Search

Nitrogen (N) fertilizer maximizes the growth of oilseed rape (Brassica napus L.) by improving photosynthetic performance. Elucidating the dynamic relationship between fluorescence and plant N status could provide a non-destructive diagnosis of N status and the breeding of N-efficient cultivars. The aim of this study was to explore the impacts of different N treatments on photosynthesis at a spatial–temporal scale and to evaluate the performance of three fluorescence techniques for the diagnosis of N status. One-way ANOVA and linear discriminant analysis were applied to analyze fluorescence data acquired by a continuous excitation chlorophyll fluorimeter (OJIP transient analysis), pulse amplitude-modulated chlorophyll fluorescence (PAM-ChlF), and multicolor fluorescence (MCF) imaging. The results showed that the maximum quantum efficiency of PSII photochemistry (Fv/Fm) and performance index for photosynthesis (PIABS) of bottom leaves were sensitive to N status at the bolting stage, whereas the red fluorescence/far-red fluorescence ratio of top leaves was sensitive at the early seedling stage. Although the classification of N treatments by the three techniques achieved comparable accuracies, MCF imaging showed the best potential for early diagnosis of N status in field phenotyping because it had the highest sensitivity in the top leaves, at the early seedling stage. The findings of this study could facilitate research on N management and the breeding of N-efficient cultivars.

HighlightsAn abnormal accumulation of sucrose and glucose was found in HLB-infected leaves, and it presented a similar pattern in different orchards from cool to hot seasons.A decreasing value of the actual quantum yield of PSII (FPSII) in HLB-infected leaves was mainly related to an increase of non-regulated energy quenching (FNO) due to the irreversible damage of PSII.Chlorophyll fluorescence imaging combined with a random forest was able to identify HLB at the asymptomatic stage.Abstract Citrus Huanglongbing (HLB) poses a serious threat to citrus production. This research aimed to explore chlorophyll fluorescence imaging for characterizing the photosynthetic response to HLB-infected citrus leaves in different orchards and seasons. Chlorophyll fluorescence images of citrus leaves were acquired with an in-house chlorophyll fluorescence imaging system. It was found that sucrose and glucose accumulated earlier than starch in HLB-infected leaves, and a similar carbohydrate metabolic pattern was observed in HLB-infected leaves grown in different orchards from cool to hot seasons. The pathogen damaged the thylakoid structure of chloroplasts with a higher value of Fo. It decreased photosynthetic activity of the host by reducing the number of active photosynthetic centers and the maximum quantum yield of PSII (Fv/Fm) with lower values of Fv/Fo and Fv/Fm. Additionally, the pathogen modified the allocation of excitation energy in citrus leaves by reducing the actual quantum yield of PSII (FPSII) due to an increase of non-regulated energy quenching (FNO), which indicated irreversible PSII damage before symptom development. Moreover, photosynthetic signatures combined with the random forest method were able to identify HLB in the asymptomatic stage with an overall accuracy of 91.8%. These results demonstrated the potential of chlorophyll fluorescence imaging for evaluating the photosynthetic response to HLB as well as disease diagnosis. Keywords: Carbohydrate metabolism, Chlorophyll fluorescence imaging, Citrus Huanglongbing, Photosynthetic efficiency, Random forest model.

Background The advances of hyperspectral technology provide a new analytic means to decrease the gap of phenomics and genomics caused by the fast development of plant genomics with the next generation sequencing technology. Through hyperspectral technology, it is possible to phenotype the biochemical attributes of rice seeds and use the data for GWAS. Results The results of correlation analysis indicated that Normalized Difference Spectral Index (NDSI) had high correlation with protein content (PC) with RNDSI2 = 0.68. Based on GWAS analysis using all the traits, NDSI was able to identify the same SNP loci as rice protein content that was measured by traditional methods. In total, hyperspectral trait NDSI identified all the 43 genes that were identified by biochemical trait PC. NDSI identified 1 extra SNP marker on chromosome 1, which annotated extra 22 genes that were not identified by PC. Kegg annotation results showed that traits NDSI annotated 3 pathways that are exactly the same as PC. The cysteine and methionine metabolic pathway identified by both NDSI and PC was reported important for biosynthesis and metabolism of some of amino acids/protein in rice seeds. Conclusion This study combined hyperspectral technology and GWAS analysis to dissect PC of rice seeds, which was high throughput and proven to be able to apply to GWAS as a new phenotyping tool. It provided a new means to phenotype one of the important biochemical traits for the determination of rice quality that could be used for genetic studies. Electronic supplementary material The online version of this article (10.1186/s13007-019-0432-x) contains supplementary material, which is available to authorized users.

There is an increasing demand of chili peppers due to their special taste and numerous applications through a number of markets, and high quality is crucial for both producers and customers. This research was aimed to investigate the potential of near-infrared hyperspectral imaging (HSI) for nondestructive quality assessment of chili peppers. Near-infrared HSI in the spectral range of 975–1646 nm was employed to acquire hyperspectral reflectance images of chili peppers. High-performance liquid chromatography and freeze-drying methods were conducted to obtain the reference values of capsaicinoid concentrations and water contents, respectively. Three different variable selection methods with successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS) and genetic algorithm-partial least squares (GA-PLS) were performed to remove the redundant information and select the optimal wavelengths. Quantitative models including partial least squares (PLS), extreme learning machine (ELM) and least-squares support vector machine (LS-SVM) were then developed to predict the capsaicinoid concentrations and the water content. The results show that the ELM models combined with the SPA method yielded the best prediction performances for the capsaicin and dihydrocapsaicin concentrations, and the water content, with the highest correlation coefficients of prediction (RP) of 0.83, 0.80 and 0.93, respectively. Distribution maps of capsaicin and dihydrocapsaicin concentrations for intact and cut chili peppers were obtained. Finally, classification models for discriminating pungent and non-pungent chili peppers with a classification accuracy of 98.0% were developed. The results demonstrate that near-infrared HSI technique is promising for pepper quality assessment.

Huanglongbing (HLB) is a highly destructive disease to citrus that is threatening the global citrus industry. It is a great challenge for HLB disease detection at various stages due to the long asymptomatic period and the similar symptom to nutrient deficient trees. This research was aimed to propose an effective method for HLB detection in different seasons and cultivars based on hyperspectral imaging coupled with carbohydrate metabolism analysis. It was found that sucrose accumulated more steadily than starch, glucose and fructose in infected leaves through the hot and cool seasons, but nutrient (Fe) deficient leaves presented a reverse pattern to HLB infected leaves. Spectral and textural features from optimal wavelengths and principle component images were well linked to the HLB fingerprint. The three-class classification models for healthy, HLB infected (asymptomatic and symptomatic), and nutrient deficient leaves achieved 90.2%, 96.0%, and 92.6% accuracy for the cool season, hot season, and the whole period, respectively, using least squares-support vector machine (LS-SVM) classifier. Additionally, the robustness of classification model was validated by a different citrus cultivar using model transfer strategy with the overall accuracy of 93.5%. These results demonstrated the potential of hyperspectral imaging combined with carbohydrate metabolic analysis for HLB detection in different seasons and cultivars.

Background Unmanned aerial vehicle (UAV)-based remote sensing provides a flexible, low-cost, and efficient approach to monitor crop growth status at fine spatial and temporal resolutions, and has a high potential to accelerate breeding process and improve precision field management. Method In this study, we discussed the use of lightweight UAV with dual image-frame snapshot cameras to estimate aboveground biomass (AGB) and panicle biomass (PB) of rice at different growth stages with different nitrogen (N) treatments. The spatial–temporal variations in the typical vegetation indices (VIs) and AGB were first investigated, and the accuracy of crop surface model (CSM) extracted from the Red Green Blue (RGB) images at two different stages were also evaluated. Random forest (RF) model for AGB estimation as well as the PB was then developed. Furthermore, variable importance and sensitivity analysis of UAV variables were performed to study the potential of improving model robustness and prediction accuracies. Results It was found that the canopy height extracted from the CSM (Hcsm) exhibited a high correlation with the ground-measured canopy height, while it was unsuitable to be independently used for biomass assessment of rice during the entire growth stages. We also observed that several VIs were highly correlated with AGB, and the modified normalized difference spectral index extracted from the multispectral image achieved the highest correlation. RF model with fusing RGB and multispectral image data substantially improved the prediction results of AGB and PB with the prediction of root mean square error (RMSEP) reduced by 8.33–16.00%. The best prediction results for AGB and PB were achieved with the coefficient of determination (r2), the RMSEP and relative RMSE (RRMSE) of 0.90, 0.21 kg/m2 and 14.05%, and 0.68, 0.10 kg/m2 and 12.11%, respectively. In addition, the result confirmed that the sensitivity analysis could simplify the prediction model without reducing the prediction accuracy. Conclusion These findings demonstrate the feasibility of applying lightweight UAV with dual image-frame snapshot cameras for rice biomass estimation, and its potential for high throughput analysis of plant growth-related traits in precision agriculture as well as the advanced breeding program. Electronic supplementary material The online version of this article (10.1186/s13007-019-0418-8) contains supplementary material, which is available to authorized users.

White shrimp (Litopenaeus vannamei) raised in low-salinity farm are considered inferior to those in seawater. In order to develop a rapid discrimination method for the food industry, we investigated the potential of using near-infrared hyperspectral imaging to discriminate shrimp muscle samples from freshwater and seawater farms. We constructed 3 different discrimination models with 4 optimal wavelength selection methods and compared the performance of each model. The results showed that sequential forward selection combined with partial least squares discriminant analysis (SFS-PLS-DA) generated the best discrimination performance with an overall accuracy of 99.2%. The elemental and isotopic analysis indicated a high correlation between 918 and 925 nm region (which was selected by SFS) and 13C concentration. This agrees with the fact that there is more 13C in shrimp of salty water compared to those of freshwater. The results demonstrated (hyperspectral imaging) HSI is promising to discriminate L. vannamei raised in fresh and seawater environments.

Timely and accurate monitoring crop production and forecasting yield before harvesting are valuable for precision management, policy and decision making, and marketing. The spectral information such as vegetation indices (VIs) calculated from unmanned aerial vehicle (UAV)-based images have shown the potential for crop yield prediction, but the reliability and the accuracy haven‘t been satisfied yet. This study was aimed to explore the potential of fusion of UAV images-based spectral and structural information extracted from the entire growth period of rice crop to improve the grain yield prediction. Field experiments with different nitrogen (N) applications were conducted in 2017 and 2018, and ground measurements including leaf chlorophyll content (LCC), aboveground biomass (AGB) and grain yield were performed. A UAV platform carrying RGB and multispectral cameras was employed to collect high spatial-temporal resolution images of rice crops. The VIs, canopy height and canopy coverage were then extracted from RGB and multispectral images, which was used to develop random forest (RF) prediction models for grain yield. The results showed that combining normalized difference vegetation index (NDVI), normalized difference yellowness index (NDYI), canopy height and canopy coverage achieved the best prediction of grain yield with the determination coefficient (r2) of 0.85, prediction of root mean square error (RMSEP) of 0.39 t/ha, and relative RMSE (rRMSE) of 3.56% in 2017, and r2 of 0.83, RMSEP of 0.33 t/ha, and rRMSE of 2.75% in 2018, respectively, which outperformed the results in the reported studies. Furthermore, the initial heading stage was proved to be the optimal stage to evaluate the grain yield, and a model transfer strategy at the initial heading stage in 2017 was successfully implemented to predict the grain yield in 2018 with the rRMSE of 6.71%. These findings demonstrated that fusion of canopy spectral and structure information obtained from UAV-based RGB and multispectral images can improve the prediction accuracy of grain yield as well as achieve a dynamic monitoring of crop growth status. The proposed approach could provide a valuable insight for the high spatial-temporal precision management in agriculture.

Timely and accurate crop monitoring and yield forecasting before harvesting are valuable for precision management, policy and decision making, and marketing. The aim of this study is to explore the potential of fusing spectral and structural information extracted from the unmanned aerial vehicle (UAV)-based images in the whole growth period of rice to improve the grain yield prediction. A UAV platform carrying RGB and multispectral cameras was employed to collect high spatial resolution images of the rice crop under different nitrogen treatments over two years. The vegetation indices (VIs), canopy height and canopy coverage were extracted from UAV-based images, which were then used to develop random forest prediction models for grain yield. Among all of the investigated VIs, it was found that normalized difference yellowness index (NDYI) was the most useful index to monitor the changes in leaf chlorophyll content as well as the leaf greenness during the whole growth period. Meanwhile, the VIs provided a comparable prediction of grain yield to field-measured aboveground biomass and leaf chlorophyll content. Fusion of the multi-temporal normalized difference vegetation index (NDVI), NDYI, canopy height and canopy coverage achieved the best prediction of grain yield with a determination coefficient of 0.85 and 0.83, and relative root mean square error of 3.56% and 2.75% in 2017 and 2018, respectively, which outperformed the results in the reported studies. The initial heading stage was the optimal growth stage for the prediction of grain yield. Furthermore, the robustness of prediction model developed from the dataset in 2017 was validated by an external dataset from 2018 using model transfer. These findings demonstrate that the proposed approach can improve the prediction accuracy of grain yield as well as achieve an efficient monitoring of crop growth.

Image processing technology has gained considerable attention in agricultural proximal sensing applications, including plant disease detection, vegetation fraction estimation, monitoring of the crop growth status, and image-based site-specific management. Image segmentation is the first and crucial step to process complex infield images. However, image segmentation by either hand engineered-based or deep learning-based methods that train the entire system from scratch is a daunting task and needs several hundreds of labeled images that may be difficult to obtain in practice. The recent development of transfer learning has shown the potential of transferring the learned feature detectors of a pre-trained convolutional neural network to a new image dataset. This study was thus aimed to evaluate three transfer learning methods using a VGG16-based encoder net for semantic segmentation of oilseed rapes images in a field with high-density weeds. Three different transfer learning approaches using a VGG16-based encoder model were proposed, and their performances were compared to a VGG19-based encoder net. Relying on the intensive use of data augmentation and transfer learning, we showed that such networks could be trained end-to-end using a few annotated training images. The highest accuracy of 96% was obtained by the VGG16-based encoder net in which the fine-tuned model was only used for feature extraction and the segmentation was performed using shallow machine learning classifiers (MLCs). Transfer learning demonstrated to be efficient and presented a robust performance in segmenting plants amongst high-density weeds. The implementation of MLCs is reasonable for real-time applications with the segmentation time less than 0.05 s/image.

Huanglongbing (HLB) is one of the most destructive diseases of citrus, which has posed a serious threat to the global citrus production. This research was aimed to explore the use of chlorophyll fluorescence imaging combined with feature selection to characterize and detect the HLB disease. Chlorophyll fluorescence images of citrus leaf samples were measured by an in-house chlorophyll fluorescence imaging system. The commonly used chlorophyll fluorescence parameters provided the first screening of HLB disease. To further explore the photosynthetic fingerprint of HLB infected leaves, three feature selection methods combined with the supervised classifiers were employed to identify the unique fluorescence signature of HLB and perform the three-class classification (i.e., healthy, HLB infected, and nutrient deficient leaves). Unlike the commonly used fluorescence parameters, this novel data-driven approach by using the combination of the mean fluorescence parameters and image features gave the best classification performance with the accuracy of 97%, and presented a better interpretation for the spatial heterogeneity of photochemical and non-photochemical components in HLB infected citrus leaves. These results imply the potential of the proposed approach for the citrus HLB disease diagnosis, and also provide a valuable insight for the photosynthetic response to the HLB disease.