A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage

Nitrogen(N)and potassium(K)are two key mineral nutrient elements involved in rice growth.Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage.Therefore,we propose a hybrid model for diagnosing rice nutrient levels at the early panicle initiation stage(EPIS),which combines a convolutional neural network(CNN)with an attention mechanism and a long short-term memory network(LSTM).The model was validated on a large set of sequential images collected by an unmanned aerial vehicle(UAV)from rice canopies at different growth stages during a two-year experiment.Compared with VGG16,AlexNet,GoogleNet,DenseNet,and inceptionV3,ResNet101 combined with LSTM obtained the highest average accuracy of 83.81%on the dataset of Huanghuazhan(HHZ,an indica cultivar).When tested on the datasets of HHZ and Xiushui 134(XS134,a japonica rice variety)in 2021,the ResNet101-LSTM model enhanced with the squeeze-and-excitation(SE)block achieved the highest accuracies of 85.38 and 88.38%,respectively.Through the cross-dataset method,the average accuracies on the HHZ and XS134 datasets tested in 2022 were 81.25 and 82.50%,respectively,showing a good generalization.Our proposed model works with the dynamic information of different rice growth stages and can efficiently diagnose different rice nutrient status levels at EPIS,which are helpful for making practical decisions regarding rational fertilization treatments at the panicle initiation stage.

Border Sensitive Knowledge Distillation for Rice Panicle Detection in UAV Images

Research on panicle detection is one of the most important aspects of paddy phenotypic analysis.A phenotyping method that uses unmanned aerial vehicles can be an excellent alternative to field-based methods.Nevertheless,it entails many other challenges,including different illuminations,panicle sizes,shape distortions,partial occlusions,and complex backgrounds.Object detection algorithms are directly affected by these factors.This work proposes a model for detecting panicles called Border Sensitive Knowledge Distillation(BSKD).It is designed to prioritize the preservation of knowledge in border areas through the use of feature distillation.Our feature-based knowledge distillation method allows us to compress the model without sacrificing its effectiveness.An imitation mask is used to distinguish panicle-related foreground features from irrelevant background features.A significant improvement in Unmanned Aerial Vehicle(UAV)images is achieved when students imitate the teacher’s features.On the UAV rice imagery dataset,the proposed BSKD model shows superior performance with 76.3%mAP,88.3%precision,90.1%recall and 92.6%F1 score.

Research on Rice Panicle L-system Model Based on Substructure Algorithm

In order to decrease model complexity of rice panicle for its complicated morphological structure,an interactive L-system based on substructure algorithm was proposed to model rice panicle in this study.Through the analysis of panicle morphology,the geometrical structure models of panicle spikelet,axis and branch were constructed firstly.Based on that,an interactive panicle L-system model was developed by using substructure algorithm to optimize panicle geometrical models with the similar structure.Simulation results showed that the interactive L-system panicle model based on substructure algorithm could fast construct panicle morphological structure in reality.In addition,this method had the well reference value for other plants model research.

Discrimination of rice panicles by hyperspectral reflectance data based on principal component analysis and support vector classification

Detection of crop health conditions plays an important role in making control strategies of crop disease and insect damage and gaining high-quality production at late growth stages. In this study, hyperspectral reflectance of rice panicles was measured at the visible and near-infrared regions. The panicles were divided into three groups according to health conditions： healthy panicles, empty panicles caused by Nilaparvata lugens St^l, and panicles infected with Ustilaginoidea virens. Low order derivative spectra, namely, the first and second orders, were obtained using different techniques. Principal component analysis （PCA） was performed to obtain the principal component spectra （PCS） of the foregoing derivative and raw spectra to reduce the reflectance spectral dimension. Support vector classification （SVC） was employed to discriminate the healthy, empty, and infected panicles, with the front three PCS as the in- dependent variables. The overall accuracy and kappa coefficient were used to assess the classification accuracy of SVC. The overall accuracies of SVC with PCS derived from the raw, first, and second reflectance spectra for the testing dataset were 96.55%, 99.14%, and 96.55%, and the kappa coefficients were 94.81%, 98.71%, and 94.82%, respectively. Our results demonstrated that it is feasible to use visible and near-infrared spectroscopy to discriminate health conditions of rice panicles.

Description of Aphelenchoides besseyi from Abnormal Rice with ‘Small Grains and Erect Panicles’ Symptom in China

The abnormal rice with small grains and erect panicles were found on a large scale in China, which showed shortend rice panicle and decreased number of grains in comparison with normal rice, and the grain was small and black-brown, and some of them were distorted, while the flag leaf was normal. A kind of nematode of Aphelenchoides was isolated from the grains of rice variety Wuyujing 3 which performed ＇small grains and erect panicles＇ symptom. There were 2014 nematodes in one hundred grains infected, and up to 74 in single grain, 92 percent of the grains tested had nematodes in the infested panicles. The diagnosis characters of nematode include lateral fields about one-fourth as wide as body, with 4 incisures. The terminus bears a mucro of diverse shape with 3-4 pointed processes. The female post-vulval uterine sac extends less than 50% of distance from vulva to anus, no sperm in it. Oocytes usually arrange in 2-4 rows. The male spicules have a moderately developed rostrum. Morphological measurements showed it to be conspecific with Aphelenchoides besseyi Christie, 1942.

Effect of Cultural Measures on Nutrient Contellts in Rice Plants with Erect Panicles

Field experiments were carried out with rice variety of Shennong 91 of short culms and erect panicles to study nutrient contents in high-yielding rice plants and to increase rice yield by appropriate fertilization.Nitrogen, phosphorus, potassium, magnesium, zinc, manganese, iron and copper contents in rice plants varied with different treatment factors. The relationship between the nutrient contents and treatment factors could be simulated using a multiple quadratic equation. The nutrient contents in plants should be appropriate for high-yielding rice. If the mean nutrient content in rice plants producing 11 t ha-1 or more of grain (μj) was set as the standard value and the standard deviation (σj) was set as the range of variation, the nutrient content in high-yielding rice plants should be μj±1.99σj. Rice leaves were sensitive to the nutrient elements. Heavy nitrogen dressing increased the content of nitrogen in rice plants. Sparse transplanting also increased nitrogen content. Improper application of nitrogen, phosphorus and potassium could affect the nutrient contents and decrease the grain yield.

Study on the Relationship of the Characteristics of Vascular Bundles in the First Internode and Grain-filling of Heavy Panicle Type Hybrid Rice

The characteristics of vascular bundle in the first internode from top and grain-filling of heavy panicle type hybrid rice(HPTHR) were studied. The results were as follows: The HPTHR had more vascular bundles and a much bigger area of single vascular bundle, all vascular bundle, all phloem and all xylem in the first inter-node than Shanyou63. The vascular bundles had the similar load of spikelet number and sink capacity between the HPTHR and Shanyou63. The HPTHR had not only a larger sink but also normal grain-filling and sink-filling, high seed-setting rate and heavier panicle. Those characteristics of vascular bundle were the biological bases for the larger and heavier panicle of HPTHR. The results also indicated that the breeding model of HPTHR was an effective measure for the super high-yielding rice breeding.

QTLs analysis of rice peduncle vascular bundle and panicle traits

The vascular bundle in plants plays an important role intransportation of photosynthetic products, mineral nutri-ents, water, arid so on. Significant positive correlationswere found between grain yield, panicle traits and the No.of peduncle vascular bundles. So, it is very important tostudy the inheritance of peduncle vascular bundle, whichis a quantitative trait.

Relationship between grain yield and ^(32)p,^(14)C in tiller and panicle of 56 hybrid rices

In recent years,much progress has been made inChina on the relationship between grain yield of Fhybrid rices and some physiological characters.Experiments were conducted in ourplant physiological lab during