The width of rice leaves determines the size of the photosynthetic area.Optimizing rice leaf width can improve the photosynthetic rate,thereby increasing rice yield.In this study,a genome-wide association study(GWAS)w...The width of rice leaves determines the size of the photosynthetic area.Optimizing rice leaf width can improve the photosynthetic rate,thereby increasing rice yield.In this study,a genome-wide association study(GWAS)was conducted by 225 rice germplasm resources to explore the genetic basis of rice flag leaf width(FLW).We identified nine QTLs associated with FLW(qFLWs),with phenotypic contribution rates ranging from 3.17%to 14.37%.Near-isogenic lines(NILs)were developed for fine-mapping of qFLW11,and the function of FLW11 was further verified.We narrowed down q FLW11 to an 87-kb interval,which contains five genes.展开更多
Rice leaf roller （Cnaphalocrocis medinalis Guenée） is a migratory pest, which mainly causes damage on rice. The morphology characteristic of rice leaf roller is introduced, which is also compared with the morph...Rice leaf roller （Cnaphalocrocis medinalis Guenée） is a migratory pest, which mainly causes damage on rice. The morphology characteristic of rice leaf roller is introduced, which is also compared with the morphology characteristic of the other insects such as Susumia exigua Butler and Tryporyza incertulas （walker）. The occurrence law, living habit and selection of prevention pesticides against rice leaf roller in China are summarized, which will provide the intergrated situation of rice leaf roller in China for worldwide further research on the insect.展开更多
As nearly half of the people in the world live on rice, so the rice leaf disease detection is very important for our agricultural sector. Many researchers worked on this problem and they achieved different results acc...As nearly half of the people in the world live on rice, so the rice leaf disease detection is very important for our agricultural sector. Many researchers worked on this problem and they achieved different results according to their applied techniques. In this paper, we applied AlexNet technique to detect the three prevalence rice leaf diseases termed as bacterial blight, brown spot as well as leaf smut and got a remarkable outcome rather than the previous works. AlexNet is a special type of classification technique of deep learning. This paper shows more than 99% accuracy due to adjusting an efficient technique and image augmentation.展开更多
In the field of agricultural information,the identification and prediction of rice leaf disease have always been the focus of research,and deep learning(DL)technology is currently a hot research topic in the field of ...In the field of agricultural information,the identification and prediction of rice leaf disease have always been the focus of research,and deep learning(DL)technology is currently a hot research topic in the field of pattern recognition.The research and development of high-efficiency,highquality and low-cost automatic identification methods for rice diseases that can replace humans is an important means of dealing with the current situation from a technical perspective.This paper mainly focuses on the problem of huge parameters of the Convolutional Neural Network(CNN)model and proposes a recognitionmodel that combines amulti-scale convolution module with a neural network model based on Visual Geometry Group(VGG).The accuracy and loss of the training set and the test set are used to evaluate the performance of the model.The test accuracy of this model is 97.1%that has increased 5.87%over VGG.Furthermore,the memory requirement is 26.1M,only 1.6%of the VGG.Experiment results show that this model performs better in terms of accuracy,recognition speed and memory size.展开更多
Eight insecticidal crystal proteins of Bacillus thuringiensis, CrylAa, CrylAb, CrylAc, CrylB, Cry2Aa, CrylC, CrylDa and Cry 1Ea were assessed for toxicity against 1 st instar larvae of rice leaf folder, Cnaphalocrocis...Eight insecticidal crystal proteins of Bacillus thuringiensis, CrylAa, CrylAb, CrylAc, CrylB, Cry2Aa, CrylC, CrylDa and Cry 1Ea were assessed for toxicity against 1 st instar larvae of rice leaf folder, Cnaphalocrocis medinalis （Guenee） at 48 HAT and 72 HAT. Bioassay results depicted CrylAa was the most toxic （LCso 2.35 ppm） followed by CrylBa （LCso 8,50 ppm） and CrylAb （LCso 8.73 ppm） at 48 HAT, whereas, at 72 HAT CrylAb proved to be highly toxic （LC50 0.50 ppm） followed by CrylAa （LCso 4.07 ppm）, CrylAc （LCso 4,84 ppm） and CrylBa （LCso 6.42 ppm）. Toxins Cry2Aa, CrylCa, CrylDa and CrylEa did not resulted in any mortality at 48 HAT and 72 HAT, respectively. Baseline estimates for CrylAb against 1st instar larvae of C. medinalis sampled from seven geographical locations revealed variation in LC50＇s from 0.37 ppm to LC50 16.25 ppm at 48 HAT and LC50 0.50 ppm to LC50 6.49 ppm 72 HAT, respectively with relative resistance ratios of 44-fold and 13-fold at 48 HAT and 72 HAT over the susceptible population.展开更多
Cs is one of the fission products of nuclearfuel.Cs can translocate to crop and then getinto human body by food chain,harming hu-manbeing’s health.Many works have reportedon the root absorption ofCs,but few re-ported...Cs is one of the fission products of nuclearfuel.Cs can translocate to crop and then getinto human body by food chain,harming hu-manbeing’s health.Many works have reportedon the root absorption ofCs,but few re-ported on the foliage absorption.展开更多
To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Cho...To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Chose mobile terminal equipment as image collecting tool and built database of rice leaf images with diseases under threshold segmentation method. Characteristic parameters were extracted from color, shape and texture. Furthermore, parameters were optimized using the single-factor variance analysis and the effects of BP neural network model. The optimization would simplify BP neural network model without reducing the recognition accuracy. The finally model could successfully recognize 98%, 96% and 98% of rice blast, sheath blight and white leaf blight, respectively.展开更多
Aromatic rice lines were examined for 2-Acetyl-1-Pyrroline (2AP) content in leaf tissue at five different growth stages (tillering, panicle initiation, 50% heading, booting, and maturity). A small plot trial with plot...Aromatic rice lines were examined for 2-Acetyl-1-Pyrroline (2AP) content in leaf tissue at five different growth stages (tillering, panicle initiation, 50% heading, booting, and maturity). A small plot trial with plot size of 1.42 m × 4.88 m (7 row-plots) was arranged in completely randomize design with three replications. Dry-seeded, delayed flood cultural practice was used in this study. The experiment was conducted at three locations. The average 2AP concentrations in leaf tissue at tillering stages were higher than the other four growth stages. 2AP levels were declined when rice plant reached booting. AP levels decreased slightly at heading stage and decreased significantly at maturity. There was no significant different between 2AP in leaf at 50% heading from three locations as well as the 2AP content in rice grain. Correlations between 2AP in leaf and 2AP in grain were significantly in all five growth stages. The highest correlation coefficient was found between 2AP in leaf at booting and grain (r = 0.811**) and lowest was in the leaf at harvest (r = 0.564**). Results indicated that 2AP could be determined in leaf tissue at early growth stage.展开更多
Rice is an essential food crop that is cultivated in many countries.Rice leaf diseases can cause significant damage to crop cultivation,leading to reduced yields and economic losses.Traditional disease detection appro...Rice is an essential food crop that is cultivated in many countries.Rice leaf diseases can cause significant damage to crop cultivation,leading to reduced yields and economic losses.Traditional disease detection approaches are often time-consuming,labor-intensive,and require expertise.Automatic leaf disease detection approaches help farmers detect diseases without or with less human interference.Most of the earlier studies on rice leaf disease detection depended on image processing and machine learning techniques.Image processing techniques are used to extract features from diseased leaf images,such as the color,texture,vein patterns,and shape of lesions.Machine learning techniques are used to detect diseases based on the extracted features.In contrast,deep learning techniques learn complex patterns from large datasets without explicit feature extraction techniques and are well-suited for disease detection tasks.This systematic review explores various deep learning approaches used in the literature for rice leaf disease detection,such as Transfer Learning,Ensemble Learning,and Hybrid approaches.This review also discusses the effectiveness of these approaches in addressing various challenges.This review discusses the details of various models and hyperparameter settings used,model fine-tuning techniques followed,and performance evaluation metrics utilized in various studies.This review also discusses the limitations of existing studies and presents future directions for further developing more robust and efficient rice leaf disease detection techniques.展开更多
Rice leaf diseases have an important impact on modern farming,threatening crop health and yield.Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease...Rice leaf diseases have an important impact on modern farming,threatening crop health and yield.Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease identification.However,the diversity of rice growing environments and the complexity of leaf diseases pose challenges.To address these issues,this study introduces an innovative semantic segmentation algorithm for rice leaf pests and diseases based on the Transformer architecture AISOA-SSformer.First,it features the sparse global-update perceptron for real-time parameter updating,enhancing model stability and accuracy in learning irregular leaf features.Second,the salient feature attention mechanism is introduced to separate and reorganize features using the spatial reconstruction module(SRM)and channel reconstruction module(CRM),focusing on salient feature extraction and reducing background interference.Additionally,the annealing-integrated sparrow optimization algorithm fine-tunes the sparrow algorithm,gradually reducing the stochastic search amplitude to minimize loss.This enhances the model's adaptability and robustness,particularly against fuzzy edge features.The experimental results show that AISOA-SSformer achieves an 83.1%MIoU,an 80.3%Dice coefficient,and a 76.5%recall on a homemade dataset,with a model size of only 14.71 million parameters.Compared with other popular algorithms,it demonstrates greater accuracy in rice leaf disease segmentation.This method effectively improves segmentation,providing valuable insights for modern plantation management.The data and code used in this study will be open sourced at .展开更多
Rice bacterial leaf streak,caused by Xanthomonas oryzae pv.oryzicola,is an important bacterial disease in rice-planting areas in South China and Southeast Asian countries.It occurs every year in local areas.This paper...Rice bacterial leaf streak,caused by Xanthomonas oryzae pv.oryzicola,is an important bacterial disease in rice-planting areas in South China and Southeast Asian countries.It occurs every year in local areas.This paper reviews the research advance in the occurrence and harms of rice bacterial leaf streak in China,classification of Xanthomonas oryzae and infection characteristics,pathogenic factors and pathogenicity of rice bacterial leaf streak and breeding of bacterial leaf streakresistance rice cultivars.Some issues involved in occurrence and control of rice bacterial leaf streak were presented,and the areas on which the future studies might be focused were discussed.展开更多
Two varieties, Yuexinzhan and Guangchao 3, were used to study leaf thickness in rice in this experiment. The thickness of the leaf blade was measured by the nondestructive leaf thickness instrument, which was modified...Two varieties, Yuexinzhan and Guangchao 3, were used to study leaf thickness in rice in this experiment. The thickness of the leaf blade was measured by the nondestructive leaf thickness instrument, which was modified from the thickness instrument for steel objects （John Bull, England）. The contacting area between the leaf and the probe of the instrument was 0.5 cm^2. There was no significant difference between the thickness of steel materials measured by the nondestructive rice leaf thickness instrument and the micrometer. The correlation between the thickness of the rice leaf blade measured by the nondestructive rice leaf thickness instrument and the specific leaf weight （SLW） was significant （P 〈 0.05 or P〈 0.01）. The results also showed that the rice leaf thickness was uneven and asymmetric. The thickness and SLW of flag leaf tended to increase from the base to the tip of the leaf blade. The middle part of the second and third top leaf was the thickest, but no significant difference in thickness between the basal part and the fore part was found. Drawing a line on the main vein in the top three leaves, the left part was thinner than the right part. The thickness of the lower leaves （6/0-9/0） on the main culm tended to increase with increasing positions of the leaves in the early and middle stages, but the tendency was not the same for the higher leaves （10/0 upwards）, although the higher leaves （10/0 upward） were thicker than the lower leaves （9/0 or downward）. Furthermore, different CO2 concentrations （550±30, 460 ± 30 μmol mol^-1） in the growth boxes had no effect on the thickness of rice leaf blades. It can be concluded that the measurement of rice leaf thickness using the nondestructive rice leaf thickness instrument is simple, precise, and nondestructive.展开更多
Rice stands as a crucial staple food globally,with its enduring sustainability hinging on the prompt detection of rice leaf diseases.Hence,efficiently detecting diseases when they have already occurred holds paramount...Rice stands as a crucial staple food globally,with its enduring sustainability hinging on the prompt detection of rice leaf diseases.Hence,efficiently detecting diseases when they have already occurred holds paramount importance for solving the cost of manual visual identification and chemical testing.In the recent past,the identification of leaf pathologies in crops predominantly relies on manual methods using specialized equipment,which proves to be time-consuming and inefficient.This study offers a remedy by harnessing Deep Learning(DL)and transfer learning techniques to accurately identify and classify rice leaf diseases.A comprehensive dataset comprising 5932 self-generated images of rice leaves was assembled along with the benchmark datasets,categorized into 9 classes irrespective of the extent of disease spread across the leaves.These classes encompass diverse states including healthy leaves,mild and severe blight,mild and severe tungro,mild and severe blast,as well as mild and severe brown spot.Following meticulous manual labelling and dataset segmentation,which was validated by horticulture experts,data augmentation strategies were implemented to amplify the number of images.The datasets were subjected to evaluation using the proposed tailored Convolutional Neural Networks models.Their performance are scrutinized in conjunction with alternative transfer learning approaches like VGG16,Xception,ResNet50,DenseNet121,Inception ResnetV2,and Inception V3.The effectiveness of the proposed custom VGG16 model was gauged by its capacity to generalize to unseen images,yielding an exceptional accuracy of 99.94%,surpassing the benchmarks set by existing state-of-the-art models.Further,the layer wise feature extraction is also visualized as the interpretable AI.展开更多
[Objective] The aim was to carry out the quality research on a purple leaf mutant （PLM） of rice and provide the basis for applied research of purple rice.[Method] A newly discovered purple mutant of rice and its hyb...[Objective] The aim was to carry out the quality research on a purple leaf mutant （PLM） of rice and provide the basis for applied research of purple rice.[Method] A newly discovered purple mutant of rice and its hybrid filial generations （F1 and F2） were employed as the experimental materials to determine its characteristic indexes,such as grain type,chalky grain rate,chalkiness,1 000-grain weight,brown rice percentage,protein content,amylose content,gelatinization temperature and consistency.[Result] The grain type and brown rice percentage of the parent （pro-Z） both reached standard of Ⅰ Grade,while chalky grain rate,chalkiness,amylose content and consistency did not meet the requirements of the standard.The F2 generation displayed some optimized properties,including larger grain,lower amylose content,reduced chalkiness,lower chalky grain rate and softened consistency.[Conclusion] The majority of the characteristic indexes of pro-Z did not meet the requirements of standard,but the qualities of F2 generation were all optimized to some extent.展开更多
The angle of rice leaf inclination is an important agronomic trait and closely related to the yields and archi- tecture of crops. Although few mutants with altered leaf angles have been reported, the molecular mechani...The angle of rice leaf inclination is an important agronomic trait and closely related to the yields and archi- tecture of crops. Although few mutants with altered leaf angles have been reported, the molecular mechanism remains to be elucidated, especially whether hormones are involved in this process. Through genetic screening, a rice gain-of- function mutant leaf inclination1, Icl-D, was identified from the Shanghai T-DNA Insertion Population （SHIP）. Phenotypic analysis confirmed the exaggerated leaf angles of Icl-D due to the stimulated cell elongation at the lamina joint. LC1 is transcribed in various tissues and encodes OsGH3-1, an indole-3-acetic acid （IAA） amido synthetase, whose homolog of Arabidopsis functions in maintaining the auxin homeostasis by conjugating excess IAA to various amino acids. Indeed, recombinant LC1 can catalyze the conjugation of IAA to Ala, Asp, and Asn in vitro, which is consistent with the decreased free IAA amount in Icl-D mutant. Icl-D is insensitive to IAA and hypersensitive to exogenous BR, in agreement with the microarray analysis that reveals the altered transcriptions of genes involved in auxin signaling and BR biosynthesis. These results indicate the crucial roles of auxin homeostasis in the leaf inclination control.展开更多
Leaf area index （LAI） is an important characteristic of land surface vegetation system, and is also a key parameter for the models of global water balancing and carbon circulation. By using the reflectance values of...Leaf area index （LAI） is an important characteristic of land surface vegetation system, and is also a key parameter for the models of global water balancing and carbon circulation. By using the reflectance values of Landsat-5 blue, green and red channels simulated from rice reflectance spectrum, the sensitivities of the bands to LAI were analyzed, and the response and capability to estimate LAI of various NDVIs （normalized difference vegetation indices）, which were established by substituting the red band of general NDVI with all possible combinations of red, green and blue bands, were assessed. Finally, the conclusion was tested by rice data at different conditions. The sensitivities of red, green and blue bands to LAI were different under various conditions. When LAI was less than 3, red and blue bands were more sensitive to LAI. Though green band in the circumstances was less sensitive to LAI than red and blue bands, it was sensitive to LAI in a wider range. When the vegetation indices were constituted by all kinds of combinations of red, green and blue bands, the premise for making the sensitivity of these vegetation indices to LAI be meaningful was that the value of one of the combinations was greater than 0.024, i.e. visible reflectance （VIS）〉0.024. Otherwise, the vegetation indices would be saturated, resulting in lower estimation accuracy of LAI. Comparison on the capabilities of the vegetation indices derived from all kinds of combinations of red, green and blue bands to LAI estimation showed that GNDVI （Green NDVI） and GBNDVI （Green-Blue NDVI） had the best relations with LAI. The capabilities of GNDVI and GBNDVI to LAI estimation were tested under different circumstances, and the same result was acquired. It suggested that GNDVI and GBNDVI performed better to predict LAI than the conventional NDVI.展开更多
Leaf thickness is an important morphological trait in rice. Its association to the yield potential, as of now has not been documented because of the shortage of the equipment which could conveniently measure the leaf ...Leaf thickness is an important morphological trait in rice. Its association to the yield potential, as of now has not been documented because of the shortage of the equipment which could conveniently measure the leaf thickness in rice. In this study, the thickness of top three leaves of 208 cultivars had been determined by a nondestructive rice leaf thickness instrument for the research of the natural variation of leaves thickness and its association to yield traits in indica rice. The results showed that the flag leaf was the thickest, and the 2nd leaf was thicker than the 3rd leaf. Analysis of variance indicated the existence of wide genetic diversity of leaf thickness among the investigated indica rice genotypes. The tight correlation among the thicknesses of the top three leaves means that the leaf thickness traits share one genetic control system. Leaf thickness had a significant positive correlation with leaf length and a positive correlation with leaf width, indicated that thicker leaf was beneficial to increasing the single leaf area. The results of correlation analysis revealed that thicker leaf should be profitable to the leaf erection, higher numbers of grains per panicle and higher grains weight per panicle. However, the significantly negative correlation between leaf thickness and number of panicles per plant counteracted the profitability from increased grains weight per panicle, so that the correlations of the thicknesses of the top three leaves to yield and biomass were positive but not significantly. It has made great progress in the genetic improvement of leaves thickness in inbred indica rice breeding in Guangdong Province, China, since the 1990s.展开更多
In nature,rice leaves exhibit special anisotropic sliding capabilities.Although researchers have succeeded in fabricating artificial rice leaf structures and realizing the wettability function of the leaf surface,thes...In nature,rice leaves exhibit special anisotropic sliding capabilities.Although researchers have succeeded in fabricating artificial rice leaf structures and realizing the wettability function of the leaf surface,these methods used to date are complex and do not allow the fabrication of surfaces with large area.Herein,we adopted a simple technology—two steps soft transfer to fabricate biomimetic rice leaf.The fabricated surface well reproduced the structures of the rice leaf surface and exhibited a static superhydrophobic property similar to that of the real rice leaf surface.In terms of its dynamic wettability,it clearly exhibited an anisotropic sliding property.Systematic measurements showed that the sliding angles parallel and perpendicular with the vein direction were 25° and 40°,respectively.The method was simple and reliable,without the need for expensive instruments and complex technologies,which could be used for the rapid fabrication of large-area artificial rice leaf surfaces.We believe that the artificial rice leaf surface fabricated by this method has great potential applications in biomimetic functional surfaces,microfluidics,and so on.展开更多
This paper was to develop a model for simulating the leaf color changes in rice （Oryza sativa L.） based on RGB （red, green, and blue） values. Based on rice experiment data with different cultivars and nitrogen （N...This paper was to develop a model for simulating the leaf color changes in rice （Oryza sativa L.） based on RGB （red, green, and blue） values. Based on rice experiment data with different cultivars and nitrogen （N） rates, the time-course RGB values of each leaf on main stem were collected during the growth period in rice, and a model for simulating the dynamics of leaf color in rice was then developed using quantitative modeling technology. The results showed that the RGB values of leaf color gradually decreased from the initial values （light green） to the steady values （green） during the first stage, remained the steady values （green） during the second stage, then gradually increased to the final values （from green to yellow） during the third stage. The decreasing linear functions, constant functions and increasing linear functions were used to simulate the changes in RGB values of leaf color at the first, second and third stages with growing degree days （GDD）, respectively; two cultivar parameters, MatRGB （leaf color matrix） and AR （a vector composed of the ratio of the cumulative GDD of each stage during color change process of leaf n to that during leaf n drawn under adequate N status）, were introduced to quantify the genetic characters in RGB values of leaf color and in durations of different stages during leaf color change, respectively; FN （N impact factor） was used to quantify the effects of N levels on RGB values of leaf color and on durations of different stages during leaf color change; linear functions were applied to simulate the changes in leaf color along the leaf midvein direction during leaf development process. Validation of the models with the independent experiment dataset exhibited that the root mean square errors （RMSE） between the observed and simulated RGB values were among 8 to 13, the relative RMSE （RRMSE） were among 8 to 10%, the mean absolute differences （da） were among 3.85 to 6.90, and the ratio of da to the mean observation values （Clap） were among 3.04 to 4.90%. In addition, the leaf color model was used to render the leaf color change over growth progress using the technology of visualization, with a good performance on predicting dynamic changes in rice leaf color. These results would provide a technical support for further developing virtual plant during rice growth and development.展开更多
基金supported by the Zhejiang Provincial Natural Science Foundation,China(Grant No.LD24C130001)the National Natural Science Foundation of China(Grant Nos.W2412006 and 32372125)+3 种基金the Hainan Provincial Natural Science Foundation,China(Grant Nos.GHYF2025029 and YBXM2422)the Innovation Platform for Academicians of Hainan Province,China(Grant No.YSPTZX202502)the National Modern Agricultural Industry Technology System Project,China(Grant No.CARS-01-18)the Special Support Program of Chinese Academy of Agricultural Sciences(Grant Nos.NKYCLJ-C-2021-015 and CAAS-ZDRW202401)。
文摘The width of rice leaves determines the size of the photosynthetic area.Optimizing rice leaf width can improve the photosynthetic rate,thereby increasing rice yield.In this study,a genome-wide association study(GWAS)was conducted by 225 rice germplasm resources to explore the genetic basis of rice flag leaf width(FLW).We identified nine QTLs associated with FLW(qFLWs),with phenotypic contribution rates ranging from 3.17%to 14.37%.Near-isogenic lines(NILs)were developed for fine-mapping of qFLW11,and the function of FLW11 was further verified.We narrowed down q FLW11 to an 87-kb interval,which contains five genes.
文摘Rice leaf roller （Cnaphalocrocis medinalis Guenée） is a migratory pest, which mainly causes damage on rice. The morphology characteristic of rice leaf roller is introduced, which is also compared with the morphology characteristic of the other insects such as Susumia exigua Butler and Tryporyza incertulas （walker）. The occurrence law, living habit and selection of prevention pesticides against rice leaf roller in China are summarized, which will provide the intergrated situation of rice leaf roller in China for worldwide further research on the insect.
文摘As nearly half of the people in the world live on rice, so the rice leaf disease detection is very important for our agricultural sector. Many researchers worked on this problem and they achieved different results according to their applied techniques. In this paper, we applied AlexNet technique to detect the three prevalence rice leaf diseases termed as bacterial blight, brown spot as well as leaf smut and got a remarkable outcome rather than the previous works. AlexNet is a special type of classification technique of deep learning. This paper shows more than 99% accuracy due to adjusting an efficient technique and image augmentation.
基金supported by National key research and development program sub-topics[2018YFF0213606-03(Mu Y.,Hu T.L.,Gong H.,Li S.J.and Sun Y.H.)http://www.most.gov.cn]Jilin Province Science and Technology Development Plan focuses on research and development projects[20200402006NC(Mu Y.,Hu T.L.,Gong H.and Li S.J.)http://kjt.jl.gov.cn]+1 种基金Science and technology support project for key industries in southern Xinjiang[2018DB001(Gong H.,and Li S.J.)http://kjj.xjbt.gov.cn]Key technology R&D project of Changchun Science and Technology Bureau of Jilin Province[21ZGN29(Mu Y.,Bao H.P.,Wang X.B.)http://kjj.changchun.gov.cn].
文摘In the field of agricultural information,the identification and prediction of rice leaf disease have always been the focus of research,and deep learning(DL)technology is currently a hot research topic in the field of pattern recognition.The research and development of high-efficiency,highquality and low-cost automatic identification methods for rice diseases that can replace humans is an important means of dealing with the current situation from a technical perspective.This paper mainly focuses on the problem of huge parameters of the Convolutional Neural Network(CNN)model and proposes a recognitionmodel that combines amulti-scale convolution module with a neural network model based on Visual Geometry Group(VGG).The accuracy and loss of the training set and the test set are used to evaluate the performance of the model.The test accuracy of this model is 97.1%that has increased 5.87%over VGG.Furthermore,the memory requirement is 26.1M,only 1.6%of the VGG.Experiment results show that this model performs better in terms of accuracy,recognition speed and memory size.
文摘Eight insecticidal crystal proteins of Bacillus thuringiensis, CrylAa, CrylAb, CrylAc, CrylB, Cry2Aa, CrylC, CrylDa and Cry 1Ea were assessed for toxicity against 1 st instar larvae of rice leaf folder, Cnaphalocrocis medinalis （Guenee） at 48 HAT and 72 HAT. Bioassay results depicted CrylAa was the most toxic （LCso 2.35 ppm） followed by CrylBa （LCso 8,50 ppm） and CrylAb （LCso 8.73 ppm） at 48 HAT, whereas, at 72 HAT CrylAb proved to be highly toxic （LC50 0.50 ppm） followed by CrylAa （LCso 4.07 ppm）, CrylAc （LCso 4,84 ppm） and CrylBa （LCso 6.42 ppm）. Toxins Cry2Aa, CrylCa, CrylDa and CrylEa did not resulted in any mortality at 48 HAT and 72 HAT, respectively. Baseline estimates for CrylAb against 1st instar larvae of C. medinalis sampled from seven geographical locations revealed variation in LC50＇s from 0.37 ppm to LC50 16.25 ppm at 48 HAT and LC50 0.50 ppm to LC50 6.49 ppm 72 HAT, respectively with relative resistance ratios of 44-fold and 13-fold at 48 HAT and 72 HAT over the susceptible population.
文摘Cs is one of the fission products of nuclearfuel.Cs can translocate to crop and then getinto human body by food chain,harming hu-manbeing’s health.Many works have reportedon the root absorption ofCs,but few re-ported on the foliage absorption.
基金Supported by Quality and Brand Construction of"Internet+County Characteristic Agricultural Products"(ZY17C06)
文摘To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Chose mobile terminal equipment as image collecting tool and built database of rice leaf images with diseases under threshold segmentation method. Characteristic parameters were extracted from color, shape and texture. Furthermore, parameters were optimized using the single-factor variance analysis and the effects of BP neural network model. The optimization would simplify BP neural network model without reducing the recognition accuracy. The finally model could successfully recognize 98%, 96% and 98% of rice blast, sheath blight and white leaf blight, respectively.
文摘Aromatic rice lines were examined for 2-Acetyl-1-Pyrroline (2AP) content in leaf tissue at five different growth stages (tillering, panicle initiation, 50% heading, booting, and maturity). A small plot trial with plot size of 1.42 m × 4.88 m (7 row-plots) was arranged in completely randomize design with three replications. Dry-seeded, delayed flood cultural practice was used in this study. The experiment was conducted at three locations. The average 2AP concentrations in leaf tissue at tillering stages were higher than the other four growth stages. 2AP levels were declined when rice plant reached booting. AP levels decreased slightly at heading stage and decreased significantly at maturity. There was no significant different between 2AP in leaf at 50% heading from three locations as well as the 2AP content in rice grain. Correlations between 2AP in leaf and 2AP in grain were significantly in all five growth stages. The highest correlation coefficient was found between 2AP in leaf at booting and grain (r = 0.811**) and lowest was in the leaf at harvest (r = 0.564**). Results indicated that 2AP could be determined in leaf tissue at early growth stage.
文摘Rice is an essential food crop that is cultivated in many countries.Rice leaf diseases can cause significant damage to crop cultivation,leading to reduced yields and economic losses.Traditional disease detection approaches are often time-consuming,labor-intensive,and require expertise.Automatic leaf disease detection approaches help farmers detect diseases without or with less human interference.Most of the earlier studies on rice leaf disease detection depended on image processing and machine learning techniques.Image processing techniques are used to extract features from diseased leaf images,such as the color,texture,vein patterns,and shape of lesions.Machine learning techniques are used to detect diseases based on the extracted features.In contrast,deep learning techniques learn complex patterns from large datasets without explicit feature extraction techniques and are well-suited for disease detection tasks.This systematic review explores various deep learning approaches used in the literature for rice leaf disease detection,such as Transfer Learning,Ensemble Learning,and Hybrid approaches.This review also discusses the effectiveness of these approaches in addressing various challenges.This review discusses the details of various models and hyperparameter settings used,model fine-tuning techniques followed,and performance evaluation metrics utilized in various studies.This review also discusses the limitations of existing studies and presents future directions for further developing more robust and efficient rice leaf disease detection techniques.
基金supported by the Changsha Municipal Natural Science Foundation(grant no.kq2014160)in part by the National Natural Science Foundation in China(grant no.61703441)+2 种基金in part by the Key Projects of the Department of Education,Hunan Province(grant no.19A511)in part by the Hunan Key Laboratory of Intelligent Logistics Technology(grant no.2019TP1015)in part by the National Natural Science Foundation of China(grant no.61902436).
文摘Rice leaf diseases have an important impact on modern farming,threatening crop health and yield.Accurate semantic segmentation techniques are crucial for segmenting diseased leaf parts and assisting farmers in disease identification.However,the diversity of rice growing environments and the complexity of leaf diseases pose challenges.To address these issues,this study introduces an innovative semantic segmentation algorithm for rice leaf pests and diseases based on the Transformer architecture AISOA-SSformer.First,it features the sparse global-update perceptron for real-time parameter updating,enhancing model stability and accuracy in learning irregular leaf features.Second,the salient feature attention mechanism is introduced to separate and reorganize features using the spatial reconstruction module(SRM)and channel reconstruction module(CRM),focusing on salient feature extraction and reducing background interference.Additionally,the annealing-integrated sparrow optimization algorithm fine-tunes the sparrow algorithm,gradually reducing the stochastic search amplitude to minimize loss.This enhances the model's adaptability and robustness,particularly against fuzzy edge features.The experimental results show that AISOA-SSformer achieves an 83.1%MIoU,an 80.3%Dice coefficient,and a 76.5%recall on a homemade dataset,with a model size of only 14.71 million parameters.Compared with other popular algorithms,it demonstrates greater accuracy in rice leaf disease segmentation.This method effectively improves segmentation,providing valuable insights for modern plantation management.The data and code used in this study will be open sourced at .
基金Supported by Special Fund for Agro-scientific Research in the Public Interest(201303015201103002-3)+2 种基金Natural Science Foundation of Jiangsu Province(BK20130713)Jiangsu Agricultural Science and Technology Innovation Fund(CX(12)3058)National High Technology Research and Development Program of China(863Program)(2011AA10A201)~~
文摘Rice bacterial leaf streak,caused by Xanthomonas oryzae pv.oryzicola,is an important bacterial disease in rice-planting areas in South China and Southeast Asian countries.It occurs every year in local areas.This paper reviews the research advance in the occurrence and harms of rice bacterial leaf streak in China,classification of Xanthomonas oryzae and infection characteristics,pathogenic factors and pathogenicity of rice bacterial leaf streak and breeding of bacterial leaf streakresistance rice cultivars.Some issues involved in occurrence and control of rice bacterial leaf streak were presented,and the areas on which the future studies might be focused were discussed.
基金the Natural Science Foundation of Guangdong Province, China.
文摘Two varieties, Yuexinzhan and Guangchao 3, were used to study leaf thickness in rice in this experiment. The thickness of the leaf blade was measured by the nondestructive leaf thickness instrument, which was modified from the thickness instrument for steel objects （John Bull, England）. The contacting area between the leaf and the probe of the instrument was 0.5 cm^2. There was no significant difference between the thickness of steel materials measured by the nondestructive rice leaf thickness instrument and the micrometer. The correlation between the thickness of the rice leaf blade measured by the nondestructive rice leaf thickness instrument and the specific leaf weight （SLW） was significant （P 〈 0.05 or P〈 0.01）. The results also showed that the rice leaf thickness was uneven and asymmetric. The thickness and SLW of flag leaf tended to increase from the base to the tip of the leaf blade. The middle part of the second and third top leaf was the thickest, but no significant difference in thickness between the basal part and the fore part was found. Drawing a line on the main vein in the top three leaves, the left part was thinner than the right part. The thickness of the lower leaves （6/0-9/0） on the main culm tended to increase with increasing positions of the leaves in the early and middle stages, but the tendency was not the same for the higher leaves （10/0 upwards）, although the higher leaves （10/0 upward） were thicker than the lower leaves （9/0 or downward）. Furthermore, different CO2 concentrations （550±30, 460 ± 30 μmol mol^-1） in the growth boxes had no effect on the thickness of rice leaf blades. It can be concluded that the measurement of rice leaf thickness using the nondestructive rice leaf thickness instrument is simple, precise, and nondestructive.
文摘Rice stands as a crucial staple food globally,with its enduring sustainability hinging on the prompt detection of rice leaf diseases.Hence,efficiently detecting diseases when they have already occurred holds paramount importance for solving the cost of manual visual identification and chemical testing.In the recent past,the identification of leaf pathologies in crops predominantly relies on manual methods using specialized equipment,which proves to be time-consuming and inefficient.This study offers a remedy by harnessing Deep Learning(DL)and transfer learning techniques to accurately identify and classify rice leaf diseases.A comprehensive dataset comprising 5932 self-generated images of rice leaves was assembled along with the benchmark datasets,categorized into 9 classes irrespective of the extent of disease spread across the leaves.These classes encompass diverse states including healthy leaves,mild and severe blight,mild and severe tungro,mild and severe blast,as well as mild and severe brown spot.Following meticulous manual labelling and dataset segmentation,which was validated by horticulture experts,data augmentation strategies were implemented to amplify the number of images.The datasets were subjected to evaluation using the proposed tailored Convolutional Neural Networks models.Their performance are scrutinized in conjunction with alternative transfer learning approaches like VGG16,Xception,ResNet50,DenseNet121,Inception ResnetV2,and Inception V3.The effectiveness of the proposed custom VGG16 model was gauged by its capacity to generalize to unseen images,yielding an exceptional accuracy of 99.94%,surpassing the benchmarks set by existing state-of-the-art models.Further,the layer wise feature extraction is also visualized as the interpretable AI.
文摘[Objective] The aim was to carry out the quality research on a purple leaf mutant （PLM） of rice and provide the basis for applied research of purple rice.[Method] A newly discovered purple mutant of rice and its hybrid filial generations （F1 and F2） were employed as the experimental materials to determine its characteristic indexes,such as grain type,chalky grain rate,chalkiness,1 000-grain weight,brown rice percentage,protein content,amylose content,gelatinization temperature and consistency.[Result] The grain type and brown rice percentage of the parent （pro-Z） both reached standard of Ⅰ Grade,while chalky grain rate,chalkiness,amylose content and consistency did not meet the requirements of the standard.The F2 generation displayed some optimized properties,including larger grain,lower amylose content,reduced chalkiness,lower chalky grain rate and softened consistency.[Conclusion] The majority of the characteristic indexes of pro-Z did not meet the requirements of standard,but the qualities of F2 generation were all optimized to some extent.
文摘The angle of rice leaf inclination is an important agronomic trait and closely related to the yields and archi- tecture of crops. Although few mutants with altered leaf angles have been reported, the molecular mechanism remains to be elucidated, especially whether hormones are involved in this process. Through genetic screening, a rice gain-of- function mutant leaf inclination1, Icl-D, was identified from the Shanghai T-DNA Insertion Population （SHIP）. Phenotypic analysis confirmed the exaggerated leaf angles of Icl-D due to the stimulated cell elongation at the lamina joint. LC1 is transcribed in various tissues and encodes OsGH3-1, an indole-3-acetic acid （IAA） amido synthetase, whose homolog of Arabidopsis functions in maintaining the auxin homeostasis by conjugating excess IAA to various amino acids. Indeed, recombinant LC1 can catalyze the conjugation of IAA to Ala, Asp, and Asn in vitro, which is consistent with the decreased free IAA amount in Icl-D mutant. Icl-D is insensitive to IAA and hypersensitive to exogenous BR, in agreement with the microarray analysis that reveals the altered transcriptions of genes involved in auxin signaling and BR biosynthesis. These results indicate the crucial roles of auxin homeostasis in the leaf inclination control.
文摘Leaf area index （LAI） is an important characteristic of land surface vegetation system, and is also a key parameter for the models of global water balancing and carbon circulation. By using the reflectance values of Landsat-5 blue, green and red channels simulated from rice reflectance spectrum, the sensitivities of the bands to LAI were analyzed, and the response and capability to estimate LAI of various NDVIs （normalized difference vegetation indices）, which were established by substituting the red band of general NDVI with all possible combinations of red, green and blue bands, were assessed. Finally, the conclusion was tested by rice data at different conditions. The sensitivities of red, green and blue bands to LAI were different under various conditions. When LAI was less than 3, red and blue bands were more sensitive to LAI. Though green band in the circumstances was less sensitive to LAI than red and blue bands, it was sensitive to LAI in a wider range. When the vegetation indices were constituted by all kinds of combinations of red, green and blue bands, the premise for making the sensitivity of these vegetation indices to LAI be meaningful was that the value of one of the combinations was greater than 0.024, i.e. visible reflectance （VIS）〉0.024. Otherwise, the vegetation indices would be saturated, resulting in lower estimation accuracy of LAI. Comparison on the capabilities of the vegetation indices derived from all kinds of combinations of red, green and blue bands to LAI estimation showed that GNDVI （Green NDVI） and GBNDVI （Green-Blue NDVI） had the best relations with LAI. The capabilities of GNDVI and GBNDVI to LAI estimation were tested under different circumstances, and the same result was acquired. It suggested that GNDVI and GBNDVI performed better to predict LAI than the conventional NDVI.
基金supported by the Natural Science Foundation of Guangdong Province,China (6025378,S2011010000983)
文摘Leaf thickness is an important morphological trait in rice. Its association to the yield potential, as of now has not been documented because of the shortage of the equipment which could conveniently measure the leaf thickness in rice. In this study, the thickness of top three leaves of 208 cultivars had been determined by a nondestructive rice leaf thickness instrument for the research of the natural variation of leaves thickness and its association to yield traits in indica rice. The results showed that the flag leaf was the thickest, and the 2nd leaf was thicker than the 3rd leaf. Analysis of variance indicated the existence of wide genetic diversity of leaf thickness among the investigated indica rice genotypes. The tight correlation among the thicknesses of the top three leaves means that the leaf thickness traits share one genetic control system. Leaf thickness had a significant positive correlation with leaf length and a positive correlation with leaf width, indicated that thicker leaf was beneficial to increasing the single leaf area. The results of correlation analysis revealed that thicker leaf should be profitable to the leaf erection, higher numbers of grains per panicle and higher grains weight per panicle. However, the significantly negative correlation between leaf thickness and number of panicles per plant counteracted the profitability from increased grains weight per panicle, so that the correlations of the thicknesses of the top three leaves to yield and biomass were positive but not significantly. It has made great progress in the genetic improvement of leaves thickness in inbred indica rice breeding in Guangdong Province, China, since the 1990s.
基金supported by the National Natural Science Foundation of China(60525412,61077002 and 90923037)
文摘In nature,rice leaves exhibit special anisotropic sliding capabilities.Although researchers have succeeded in fabricating artificial rice leaf structures and realizing the wettability function of the leaf surface,these methods used to date are complex and do not allow the fabrication of surfaces with large area.Herein,we adopted a simple technology—two steps soft transfer to fabricate biomimetic rice leaf.The fabricated surface well reproduced the structures of the rice leaf surface and exhibited a static superhydrophobic property similar to that of the real rice leaf surface.In terms of its dynamic wettability,it clearly exhibited an anisotropic sliding property.Systematic measurements showed that the sliding angles parallel and perpendicular with the vein direction were 25° and 40°,respectively.The method was simple and reliable,without the need for expensive instruments and complex technologies,which could be used for the rapid fabrication of large-area artificial rice leaf surfaces.We believe that the artificial rice leaf surface fabricated by this method has great potential applications in biomimetic functional surfaces,microfluidics,and so on.
基金the National High-Tech R&D Program of China(2013AA100404,2012AA101306-2)the Priority Academic Program Development of Jiangsu Higher Education Institutions of China(PAPD)
文摘This paper was to develop a model for simulating the leaf color changes in rice （Oryza sativa L.） based on RGB （red, green, and blue） values. Based on rice experiment data with different cultivars and nitrogen （N） rates, the time-course RGB values of each leaf on main stem were collected during the growth period in rice, and a model for simulating the dynamics of leaf color in rice was then developed using quantitative modeling technology. The results showed that the RGB values of leaf color gradually decreased from the initial values （light green） to the steady values （green） during the first stage, remained the steady values （green） during the second stage, then gradually increased to the final values （from green to yellow） during the third stage. The decreasing linear functions, constant functions and increasing linear functions were used to simulate the changes in RGB values of leaf color at the first, second and third stages with growing degree days （GDD）, respectively; two cultivar parameters, MatRGB （leaf color matrix） and AR （a vector composed of the ratio of the cumulative GDD of each stage during color change process of leaf n to that during leaf n drawn under adequate N status）, were introduced to quantify the genetic characters in RGB values of leaf color and in durations of different stages during leaf color change, respectively; FN （N impact factor） was used to quantify the effects of N levels on RGB values of leaf color and on durations of different stages during leaf color change; linear functions were applied to simulate the changes in leaf color along the leaf midvein direction during leaf development process. Validation of the models with the independent experiment dataset exhibited that the root mean square errors （RMSE） between the observed and simulated RGB values were among 8 to 13, the relative RMSE （RRMSE） were among 8 to 10%, the mean absolute differences （da） were among 3.85 to 6.90, and the ratio of da to the mean observation values （Clap） were among 3.04 to 4.90%. In addition, the leaf color model was used to render the leaf color change over growth progress using the technology of visualization, with a good performance on predicting dynamic changes in rice leaf color. These results would provide a technical support for further developing virtual plant during rice growth and development.
