Search

Chlorophyll (Chl) is one of the most important classes of light-absorbing pigments in photosynthesis, and the proportion of Chl in leaves is closely related to vegetation nutrient status. Remote sensing-based estimation of Chl content holds great potential for evaluating crop growth status in agricultural management, precision farming and ecosystem monitoring. Recent studies have shown that steady-state fluorescence contributed up to 2% on the apparent reflectance in the 750-nm spectral region of plant and also provided additional evidence for fluorescence in-filling of the atmospheric oxygen absorption band at a central wavelength of 760 nm (O2–A band). In this study, an in situ hyperspectral remote sensing approach zwas employed to estimate corn Chl content at the canopy level by using chlorophyll fluorescence (ChlF) signals in the O2–A absorption band. Two new spectral indices, REArea760 (sum of first derivative reflectance between 755 and 763 nm) and REA760 (maximum of first derivative reflectance between 755 and 763 nm), derived from the first derivative spectra in the O2–A band, were proposed for estimating the corn canopy Chl content (CCC). They were compared with the performance of published indices measured at ground level, including the MERIS Terrestrial Chlorophyll Index (MTCI), Optimized Soil-Adjusted Vegetation Index 2 (OSAVI2), Modified Chlorophyll Absorption Ratio Index 2 (MCARI2), SR710, REArea (sum of first derivative reflectance between 680 and 780 nm), REA (maximum value of first derivative reflectance between 680 and 780 nm), and mND705. The results indicated that corn Chl content at the canopy level was better predicted by the new indices (with R2 = 0.835) than the published indices (with R2 ranging from 0.676 to 0.826). The two new indices ranked in the top four according to their summed ranks by integrating the ranks of RMSE and R2 of CCC linear regression models. ChlF originates only from chlorophyll in the photosynthetic apparatus and therefore is less sensitive to soil, wood, and dead biomass interference. Moreover, due to the fluorescence in-filling of the O2–A band and the amplified effect on spectrum signals by derivative operation, the spectral derivative indices in the O2–A band have great potential for estimating the CCC. [ABSTRACT FROM AUTHOR]

Nitrogen has significant effect on the growth and development in crop, the formation of yield and quality. Precision diagnosis and dynamic regulation of crop is the important content and scientific basis of precision agriculture. Thus, predicting crop N status accurately and applying appropriate rate N to crop are the focus for many studies in agricultural sciences. The crop canopy nitrogen status estimation based on spectroscopy is important tool for crop nitrogen management, but its accuracy of estimation is often affected by other factors such as canopy structures. The nitrogen nutrition index (NNI) was sensitive to nitrogen status because it combined the information of plant nitrogen content, the individual character of crop and biomass, and the group character of crop. The traditional methods for calculation of plant N concentration and aboveground biomass are done manually and they are time consuming. Thus, it is hard to apply NNI in precise farming. Recently, it has been documented remote sensing technology can be used to assess many biophysical and biochemical variable of crops, especially through spectral indices. NNI was considered a good indicator of crop nitrogen status and provided new opportunities for hyperspectral applications. The objective of this study was on the NNI estimation through remote sensing spectral parameters sensitive to leaf N content and canopy nitrogen density (CND). Based on the field experiments of different N rates and varieties of winter wheat from booting to filling stages, the relationships between spectral indices and leaf N and CND status in wheat were analyzed to determine the key spectral indices for assessment of leaf N content and CND. These relationships can help accurately quantitative diagnosis of nitrogen status, and provide the reference for the estimation of fertilizer rate and crop yield and quality. Upon the analysis the empirical model for NNI estimation based on the optimal parameters of leaf N and CND was established and evaluated. The results showed that, Red edge position based on linear interpolation method (REPLI), modified red edge simple ratio index (mSR705), ratio index-1dB (RI-1dB), simple ratio pigment index (SRPI), Vogelman red edge index (VOG) and other indicators had a good correlation with winter wheat nitrogen nutrition (r⩾0.85), and this correlation was not affected by growing period. Therefore, they can be used to evaluate the nutritional status of canopy nitrogen inversion. Then the optimal spectral parameters were selected and the nitrogen index regression models were established. Independent experimental data was used for model validation. The results showed that REPLI in the nitrogen nutrition index estimation performed better (r=0.927, p<0.01), and the model estimation accuracy was high (R2=0.859, RMSE=0.078). Our research indicated that NNI had advantages in the field crop nitrogen nutrition diagnosis, and it had potential in qualitative and quantitative diagnosis of nitrogen nutrition status by hyperspectral inversion. [ABSTRACT FROM AUTHOR]

Background: Cotton pests have a major impact on cotton quality and yield during cotton production and cultivation. With the rapid development of agricultural intelligence, the accurate classification of cotton pests is a key factor in realizing the precise application of medicines by utilize unmanned aerial vehicles (UAVs), large application devices and other equipment., Methods: In this study, a cotton insect pest classification model based on improved Swin Transformer is proposed. The model introduces the residual module, skip connection, into Swin Transformer to improve the problem that pest features are easily confused in complex backgrounds leading to poor classification accuracy, and to enhance the recognition of cotton pests. In this study, 2705 leaf images of cotton insect pests (including three insect pests, cotton aphids, cotton mirids and cotton leaf mites) were collected in the field, and after image preprocessing and data augmentation operations, model training was performed., Results: The test results proved that the accuracy of the improved model compared to the original model increased from 94.6% to 97.4%, and the prediction time for a single image was 0.00434s. The improved Swin Transformer model was compared with seven kinds of classification models (VGG11, VGG11-bn, Resnet18, MobilenetV2, VIT, Swin Transformer small, and Swin Transformer base), and the model accuracy was increased respectively by 0.5%, 4.7%, 2.2%, 2.5%, 6.3%, 7.9%, 8.0%., Discussion: Therefore, this study demonstrates that the improved Swin Transformer model significantly improves the accuracy and efficiency of cotton pest detection compared with other classification models, and can be deployed on edge devices such as utilize unmanned aerial vehicles (UAVs), thus providing an important technological support and theoretical basis for cotton pest control and precision drug application., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Zhang, Zhu, Zhang, Zhao, Liu, He, Dong, Hong, Tan and Li.)

Accurate wheat ear counting is one of the key indicators for wheat phenotyping. Convolutional neural network (CNN) algorithms for counting wheat have evolved into sophisticated tools, however because of the limitations of sensory fields, CNN is unable to simulate global context information, which has an impact on counting performance. In this study, we present a hybrid attention network (CTHNet) for wheat ear counting from RGB images that combines local features and global context information. On the one hand, to extract multi-scale local features, a convolutional neural network is built using the Cross Stage Partial framework. On the other hand, to acquire better global context information, tokenized image patches from convolutional neural network feature maps are encoded as input sequences using Pyramid Pooling Transformer. Then, the feature fusion module merges the local features with the global context information to significantly enhance the feature representation. The Global Wheat Head Detection Dataset and Wheat Ear Detection Dataset are used to assess the proposed model. There were 3.40 and 5.21 average absolute errors, respectively. The performance of the proposed model was significantly better than previous studies., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Hong, Liu, Zhu, Ren, Shi, Lu, Yang, Deng, Qian and Tan.)

Chlorophyll (Chl) is one of the most important classes of light-absorbing pigments in photosynthesis, and the proportion of Chl in leaves is closely related to vegetation nutrient status. Remote sensing-based estimation of Chl content holds great potential for evaluating crop growth status in agricultural management, precision farming and ecosystem monitoring. Recent studies have shown that steady-state fluorescence contributed up to 2% on the apparent reflectance in the 750-nm spectral region of plant and also provided additional evidence for fluorescence in-filling of the atmospheric oxygen absorption band at a central wavelength of 760 nm (O 2 -A band). In this study, an in situ hyperspectral remote sensing approach zwas employed to estimate corn Chl content at the canopy level by using chlorophyll fluorescence (ChlF) signals in the O 2 -A absorption band. Two new spectral indices, REArea 760 (sum of first derivative reflectance between 755 and 763 nm) and REA 760 (maximum of first derivative reflectance between 755 and 763 nm), derived from the first derivative spectra in the O 2 -A band, were proposed for estimating the corn canopy Chl content (CCC). They were compared with the performance of published indices measured at ground level, including the MERIS Terrestrial Chlorophyll Index (MTCI), Optimized Soil-Adjusted Vegetation Index 2 (OSAVI2), Modified Chlorophyll Absorption Ratio Index 2 (MCARI2), SR710, REArea (sum of first derivative reflectance between 680 and 780 nm), REA (maximum value of first derivative reflectance between 680 and 780 nm), and mND 705 . The results indicated that corn Chl content at the canopy level was better predicted by the new indices (with R 2 = 0.835) than the published indices (with R 2 ranging from 0.676 to 0.826). The two new indices ranked in the top four according to their summed ranks by integrating the ranks of RMSE and R 2 of CCC linear regression models. ChlF originates only from chlorophyll in the photosynthetic apparatus and therefore is less sensitive to soil, wood, and dead biomass interference. Moreover, due to the fluorescence in-filling of the O 2 -A band and the amplified effect on spectrum signals by derivative operation, the spectral derivative indices in the O 2 -A band have great potential for estimating the CCC.