Chengxin Ju

Wheat (Triticum aestivum L.) leaf rust is the most common and widely distributed wheat disease. Non‐destructive and real‐time methods for monitoring wheat leaf rust can help prevent and control plant diseases in agricultural production. In this study, we obtained multispectral imagery of the wheat canopy acquired by an unmanned aerial vehicle, selected the vegetation index using the K‐means algorithm (KA) and genetic algorithm (GA), and established a wheat leaf rust monitoring model based on the backpropagation neural network (BPNN) method. The results showed that the R² and RMSE of the KA‐BPNN model were 0.902% and 5.45% for the modeling set, respectively, and 0.784% and 4.76% for the validation set, respectively; and the R² and RMSE of the GA‐BPNN model was 0.922% and 4.88% for the modeling set, respectively, and 0.780% and 4.28% for the validation set, respectively. The prediction model after optimizing the variables using KA and GA had higher accuracy than the BPNN model, implying that using variable dimensionality reduction methods and complex machine learning algorithms to construct estimation models can improve model accuracy significantly. These models accurately monitored leaf rust in winter wheat, providing a theoretical basis and technical support for assessing plant diseases and screening disease‐resistant wheat varieties.

Wheat ears in unmanned aerial vehicles (UAV) orthophotos are characterized by occlusion, small targets, dense distribution, and complex backgrounds. Rapid identification of wheat ears in UAV orthophotos in a field environment is critical for wheat yield prediction. Three improvements were achieved based on YOLOX-m: mosaic optimized, using BiFPN structure, and attention mechanism, then ablation experiments were performed to verify the effect of each improvement. Three scene datasets were established: images were acquired during three different growing periods, at three planting densities, and under three scenarios of UAV flight heights. In ablation experiments, three improvements had increased recognition accuracies on the experimental dataset. Compared the accuracy of the standard model with our improved model on three scene datasets. Our improved model during three different periods, at three planting densities, and under three scenarios of the UAV flight height, obtaining 88.03%, 87.59%, and 87.93% accuracies, which were, respectively, 2.54%, 1.89%, and 2.15% better than the original model. The results of this study showed that the improved YOLOX-m model can achieve UAV orthophoto wheat recognition under different practical scenarios in large fields, and that the best combination were obtained images from the wheat milk stage, low planting density, and low flight altitude.

Tiller are an important biological characteristic of wheat, a primary food crop. Accurate estimation of tiller number can help monitor wheat growth and is important in forecasting wheat yield. However, because of leaf cover and other factors, it is difficult to estimate tiller number and the accuracy of estimates based on vegetation indices is low. In this study, a gradual change feature was introduced to optimize traditional prediction models of wheat tiller number. Accuracy improved in optimized models, and model R2 values for three varieties of winter wheat were 0.7044, 0.7060, and 0.7357. The optimized models improved predictions of tiller number in whole wheat fields. Thus, compared with the traditional linear model, the addition of a gradual change feature greatly improved the accuracy of model predictions of wheat tiller number.

Extraction of farming progress information in rice–wheat rotation regions is an important topic in smart field research. In this study, a new method for the classification of farming progress types using unmanned aerial vehicle (UAV) RGB images and the proposed regional mean (RM) model is presented. First, RGB information was extracted from the images to create and select the optimal color indices. After index classification, we compared the brightness reflection of the corresponding grayscale map, the classification interval, and the standard deviation of each farming progress type. These comparisons showed that the optimal classification color indices were the normalized red–blue difference index (NRBDI), the normalized green–blue difference index (NGBDI), and the modified red–blue difference index (MRBDI). Second, the RM model was built according to the whole-field farming progress classification requirements to achieve the final classification. We verified the model accuracy, and the Kappa coefficients obtained by combining the NRBDI, NGBDI, and MRBDI with the RM model were 0.86, 0.82, and 0.88, respectively. The proposed method was then applied to predict UAV RGB images of unharvested wheat, harvested wheat, and tilled and irrigated fields. The results were compared with those obtained with traditional machine learning methods, that is, the support vector machine, maximum likelihood classification, and random forest methods. The NRBDI, NGBDI, and MRBDI were combined with the RM model to monitor farming progress of ground truth ROIs, and the Kappa coefficients obtained were 0.9134, 0.8738, and 0.9179, respectively, while traditional machine learning methods all produced a Kappa coefficient less than 0.7. The results indicate a significantly higher accuracy of the proposed method than those of the traditional machine learning classification methods for the identification of farming progress type. The proposed work provides an important reference for the application of UAV to the field classification of progress types.

The reduction of nitrogen (N) fertilizer during the rice growing season is an important practice in rice production and is ecologically beneficial. Will different N reduction stages affect rice yields and NUE? The timing of the reduction in N-efficient varieties (NEVs) is yet to be identified, especially under moderate N rate applications. We investigated the effectiveness of various N reduction stages (NRSs) on grain yield and N-use efficiency (NUE) in NEVs in the lower reaches of the Yangtze River in China. Two NEVs were grown in the field, and five N reduction treatments, including basal N reduction (BR) at pre-transplanting (PT), tillering N reduction (TR) at early tillering (ET), promoting-spikelet N reduction (PR) at panicle initiation (PI), keeping-spikelet N reduction (KR) at spikelet differentiation (SD), and N split reduction (SR) at all four stages, were adopted, with no N reduction (CK) and no N application (N0) as controls. The results showed that grain yield and NUE varied substantially with the NRSs. Yield decreases were observed in descending order of magnitude in BR, PR, SR, TR, and KR when compared to CK. For both NEVs, BR and PR were the most effective treatments in decreasing yield and NUE at the same N reduction rate. BR and PR markedly decreased the panicles per unit area or spikelets per panicle, root biomass, root length, root length density, and root oxidation activity and exhibited simultaneously decreased leaf area index, grain leaf ratio, shoot biomass, and crop growth rate from joining to the heading and from heading to maturity. According to the results, PT and PI were considered to be N reduction sensitive stages, and ET and SD were considered to be N reduction insensitive stages. According to the results, an N reduction strategy was suggested as follows: N reduction at SD and ET, with increased N proportions at PT and PI for NEVs when adopting moderate N application rates.

Nitrogen (N) management is of great importance in rice production, but most previous studies have focused on high N rates and there is a lack of research on management plans under a moderate N rate. This study aimed to explore the agronomic and physiological traits of N-efficient rice varieties (NEVs) and to optimize the management strategy at an N rate below the inflection point of the parabolic curve between N rate and grain yield. Two NEVs and two N-inefficient rice varieties (NIVs) were planted, and three treatments were designed according to the panicle N application method. A larger amount of N applied at panicle initiation (PI) led to higher rice yield and N-use efficiency (NUE). This was mainly due to increases in the total number of spikelets per unit area, root oxidation activity, leaf area duration, and leaf photosynthesis rate as well as to the increased carbon (C) and N utilization rates. Compared with NIVs, NEVs exhibited improved root and shoot functions and higher C and N transport characteristics at the moderate N rate. We suggest that increasing the application of N at PI and that planting of NEVs are important ways to increase rice yield and NUE when adopting moderate N rates.

Controlled soil drying can substantially enhance water use efficiency by reducing irrigation water. However, grain quality traits are yet to be studied under such an irrigation regime, particularly on nutritional quality and heavy metal residues. This study investigated these issues by using two varieties Yongyou 2640 (YY‐2) and Nanjing 9108 (NJ‐9). Rice (Oryza sativa L.) was grown in the field under controlled soil drying (SD) and continuous flooding irrigation (FI). The results showed that, compared with FI, SD increased grain yield and nutritional quality simultaneously for both NJ‐9 and YY‐2. When compared with NJ‐9, YY‐2 had greater grain and protein yield, higher concentrations of As and Cd, and higher photosynthetic rate and transpiration rate when plants were rewatered. Although the relative content of protein and essential amino acids decreased in the SD regime, the absolute content (protein yield and amino acid yield) was increased. Besides, SD improved protein components and essential amino acid score (AAS) and decreased residues of As. The results demonstrated that SD improved photosynthetic characteristics and increased grain abscisic acid levels of inferior grains during soil drying. The results suggest that the adoption of SD may exert a synergistic effect on both grain yield and grain quality.