) evaluate the performance of different models to test the validity of the model
To reduce the infToormreadtuiocne trhede uinnfdoarnmcaytiaonndreimdupnrodvaencthyeaancdcuimrapcryoovfetthheemacocduerla,ctyheof the model, the random forest alrgaonrditohmmfworaesstuaslegdortiothamnawlyazse uthseedretolatainvaelyimzepothrtearnecleatoivfe26imvpeogrettaanticoenof 26 vegetation indices, as showinndiinceFs,igaus rseho4w. nThine Friegluatriev4e. iTmhpe orertlaatnivcee iomf ptohretavnecgeeotaf ttihoenviengdeitcaetisonwiansdices was ranked ranked in descenidnindgesocrednedri,nagndortdheer,toapnd30th%eatroeps3e0le%ctaedreassetlehcetepdreafsertrheedpVrIesf,ewrrehdichVIasr,ewhich are NDVI NDVI g-b#, SIPI, NgP-bC#,I,SVIPOI,GN3P, CVIO, GVO2,GR3V, IVIO, SGA2V, RI VIIIaIn, dSAMVTIVIII2a.nd MTVI2
Summary
Wheat occupies an important position in agricultural production and strategic food reserves. Rapid and accurate detection of the wheat nitrogen nutrition status is of great significance for guiding farmland management and improving wheat production efficiency, yield and quality [2]. Full bands or characteristic bands extracted from the hyperspectral image have been used to monitor crop growth, which obtained good estimation results. Leemans et al successfully used the spectral features of the hyperspectral image to estimate the nitrogen content of wheat [13]. Mutanga et al used the spectral features extracted by the depth analysis of the band to estimate the physiological and biochemical parameters of a variety of crops [14]. The inversion model of crop biochemical parameters based on spectral information is prone to saturation when the vegetation coverage is large [1]. Improving the accuracy of the estimation model still faces many difficulties
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
