• Background and Aims There are three reasons for the increasing demand for crop models that build the plant on the basis of architectural principles and organogenetic processes: (1) realistic concepts for developing new crops need to be guided by such models; (2) there is an increasing interest in crop phenotypic plasticity, based on variable architecture and morphology; and (3) engineering of mechanized cropping systems requires information on crop architecture. The functional–structural model GREENLAB was recently presented that simulates resource-dependent plasticity of plant architecture. This study introduces a new methodology for crop parameter optimization against measured data called multi-fitting, validates the calibrated model for maize with independent field data, and describes a technique for 3D visualization of outputs. • Methods Maize was grown near Beijing during the 2000, 2001 and 2003 (two sowing dates) summer seasons in a block design with four to five replications. Detailed morphological and topological observations were made on the plant architecture throughout the development of the four crops. Data obtained in 2000 was used to establish target files for parameter optimization using the generalized least square method, and parameter accuracy was evaluated by coefficient of variance. In situ plant digitization was used to establish 3D symbol files for organs that were then used to translate model outputs directly into 3D representations for each time step of model execution. •Key Results and Conclusions Multi-fitting against several target files obtained at different growth stages gave better parameter accuracy than single fitting at maturity only, and permitted extracting generic organ expansion kinetics from the static observations. The 2000 model gave excellent predictions of plant architecture and vegetative growth for the other three seasons having different temperature regimes, but predictions of inter-seasonal variability of biomass partitioning during grain filling were less accurate. This was probably due to insufficient consideration of processes governing cob sink size and terminal leaf senescence. Further perspectives for model improvement are discussed.

Maize tassels play a critical role in plant growth and yield. Extensive RGB images obtained using unmanned aerial vehicle (UAV) and the prevalence of deep learning provide a chance to improve the accuracy of detecting maize tassels. We used images from UAV, a mobile phone, and the Maize Tassel Counting dataset (MTC) to test the performance of faster region-based convolutional neural network (Faster R-CNN) with residual neural network (ResNet) and a visual geometry group neural network (VGGNet). The results showed that the ResNet, as the feature extraction network, was better than the VGGNet for detecting maize tassels from UAV images with 600 × 600 resolution. The prediction accuracy ranged from 87.94% to 94.99%. However, the prediction accuracy was less than 87.27% from the UAV images with 5280 × 2970 resolution. We modified the anchor size to [85², 128², 256²] in the region proposal network according to the width and height of pixel distribution to improve detection accuracy up to 89.96%. The accuracy reached up to 95.95% for mobile phone images. Then, we compared our trained model with TasselNet without training their datasets. The average difference of tassel number was 1.4 between the calculations with 40 images for the two methods. In the future, we could further improve the performance of the models by enlarging datasets and calculating other tassel traits such as the length, width, diameter, perimeter, and the branch number of the maize tassels.

Global agriculture is facing the challenge of a phenotyping bottleneck due to large-scale screening/breeding experiments with improved breeds. Phenotypic analysis with high-throughput, high-accuracy and low-cost technologies has therefore become urgent. Recent advances in image-based 3D reconstruction offer the opportunity of high-throughput phenotyping. The main aim of this study was to quantify and evaluate the canopy structure of plant populations in two and three dimensions based on the multi-view stereo (MVS) approach, and to monitor plant growth and development from seedling stage to fruiting stage. Multi-view images of flat-leaf cucumber, small-leaf pepper and curly-leaf eggplant were obtained by moving a camera around the plant canopy. Three-dimensional point clouds were reconstructed from images based on the MVS approach and were then converted into surfaces with triangular facets. Phenotypic parameters, including leaf length, leaf width, leaf area, plant height and maximum canopy width, were calculated from reconstructed surfaces. Accurate evaluation in 2D and 3D for individual leaves was performed by comparing reconstructed phenotypic parameters with referenced values and by calculating the Hausdorff distance, i.e. the mean distance between two surfaces. Our analysis demonstrates that there were good agreements in leaf parameters between referenced and estimated values. A high level of overlap was also found between surfaces of image-based reconstructions and laser scanning. Accuracy of 3D reconstruction of curly-leaf plants was relatively lower than that of flat-leaf plants. Plant height of three plants and maximum canopy width of cucumber and pepper showed an increasing trend during the 70 d after transplanting. Maximum canopy width of eggplants reached its peak at the 40th day after transplanting. The larger leaf phenotypic parameters of cucumber were mostly found at the middle-upper leaf position. High-accuracy 3D evaluation of reconstruction quality indicated that dynamic capture of the 3D canopy based on the MVS approach can be potentially used in 3D phenotyping for applications in breeding and field management.

Spatial configuration and plant phenotypic plasticity contribute to increased light capture in relay intercropping, but there is little information on whether these factors also increase light capture in simultaneous intercropping. We developed and validated a three-dimensional functional–structural plant model to simulate light capture in maize and soybean sole crops and intercrop scenarios, using species traits observed in sole crops and intercrops. The intercrop maize phenotype had 2% greater light capture than the sole crop phenotype in a pure stand. The soybean intercrop phenotype had 5–10% lower light capture than the sole crop phenotype in a pure stand. The intercrop configuration increased the light capture of maize by 29% and reduced the light capture of soybean by 42%, compared with the light capture expected from sole crops. However, intercrop configuration only marginally affected total light capture by the intercrop system (+1%). Testing of individual soybean plant traits revealed that plasticity in leaf dimensions was the main reason for differences in light capture by soybean in simulated sole crops and intercrops. The results of this study illustrate a major shift of light capture from shorter species (soybean) to the taller component (maize) in a simultaneous strip intercrop. Plastic plant traits modulate this overall effect, but only marginally.

High-throughput estimation of phenotypic traits from UAV (unmanned aerial vehicle) images is helpful to improve the screening efficiency of breeding maize. Accurately estimating phenotyping traits of breeding maize at plot scale helps to promote gene mining for specific traits and provides a guarantee for accelerating the breeding of superior varieties. Constructing an efficient and accurate estimation model is the key to the application of UAV-based multiple sensors data. This study aims to apply the ensemble learning model to improve the feasibility and accuracy of estimating maize phenotypic traits using UAV-based red-green-blue (RGB) and multispectral sensors. The UAV images of four growth stages were obtained, respectively. The reflectance of visible light bands, canopy coverage, plant height (PH), and texture information were extracted from RGB images, and the vegetation indices were calculated from multispectral images. We compared and analyzed the estimation accuracy of single-type feature and multiple features for LAI (leaf area index), fresh weight (FW), and dry weight (DW) of maize. The basic models included ridge regression (RR), support vector machine (SVM), random forest (RF), Gaussian process (GP), and K-neighbor network (K-NN). The ensemble learning models included stacking and Bayesian model averaging (BMA). The results showed that the ensemble learning model improved the accuracy and stability of maize phenotypic traits estimation. Among the features extracted from UAV RGB images, the highest accuracy was obtained by the combination of spectrum, structure, and texture features. The model had the best accuracy constructed using all features of two sensors. The estimation accuracies of ensemble learning models, including stacking and BMA, were higher than those of the basic models. The coefficient of determination () of the optimal validation results were 0.852, 0.888, and 0.929 for LAI, FW, and DW, respectively. Therefore, the combination of UAV-based multisource data and ensemble learning model could accurately estimate phenotyping traits of breeding maize at plot scale.

High-throughput phenotyping is a limitation in plant genetics and breeding due to large-scale experiments in the field. Unmanned aerial vehicles (UAVs) can help to extract plant phenotypic traits rapidly and non-destructively with high efficiency. The general aim of this study is to estimate the dynamic plant height and leaf area index (LAI) by nadir and oblique photography with a UAV, and to compare the integrity of the established three-dimensional (3-D) canopy by these two methods. Images were captured by a high-resolution digital RGB camera mounted on a UAV at five stages with nadir and oblique photography, and processed by Agisoft Metashape to generate point clouds, orthomosaic maps and digital surface models. Individual plots were segmented according to their positions in the experimental design layout. The plant height of each inbred line was calculated automatically by a reference ground method. The LAI was calculated by the 3-D voxel method. The reconstructed canopy was sliced into different layers to compare leaf area density obtained from oblique and nadir photography. Good agreements were found for plant height between nadir photography, oblique photography and manual measurement during the whole growing season. The estimated LAI by oblique photography correlated better with measured LAI (slope = 0.87, R² = 0.67), compared with that of nadir photography (slope = 0.74, R² = 0.56). The total number of point clouds obtained by oblique photography was about 2.7–3.1 times than those by nadir photography. Leaf area density calculated by nadir photography was much less than that obtained by oblique photography, especially near the plant base. Plant height and LAI can be extracted automatically and efficiently by both photography methods. Oblique photography can provide intensive point clouds and relatively complete canopy information at low cost. The reconstructed 3-D profile of the plant canopy can be easily recognized by oblique photography.