Search

Although crop-growth monitoring is important for agricultural managers, it has always been a difficult research topic. However, unmanned aerial vehicles (UAVs) equipped with RGB and hyperspectral cameras can now acquire high-resolution remote-sensing images, which facilitates and accelerates such monitoring. To explore the effect of monitoring a single crop-growth indicator and multiple indicators, this study combines six growth indicators (plant nitrogen content, above-ground biomass, plant water content, chlorophyll, leaf area index, and plant height) into the new comprehensive growth index (CGI). We investigate the performance of RGB imagery and hyperspectral data for monitoring crop growth based on multi-time estimation of the CGI. The CGI is estimated from the vegetation indices based on UAV hyperspectral data treated by linear, nonlinear, and multiple linear regression (MLR), partial least squares (PLSR), and random forest (RF). The results are as follows: (1) The RGB-imagery indices red reflectance (r), the excess-red index (EXR), the vegetation atmospherically resistant index (VARI), and the modified green-red vegetation index (MGRVI), as well as the spectral indices consisting of the linear combination index (LCI), the modified simple ratio index (MSR), the simple ratio vegetation index (SR), and the normalized difference vegetation index (NDVI), are more strongly correlated with the CGI than a single growth-monitoring indicator. (2) The CGI estimation model is constructed by comparing a single RGB-imagery index and a spectral index, and the optimal RGB-imagery index corresponding to each of the four growth stages in order is r, r, r, EXR; the optimal spectral index is LCI for all four growth stages. (3) The MLR, PLSR, and RF methods are used to estimate the CGI. The MLR method produces the best estimates. (4) Finally, the CGI is more accurately estimated using the UAV hyperspectral indices than using the RGB-image indices. [ABSTRACT FROM AUTHOR]

Rapidly developing remote sensing techniques are shedding new light on large-scale crop growth status monitoring, especially in recent applications of unmanned aerial vehicles (UAVs). Many inversion models have been built to estimate crop growth variables. However, the present methods focused on building models for each single crop stage, and the features generally used in the models are vegetation indices (VI) or joint VI with data derived from UAV-based sensors (e.g., texture, RGB color information, or canopy height). It is obvious these models are either limited to a single stage or have an unstable performance across stages. To address these issues, this study selected four key wheat growth parameters for inversion: above-ground biomass (AGB), plant nitrogen accumulation (PNA) and concentration (PNC), and the nitrogen nutrition index (NNI). Crop data and multispectral data were acquired in five wheat growth stages. Then, the band reflectance and VI were obtained from multispectral data, along with the five stages that were recorded as phenology indicators (PIs) according to the stage of Zadok's scale. These three types of data formed six combinations (C1–C6): C1 used all of the band reflectances, C2 used all VIs, C3 used bands and VIs, C4 used bands and PIs, C5 used VIs and PIs, and C6 used bands, Vis, and PIs. Some of the combinations were integrated with PIs to verify if PIs can improve the model accuracy. Random forest (RF) was used to build models with combinations of different parameters and evaluate the feature importance. The results showed that all models of different combinations have good performance in the modeling of crop parameters, such as R2 from 0.6 to 0.79 and NRMSE from 10.51 to 15.83%. Then, the model was optimized to understand the importance of PIs. The results showed that the combinations that integrated PIs showed better estimations and the potential of using PIs to minimize features while still achieving good predictions. Finally, the varied model results were evaluated to analyze their performances in different stages or fertilizer treatments. The results showed the models have good performances at different stages or treatments (R2 > 0.6). This paper provides a reference for monitoring and estimating wheat growth parameters based on UAV multispectral imagery and phenology information. [ABSTRACT FROM AUTHOR]

Fast and accurate counting of wheat ears in field conditions is a key element for determining wheat yield. To obtain the number of wheat ears in a field, we propose a new counting algorithm based on computer vision. This algorithm counts wheat ears in remote images through semantic segmentation regression network (SSRNet). SSRNet is a multistage convolutional neural network that we propose to achieve counting problems through regression. In SSRNet, first, the original image is cropped to increase the amount of data. This method effectively solves the small sample dataset. Next, based on the cropping results, we build a fully convolutional neural network (FCNN) to segment wheat ears in field conditions. FCNN increases the accuracy of wheat ears counting by accurately segmenting wheat ears in a complex background. Then, we build a regression convolutional neural network (RCNN) to count wheat ears based on the segmentation results of FCNN. In RCNN, we propose a new activation function positive rectification linear unit (PrLU) to process the last layer of the fully connected layer, so that RCNN can effectively count the number of wheat ears in the image. Finally, a counting strategy is proposed to count the number of wheat ears in the original image. To verify the counting performance of SSRNet, we compare the counting result of SSRNet with the real value of manual statistics. The results show that the average accuracy (Acc), $R^{2}$ , and root mean squared error (RMSE) of the SSRNet count results on the test set in this article are 0.980, 0.996, and 9.437, respectively. It can be seen from the results that our proposed method can accurately count wheat ears in field conditions. At the same time, the counting time (0.11 s) shows that SSRNet can quickly estimate the number of wheat ears in field conditions. We concluded that this study can provide important technical support for the high-throughput field wheat ears counting task in large-scale phenotyping work. [ABSTRACT FROM AUTHOR]

To obtain an accurate count of wheat spikes, which is crucial for estimating yield, this paper proposes a new algorithm that uses computer vision to achieve this goal from an image. First, a home-built semi-autonomous multi-sensor field-based phenotype platform (FPP) is used to obtain orthographic images of wheat plots at the filling stage. The data acquisition system of the FPP provides high-definition RGB images and multispectral images of the corresponding quadrats. Then, the high-definition panchromatic images are obtained by fusion of three channels of RGB. The Gram-Schmidt fusion algorithm is then used to fuse these multispectral and panchromatic images, thereby improving the color identification degree of the targets. Next, the maximum entropy segmentation method is used to do the coarse-segmentation. The threshold of this method is determined by a firefly algorithm based on chaos theory (FACT), and then a morphological filter is used to de-noise the coarse-segmentation results. Finally, morphological reconstruction theory is applied to segment the adhesive part of the de-noised image and realize the fine-segmentation of the image. The computer-generated counting results for the wheat plots, using independent regional statistical function in Matlab R2017b software, are then compared with field measurements which indicate that the proposed method provides a more accurate count of wheat spikes when compared with other traditional fusion and segmentation methods mentioned in this paper. [ABSTRACT FROM AUTHOR]

Process-based models can be usefully employed for the assessment of field and regional-scale impact of drought on crop yields. However, in many instances, especially when they are used at the regional scale, it is necessary to identify the parameters and input variables that most influence the outputs and to assess how their influence varies when climatic and environmental conditions change. In this work, two different crop models, able to represent yield response to water, Aquacrop and SAFYE, were compared, with the aim to quantify their complexity and plasticity through Global Sensitivity Analysis (GSA), using Morris and EFAST (Extended Fourier Amplitude Sensitivity Test) techniques, for moderate to strong water limited climate scenarios. Although the rankings of the sensitivity indices was influenced by the scenarios used, the correlation among the rankings, higher for SAFYE than for Aquacrop, assessed by the top-down correlation coefficient (TDCC), revealed clear patterns. Parameters and input variables related to phenology and to water stress physiological processes were found to be the most influential for Aquacrop. For SAFYE, it was found that the water stress could be inferred indirectly from the processes regulating leaf growth, described in the original SAFY model. SAFYE has a lower complexity and plasticity than Aquacrop, making it more suitable to less data demanding regional scale applications, in case the only objective is the assessment of crop yield and no detailed information is sought on the mechanisms of the stress factors affecting its limitations. [ABSTRACT FROM AUTHOR]

• We introduce leaf N profile characteristic coefficient K m on its remote estimates. • Diverse datasets are used for developing robust models for remote estimates of K m. • Four regression algorithms are tested with various possible sets of predictors. • A robust method is proposed to estimate K m from canopy reflectance for winter wheat. The characteristic coefficient of vertical leaf nitrogen (N) profile is a canopy parameter that indicates the attenuation steepness of leaf N from the top of canopy downward. It is sensitive not only to crop production, grain yield and quality, and light- and N-use efficiency but also to N deficiency in the crop. We introduce this coefficient by exploring a robust method to estimate it from canopy spectral reflectance. We analyze comprehensively various approaches based on diverse datasets of winter wheat. We test and compare the accuracy and stability of models by using the adjusted and weighted coefficient of determination (wR adj 2), the mean absolute error (MAE), and the mean and coefficient of variation (CV) over multiple seasons. The analysis focuses mainly on the coefficient of mass-based leaf N profile (K m); nevertheless, a comparison with the coefficient of area-based leaf N profile is presented. The results indicate that the most robust model to estimate K m of winter wheat is K m = (1.8037 R G V I - 0.9702 + 0.0786 e x p (0.6315 / D A S F)) / 2 , where RGVI is the red and green ratio vegetation index, and DASF is the directional area scattering factor. The mean wR adj 2 is 0.663 with CV = 8.2% and the mean MAE is 0.117 with CV = 12.8% over three seasons including various situations. This makes it possible to assess K m at large areas and follow its dynamics over multiple periods in a timely and nondestructive manner. [ABSTRACT FROM AUTHOR]

The feasibility of monitoring lodging of wheat fields by exploiting fully polarimetric C-band radar images has been investigated in this paper. A set of backscattering intensity features and polarimetric features, derived by target decomposition techniques, was extracted from 5 consecutive Radarsat-2 images. The temporal evolutions of these features of lodging wheat fields were investigated as a function of DAS (day after sowing) during the entire growing season. The temporal behavior was compared between typical lodging fields and normal fields in different growing stages. It was found that polarimetric feature from synthetic aperture radar (SAR) data was very sensitive to wheat lodging. Then a method called polarimetric index, availing the sensitivity of polarimetry to the structure, was put forward to monitor wheat lodging. The method was validated by two sets of in situ data collected in Shangkuli Farmland area, Inner Mongolia, China, at heading and ripe stages of spring wheat. Almost all the lodging fields were successfully distinguished from normal fields. Furthermore, the result revealed that the polarimetric index can reflect the intrinsic feature of lodging wheat with good anti-inference ability such as wheat growth difference. While optical sensors relied on its spectral features to monitor crop lodging, the proposed method based on radar data utilized polarimetric features to monitor crop lodging. [ABSTRACT FROM AUTHOR]

Powdery mildew is one of the most serious diseases that have a significant impact on the production of winter wheat. As an effective alternative to traditional sampling methods, remote sensing can be a useful tool in disease detection. This study attempted to use multi-temporal moderate resolution satellite-based data of surface reflectances in blue (B), green (G), red (R) and near infrared (NIR) bands from HJ-CCD (CCD sensor on Huanjing satellite) to monitor disease at a regional scale. In a suburban area in Beijing, China, an extensive field campaign for disease intensity survey was conducted at key growth stages of winter wheat in 2010. Meanwhile, corresponding time series of HJ-CCD images were acquired over the study area. In this study, a number of single-stage and multi-stage spectral features, which were sensitive to powdery mildew, were selected by using an independent t-test. With the selected spectral features, four advanced methods: mahalanobis distance, maximum likelihood classifier, partial least square regression and mixture tuned matched filtering were tested and evaluated for their performances in disease mapping. The experimental results showed that all four algorithms could generate disease maps with a generally correct distribution pattern of powdery mildew at the grain filling stage (Zadoks 72). However, by comparing these disease maps with ground survey data (validation samples), all of the four algorithms also produced a variable degree of error in estimating the disease occurrence and severity. Further, we found that the integration of MTMF and PLSR algorithms could result in a significant accuracy improvement of identifying and determining the disease intensity (overall accuracy of 72% increased to 78% and kappa coefficient of 0.49 increased to 0.59). The experimental results also demonstrated that the multi-temporal satellite images have a great potential in crop diseases mapping at a regional scale. [ABSTRACT FROM AUTHOR]

Fusarium head blight (FHB), one of the most prevalent and damaging infection diseases of wheat, affects quality and safety of associated food. In this study, to realize the early accurate monitoring of FHB, a diagnostic model of disease severity was proposed based on the fusion features of image and spectral features. First, the hyperspectral image of FHB infected in the range of the 400–1000 nm spectrum was collected, and the color parameters of wheat ear and spot region were segmented based on image features. Twelve sensitive bands were extracted using the successive projection algorithm, gray-scale co-occurrence matrix, and RGB color model. Four texture features were extracted from each feature band image as texture variables, and nine color feature variables were extracted from R, G, and B component images. Texture features with high correlation and color features were selected to participate in the final model building parameters via correlation analysis. Finally, the particle swarm optimization support vector machine (PSO-SVM) algorithm was used to build the model based on the diagnosis model of disease severity of FHB with different combinations of characteristic variables. The experimental results showed that the PSO-SVM model based on spectral and color feature fusion was optimal. Moreover, the accuracy of the training and prediction set was 95% and 92%, respectively. The method based on fusion features of image and spectral features can accurately and effectively diagnose the severity of FHB, thereby providing a technical basis for the timely and effective control of FHB and precise application of a pesticide. [ABSTRACT FROM AUTHOR]

Plant nitrogen (N) information has widely been estimated through empirical techniques using hyperspectral data. However, the physical model inversion approach on N spectral response has seldom developed and remains a challenge. In this study, an N-PROSAIL model based on the N-based PROSPECT model and the SAIL model canopy model was constructed and used for retrieving crop N status both at leaf and canopy scales. The results show that the third parameter (3rd-par) retrieving strategy (leaf area index (LAI) and leaf N density (LND) optimized where other parameters in the N-PROSAIL model are set at different values at each growth stage) exhibited the highest accuracy for LAI and LND estimation, which resulted in R2 and RMSE values of 0.80 and 0.69, and 0.46 and 21.18 µg·cm−2, respectively. It also showed good results with R2 and RMSE values of 0.75 and 0.38% for leaf N concentration (LNC) and 0.82 and 0.95 g·m−2 for canopy N density (CND), respectively. The N-PROSAIL model retrieving method performed better than the vegetation index regression model (LNC: RMSE = 0.48 − 0.64%; CND: RMSE = 1.26 − 1.78 g·m−2). This study indicates the potential of using the N-PROSAIL model for crop N diagnosis on leaf and canopy scales in wheat. [ABSTRACT FROM AUTHOR]

Crop failure detection using UAV images is helpful for precision agriculture, enabling the precision management of failure areas to reduce crop loss. For wheat failure area detection at the seedling stage using UAV images, the commonly used methods are not sufficiently accurate. Thus, herein, a new tool for precision wheat management at the seedling stage is designed. For this purpose, field experiments with two wheat cultivars and four nitrogen (N) treatments were conducted to create different scenarios for the failure area, and multispectral UAV images were acquired at the seedling growth stage. Based on the above data, a new failure detection method was designed by assimilating prior knowledge and a filter analysis strategy and compared with classical filter-based methods and Hough transform-based methods for wheat failure area detection. The results showed that the newly proposed assimilation method had a detection accuracy between 83.86% and 97.67% for different N levels and cultivars. In contrast, the filter-based methods and Hough transform-based methods had detection accuracies between 53.73% and 83.95% and between 20.71% and 75.79%, respectively. Thus, the assimilation method demonstrated the best failure detection performance. • An assimilation method was proposed for wheat failure area detection. • Different methods were compared for wheat failure area detection. • Wheat failure area can be detected using unmanned aerial vehicles imagery. [ABSTRACT FROM AUTHOR]

The fundamental basis for applying remote sensing methods to crop assessments is the interrelationships between crop features and canopy spectral characteristics. Thus, a thorough understanding of the differences in the distributions of crop variables among different vertical layers and modules, as well as the effects of these layers and modules on canopy spectral characteristics and derived vegetation indices, is vital to improving the performance of crop monitoring by remote sensing. The main goal of this work was to provide insight into the above issues based on field measurements of winter wheat under different treatments during anthesis. The results demonstrated that the leaf area index (LAI), leaf chlorophyll a and b content (Chl a + b ), nitrogen (N) content per unit leaf area (N L ), N concentration on a mass basis (N M ), dry matter accumulation (DM), N accumulation (NA), and water content (W c ) in leaves and stems generally exhibited great vertical differences within wheat canopies during anthesis. There were also significant differences in N M , DM, NA, and W c among the different plant modules (i.e., leaves, stems, and spikes) and the entire canopy. Moreover, the removal of wheat spikes and different vertical leaf layers had evident effects on the canopy spectral reflectance, and there were differences in the types and degrees of these effects at different wavelengths and treatments. In most cases, the vegetation indices decreased after removing wheat spikes and different leaf layers, although a few indices increased. There were also some vegetation indices that responded weakly to removal events. In comparison, the vegetation indices mostly showed stronger responses to the removal of the top 1st leaves than the spikes. To a certain extent, the responses to the removal of the top 2nd leaves were comparable to those of the top 1st leaves. The responses of most vegetation indices to the top 3rd leaves' removal were less than the responses to the top 2nd leaves' removal. In the case of the removal of the top 4th leaves and below, many of the R V (i.e., relative variation rate) absolute values of vegetation indices were greater than those of the top 3rd leaves' removal but smaller than or close to those of the top 2nd leaves' removal; this may partly be because all the withered and dead leaves covering the soil surface were also removed in this case. The above findings indicated that crop features may not be well characterized when they are based solely on leaves, especially only the upper leaves, as the lower leaves, stems, and spikes also have important effects. Moreover, wheat spikes, not just leaves, and even bottom-layer leaves, could have evident effects on canopy reflectance characteristics and derived vegetation indices. More effort is needed in future research to obtain a thorough understanding of the effects of canopy heterogeneity on canopy spectral characteristics and the relationships between crop variables and spectral vegetation indices. [ABSTRACT FROM AUTHOR]

Fusarium damage in wheat reduces the quality and safety of associated food and feed products. In this study, a specific Fusarium head blight (FHB) classification index (FCI) for detection of this disease in wheat is proposed. Hyperspectral microscopy images of wheat spikelets are used as the data source. An algorithm combining the instability index (ISI) and spectral angle mapper (SAM) classifier (ISI-SAM) is used to extract four sensitive single wavelengths. Then, partial least-squares regression of the disease area ratio with simple spectral vegetation indices (SVIs) for each image is used to determine the most relevant spectral index (i.e., difference spectral index, DSI (668, 417)). On this basis, in order to develop a hyperspectral index for FHB detection, an exhaustive search for the best weighted combination of a single wavelength and DSI (668, 417) is conducted, with all possible combinations being tested. The final FCI is F C I = 0.25 × [ 2 (R 668 − R 417) − R 539 ] , with an overall classification accuracy of 89.80%. The FCI is tested for its ability to detect and classify the healthy and diseased areas of wheat spikelets through comparison with six commonly used SVIs, and its disease identification accuracy is almost 30% higher than that of the best-performing SVI. The FCI is also successfully applied to classification of hyperspectral image data from wheat spikes. The FCI developed in this study constitutes a stable and feasible method of early FHB detection through spectral and low-altitude remote sensing, and will improve FHB detection, identification, and monitoring performance in precision agriculture applications. Image 1 • Hyperspectral microscopic images used to develop Fusarium classification index FCI. • A joint algorithm, ISI-SAM, is proposed to select the optimum sensitive wavebands. • A diseased area ratio of each HMI image is provided to assess damage level. • FCI based on combination of optimal single waveband and difference spectral index. • The proposed FCI is effective for recognition of FHB infected wheat ears. [ABSTRACT FROM AUTHOR]

• The invariant shape spectral preprocessing method is effective for WYMV detection. • Machine learning has great potential for narrow to wide band migration applications. • The 3SV-SIW-SVM mode is most effective for WYMV detection. Wheat yellow mosaic disease (WYMD) is a low-temperature soil-borne disease that causes serious yield and economic losses. Reflectance spectroscopy has great potential for detecting crop diseases, but it has not been applied for detection of WYMD. Herein, we collected 2 years of wheat physiological and reflectance spectroscopy data at green-up and jointing stages, and conducted disease detection studies. We evaluated standard normal variate (SNV), multiplicative scatter correction (MSC), and spectral separation of soil and vegetation (3SV) as preprocessing methods for invariant spectral shapes, and 96 spectral indices. The spectral index wavelength (SIW), threshold method, and variance inflation factor (TVIF) were used as feature selection methods combined with machine learning to construct a systematic disease detection scheme. The results showed that the visible region centred at 750 nm was the most sensitive wavelength. Additionally, 900–––1000 nm was the sensitive wavelength in the middle and latter stages, during disease aggravation and fertility development. The preprocessing method was best with 3SV, which was highly consistent with the characteristic regions of the original spectra, followed by SNV and MSC. spectral indices OR-BG1 I, SNV-RPMI, MSC-RPMI and 3SV-CTRI 1 could be applied to detect WYMD, and the best index was 3SV-CTRI 1, with OA and Kappa values of 75.88% and 0.516, respectively. The effectiveness of the SIW feature selection method and coupling with machine learning was superior to TVIF. The best results among different machine learning models were obtained with SVM, followed by RF and KNN. The optimal 3SV-SIW-SVM disease detection mode achieved OA and Kappa values of 94.71% and 0.893, respectively, for field data validation, and 68.06% and 0.381, respectively, for simulated satellite data validation. The findings will facilitate migration of ground-based research to satellite platforms, and provide new ideas for quantitative identification of crop diseases. [ABSTRACT FROM AUTHOR]

Highlights • An unmanned aerial vehicle (UAV) was optimized and used for non-destructive high-throughput phenotyping of NDVI. • UAV-NDVI measurements were highly consistent with ground data captured by a handheld Greenseeker. • UAV-NDVI explained significant variations in biomass and grain yield. • UAV-NDVI was accurate and can be used for selection of high yielding genotypes during grain-filling stages in large breeding programs. Abstract Wheat improvement programs require rapid assessment of large numbers of individual plots across multiple environments. Vegetation indices (VIs) that are mainly associated with yield and yield-related physiological traits, and rapid evaluation of canopy normalized difference vegetation index (NDVI) can assist in-season selection. Multi-spectral imagery using unmanned aerial vehicles (UAV) can readily assess the VIs traits at various crop growth stages. Thirty-two wheat cultivars and breeding lines grown in limited irrigation and full irrigation treatments were investigated to monitor NDVI across the growth cycle using a Sequoia sensor mounted on a UAV. Significant correlations ranging from R2 = 0.38 to 0.90 were observed between NDVI detected from UAV and Greenseeker (GS) during stem elongation (SE) to late grain gilling (LGF) across the treatments. UAV-NDVI also had high heritabilities at SE (h2 = 0.91), flowering (F)(h2 = 0.95), EGF (h2 = 0.79) and mid grain filling (MGF) (h2 = 0.71) under the full irrigation treatment, and at booting (B) (h2 = 0.89), EGF (h2 = 0.75) in the limited irrigation treatment. UAV-NDVI explained significant variation in grain yield (GY) at EGF (R2 = 0.86), MGF (R2 = 0.83) and LGF (R2 = 0.89) stages, and results were consistent with GS-NDVI. Higher correlations between UAV-NDVI and GY were observed under full irrigation at three different grain-filling stages (R2 = 0.40, 0.49 and 0.45) than the limited irrigation treatment (R2 = 0.08, 0.12 and 0.14) and GY was calculated to be 24.4% lower under limited irrigation conditions. Pearson correlations between UAV-NDVI and GY were also low ranging from r = 0.29 to 0.37 during grain-filling under limited irrigation but higher than GS-NDVI data. A similar pattern was observed for normalized difference red-edge (NDRE) and normalized green red difference index (NGRDI) when correlated with GY. Fresh biomass estimated at late flowering stage had significant correlations of r = 0.30 to 0.51 with UAV-NDVI at EGF. Some genotypes Nongda 211, Nongda 5181, Zhongmai 175 and Zhongmai 12 were identified as high yielding genotypes using NDVI during grain-filling. In conclusion, a multispectral sensor mounted on a UAV is a reliable high-throughput platform for NDVI measurement to predict biomass and GY and grain-filling stage seems the best period for selection. [ABSTRACT FROM AUTHOR]

Highlights • Dynamic model of the DSSAT-CERES model for wheat production. • GLUE with a systematic approach for well calibrating parameters in DSSAT-CERES model. • Crop variables in time series were in agreement with measured values. • DSSAT-CERES model as optimization management tool in agriculture. Abstract Crop growth models integrate genotype, environment and management and can serve as an analytical tool by which to study the influences of these factors on crop growth, production, and agricultural planning. Parameter calibration is the primary step taken before the local application of crop growth models. In this study, experimental field data were collected by way of a five-year (2008–2013) set of field experiments at a field site in Beijing, China. The DSSAT-CERES model was calibrated by integrating the generalized likelihood uncertainty estimation (GLUE) method and a systematic approach, and used experimental data relating to two seasons 2009/2010 and 2012/2013. The calibrated model was evaluated for its prediction performance using experimental data relating to the three seasons 2008/2009, 2010/2011 and 2011/2012. The results showed that the GLUE method can accurately estimate the genotype parameters of wheat; that the simulated leaf area index (LAI), aboveground biomass (AGB), aboveground nitrogen (AGN) and grain yield (GY) were close to the measured values; and that the DSSAT-CERES-Wheat model can be used to schedule wheat seed sowing dates, and optimize N fertilizer application in areas around Beijing. In general, the DSSAT-CERES-Wheat model was proved to be a useful decision-making tool for winter wheat production in the Beijing area. [ABSTRACT FROM AUTHOR]

[Display omitted] • Multi-source environmental data were used to predict wheat yield in China. • We developed a robust machine learning model to predict wheat yield. • The random forest model using NIRv had better performance than models using NDVI and EVI. • NIRv from jointing to heading was the most important predictor in determining yield. Crop yield is controlled by different environmental factors. Multi-source data for site-specific soils, climates, and remotely sensed vegetation indices are essential for yield prediction. Algorithms of data-model fusion for crop growth monitoring and yield prediction are complicated and need to be optimized to deal with model uncertainty. This study integrated multi-source environmental variables (e.g., satellite-based vegetation indices, climate data, and soil properties) into random forest (RF) and support vector machine (SVM) models for wheat yield prediction in China. The performance of both RF and SVM models was investigated using different types of vegetation indices associated with other predictors. Relative importance and partial dependence analyses were used to identify the main predictors and their relationships with wheat yield. We found that using remotely sensed vegetation indices improved our model precision, and that near-infrared reflectance of terrestrial vegetation (NIRv) was slightly better than normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) in predicting yield. NIRv was better in detecting climate stress on crops, and could capture more information regarding crop growth and yield formation. Compared with the SVM model, the RF model with NIRv and other covariates had better performance in wheat yield prediction, with R2 and RMSE being 0.74 and 758 kg/ha respectively. We also found that NIRv from jointing to heading was the most important predictor in determining yield, followed by solar radiation (especially during tillering–heading), relative humidity (during planting–tillering), soil organic carbon, and wind speed (throughout the growing season). In addition, wheat yield exhibited threshold-like responses to most factors based on our RF model. These threshold values can help to better understand how different environmental factors limit wheat yield, which will provide useful information for climate-adaptive crop management. Our findings demonstrated the potential of using NIRv for yield prediction. This approach is broadly applicable to other regions globally using publicly available data. [ABSTRACT FROM AUTHOR]

Abstract: Crop growth and production are dependent not only on the amount of total nitrogen (N) absorbed by plants, but also on the vertical leaf N distribution within canopies. The non-uniform leaf N distribution has been reported for various plant canopies. Remote sensing has been widely used for determination of crop N status, but such analysis seldom takes N distribution into consideration, ultimately leading to limited accuracy and decreased practical value of the related results. This paper has reviewed the results of previous studies that investigated the ecophysiological aspects of non-uniform N distribution, and the remote sensing methods that have been proposed to monitor this phenomenon. Additionally, this study used field data to analyze the differences in leaf N distribution in wheat canopies with different plant types (i.e. spread type, semi-spread type, and erect type), and provided insights into the estimation of vertical leaf N distribution by means of remote sensing. The process of reviewing research related to the ecophysiological issues of leaf N distribution led to identification of several important inadequacies in the current body of research. We propose that future work should aim to strengthen an understanding of the dynamic response of vertical N distribution within canopies to the various related environment factors and field management strategies. When a more thorough understanding of vertical N distribution is achieved, researchers will be able to improve related quantitative modeling, and may be able to comprehensively reveal the effect of vertical N distribution on canopy photosynthesis performances. In addition, through a comparison of the leaf N profiles of spread, semi-spread, and erect wheat canopies, it was found here that the semi-spread wheat canopy had a more non-uniform N distribution than did the other two types, despite all types having large and full vegetation coverage at the booting stage. Regarding detection of leaf N distribution using remote sensing, the few existing studies can be grouped into three classes according to the hyperspectral data used. One class employed the spectral data obtained from top-view observations; another class used multi-angle canopy reflectance data, while the third mainly focused on the relationships between spectral reflectance and fluorescence characteristics and the leaf N or chlorophyll content for different vertical layers. Despite important progress having been made, the results of the studies and the methods therein face key limitations in practical application. The present paper suggests two possibilities for the estimation of vertical leaf N distribution with remote sensing. One possibility is based upon hyperspectral imaging, and the other possibility combines a vertical N distribution model and canopy reflectance data. The former method requires investigation of the ability of hyperspectral imaging to obtain pure spectral information of different vertical leaf layers. The latter method requires that the key determinants of vertical N distribution be identified to improve quantitative modeling, and that the parameters of the N distribution model be determined from remotely sensed data. Because of the current lack of adequate data, a concrete case study and a very thorough test analysis could not be presented here. But it is still hoped that this work can provide helpful information for future studies. [Copyright &y& Elsevier]

• An interannual expandable wheat yield and quality predicting model. • Integrating spectral vegetative indices and meteorological data for yield and GPC prediction. • GPC prediction model was enhanced by adding a gluten type variable. The use of remote sensing data for predicting wheat yield and quality is becoming a more feasible alternative to destructive and post-harvest laboratory-based test methods. However, most prediction models which make use of remote sensing data are statistical rather than mechanistic, therefore difficult to extend at interannual and regional scales. In this work, an interannual expandable wheat yield and quality predicting model using hierarchical linear modeling (HLM) was developed, integrating hyperspectral and meteorological data. The results showed that the ordinary least squares (OLS) regression for predicting wheat yield and grain protein content (GPC), one key indicator of grain quality, had low stability at the interannual extension. The predictive power for yield by HLM method was higher than OLS, with R2, RMSEv and nRMSE values of 0.75, 1.10 t/ha, and 20.70 %, respectively. GPC prediction by the HLM method was enhanced when the gluten type was considered, with R2, RMSEv and nRMSE values of 0.85, 1.02 %, and 6.87 %, respectively. The results of this study confirmed that HLM can be a robust method for improving yield and GPC predicting stability under various growing seasons in winter wheat. [ABSTRACT FROM AUTHOR]