250 results about "Leaf disease" patented technology

A method for identifying crop leaf diseases based on an improved convolution neural network model AlexNet is disclosed. Firstly, the expanded and balanced data set is divided into a training set and atest set according to the ratio of 4: 1, and the picture data set is normalized, averaged and so on. Then the iterative input samples are trained to set and optimize the relevant parameters of the network. Finally, the trained network is tested using the test set. It is found that the average classification accuracy of the improved model is 99.3% and the loss rate is only 2%. On this basis, the invention also conducts a comparative experiment based on the gray image and the segmented image training network to explore the influence of the background and the color on the crop disease identification system. The analysis result shows that the disease identification method of the invention has high accuracy rate and low loss rate for disease identification classification of crops, and featuressuch as color and background of the fused image can improve the identification effect.

The invention relates to a Bacillus subtilis T-500. The Bacillus subtilis T-500 has been preserved in CGMCC (China General Microbiological Culture Collection), and the preservation number is CGMCC NO:6058. The Bacillus subtilis T-500 can be used as a biological pesticide for preventing and treating multiple plant diseases, and can also be used as a biological fertilizer for promoting the yield increase of crops. The Bacillus subtilis T-500 has higher antibacterial activity on Magnaporthe oryzae, Pellicularia sasakii, Xanthomonas oryzae, Ustilaginoidea virens, Xanthomonas oryzae pv. oryzicola, Fusarium graminearum, Aspergillus flavus, Aspergillus niger and other pathogenic bacteria, and has better prevention and control effects on diseases caused by the pathogenic bacteria. The Bacillus subtilis T-500 can prevent and treat rice leaf diseases when being diluted 200-500 times on the leaves of rice, can prevent and treat bakanae diseases of rice after seed soaking, and can prevent and treat soil-borne diseases of vegetables and the like after root irrigation.

The invention discloses a cucumber disease identification method and apparatus based on image information, and relates to the fields of system engineering and information technology. The invention acquires a leaf disease image of a cucumber to be identified; carries out image segmentation for the leaf disease image to obtain segmented leaf patches; extracts features of the leaf patches to obtain disease feature information; carries out disease identification for the disease feature information according to a preset disease feature sample, to obtain the disease of the cucumber to be identified; and therefore, improves the accuracy of identification, and avoids subjectivity and limitation due to artificial identification.

The invention relates to a computer vision-based rice disease, pest and weed diagnostic method. The method comprises the following steps: collecting different varieties of rice leaf disease samples at different morbidity periods in different growth environments, and letting a plant disease expert identify the diseases infecting all the samples; then acquiring images of disease symptoms of the samples; realizing the automatic segmentation of disease spots by utilizing an image processing technology; extracting all characteristic indexes of the disease spots, and establishing a characteristic database corresponding to the diseases; on the basis, selecting proper disease spot characteristic parameters and an effective pattern recognition algorithm so as to establish a machine vision-based rice disease, pest and weed real-time diagnostic model.

The invention discloses a hyperspectral plant leaf disease and insect pest diagnosis system belonging to the field of agriculture. A hyperspectral imager and a line light source are together fixedly connected with an electric control displacement platform, and move together by control of a displacement platform control device; in the process of moving, the line light source irradiates a calibration board and a to-be-measured plant leaf, the hyperspectral imager collects data and uploads to a computer in real time; through image analysis and processing by processing software, the data is inputted into a disease and insect pest triple diagnosis model, the plant disease and insect pest infection degree can be quantitatively obtained in real time, according to the analysis, decision on whether a to-be-measured plant needs to be sprayed with a pesticide can be made, and decision on pesticide dose and type and spray head form can be made. The hyperspectral plant leaf disease and insect pest diagnosis system is mainly used for the fast nondestructive diagnosis of plant diseases and insect pest infection degree, and can play a positive role to improve the decision-making level of precision pesticide application and implement precision agriculture.

The invention discloses a leaf disease identification method based on a machine learning algorithm, belonging to the technical field of image processing. The invention firstly performs preprocessing operations such as grayscale transformation, image enhancement and denoising on the collected leaf sample image; Then the preprocessed image is segmented by adaptive threshold algorithm to represent the texture information of the sample image effectively. The RGB color space is selected to extract the color features of the sample image, and the texture features of the segmented image are extractedaccording to the gray level co-occurrence matrix. Finally, support vector machine model is selected to classify and recognize the sample images by cross-validation algorithm. Firstly, the main parameters of SVM model are optimized by grid optimization method, and then the parameters with the best recognition accuracy are selected to establish SVM classification and recognition model. The inventioncan enable the computer to automatically identify the diseases and pests of the leaves through training, greatly reducing the space and time overhead, and improving the identification accuracy, and has the characteristics of fast, accurate and strong robustness.

The invention discloses a leaf disease spot identification method and a leaf disease spot identification device. The leaf disease spot identification method comprises the following steps of: acquiring an image which contains leaf disease spot information under a complex background; analyzing the color characteristic of the overall image and simplifying the background; extracting the intramembranous areas of a plurality of disease spot areas and a background area in a certain color channel component, extracting the grain characteristics of each intramembranous area, and forming candidate characteristic vectors by using the extracted grain characteristics and color characteristic components in different areas together; optimizing the weight values of the candidate characteristic vectors; selecting the characteristic dimensions of the optimized characteristic vectors; and clustering optimized characteristic spaces. The leaf disease spot identification device comprises an image acquisition unit, an image processing and identification unit and a display unit. By the leaf disease spot identification method and the leaf disease spot identification device, parts outside disease spots in the image can be more precisely removed, and an optimal identification effect can be achieved.

The invention discloses bacillus subtilis, a biological prevention and control preparation thereof and an application of the biological prevention and control preparation, and belongs to the field of biological plant disease and pest prevention and control. The stain is bacillus subtilis XLBS-01, and has the preservation number of CGMCC No. 6692. Tests show that the bacillus subtilis disclosed by the invention has the characteristics of high growing speed, large sporulation quantity, wide action spectrum, strong stress resistance, capability of realizing rapid and large-quantity colonization at plant roots, and the like, and therefore, the bacillus subtilis has good application prospects. The biological prevention and control preparation prepared from the bacillus subtilis can not only effectively prevent and control plant soil-borne diseases, but also can effectively increase the crop output, thereby being a biological prevention and control preparation with vast application prospects. The microbial preparation can be used as a biopesticide or a biofertilizer for preventing and controlling various soil-borne plant diseases and also preventing and controlling plant leaf diseases, such as hot pepper anthracnose, cucumber target spot, grape downy mildew, rose powdery mildew and the like.

The invention discloses a cutting propagation method of eustoma grandiflorum. The cutting propagation method includes: day temperature of a female parent cultivation greenhouse is kept at 20-30 DEG C, night temperature is kept at 13-18 DEG C, relative air humidity during the day is kept to be 50-75%, and relative air humidity during the night is kept to be 70-85%; and sunshine time in a year is less than 13 hours. When a lateral bud of a female parent plant has eight leaves and one heart, a bigslip is cut out, cutting is performed on the bigslip after the bigslip is dipped in rooting powder, shading coefficient of an outer shading net of a cutting greenhouse is 30%, inner relative air humidity is kept to be 80-95% through high pressure mist, temperature is at 20-25 DEG C, CO2 concentration in the cutting greenhouse is kept to be 600-800ppm through CO2 fertilization, and a cutting seedling is transplanted to a flower cutting production greenhouse after the cutting seedling takes root. The cutting propagation method of eustoma grandiflorum reduces root disease rate and leaf disease rate substantially, shortens seed breeding stage, and promotes the eustoma grandiflorum pigslip to take root. Rooting time of eustoma grandiflorum is 23-25 days, rooting rate of eustoma grandiflorum is above 92%, and planting percent of eustoma grandiflorum is above 87%. The cutting propagation method of eustoma grandiflorum is suitable for commercial and large-scale propagation of eustoma grandiflorum.

The invention relates to an anniversary application method of leaf fertilizer for red fuji apples. The method comprises the following steps of: applying nitrogenous fertilizer, phosphatic fertilizer and potassic fertilizer according to the growth characteristic and the nutrient requirement of the red fuji apples at the seven key growth and development stages, i.e., before germination, after germination, at the blooming period, at the vigorous young sprout growth period, at the fruit expansion period, at the later period of fruit development and before defoliation; and meanwhile, replenishing trace elements such as calcium, ferrum, zinc, boron and the like in good time. The anniversary application method can be used for effectively increasing the fruit setting rate of applies, preventing and controlling the little leaf disease, the yellowtop, the fruit shrink disease and the bitter pits, improving the fruit quality and increasing the fruit yield. If the anniversary application method is used for apple production, the growth vigour of a tree body is remarkably enhanced, the occurrence rate of various physiologic diseases is remarkably reduced, the high-quality fruit rate is increased by 23%, and guarantee is provided for the increment of fruit growers and the sustainable development of fruit industry.

The present invention discloses a crop leaf disease identification method based on a deep convolutional neural network, belonging to the field of image processing and machine learning technology. Themethod comprises the steps of: performing extension of an original image database to obtain an extended image database; constructing a deep convolutional neural network, and employing the extended image database to perform training of the deep convolutional neural network to obtain a crop disease identification model; inputting leaf images of crops to be identified into the crop disease identification model to obtain feature vectors, and performing image classification of the feature vectors; and obtaining types of diseases of the crops to be identified according to category labels of the crops to be identified and an image classification result. The method provided by the invention can improve the accuracy rate of the crop disease identification model, and can improve the applicability ofthe crop disease identification model.

The invention discloses a plant leaf pest identification method based on an improved convolutional neural network. According to the method, an improved AlexNet network model is provided, a convolutional neural network model combining batch normalization and global pooling is adopted to recognize various leaf diseases and insect pests, the improved model is greatly optimized in training time and memory requirements, model parameters are simplified, and meanwhile, the generalization ability of the model is also improved; according to the invention, the trained improved AlexNet feature network isused as a plant disease and insect pest identification model, so that the accuracy of plant leaf disease and insect pest identification is improved, the robustness is better, different diseases and insect pests of various plant leaves can be identified, and resources and time required by model training are reduced.

The invention discloses a strain of bacillus simplex and application thereof. The bacterial strain is bacillus simplex STY005, and the preservation number is CGMCC No.11052. The invention also discloses a biological control preparation containing the bacterial strain and a preparation method thereof. Experiment results show that the bacillus simplex strain STY005 provided by the invention has the characteristics of being long in diameter, hypoxia resistant, wide in action spectrum, high in adaptability, capable of quickly growing and breeding under low nutrition, and the like, thereby having a good application prospect; the biological control preparation prepared from the bacterial strain can not only effectively prevent and treat plant diseases, but also effectively increase crop yield, is a biological control preparation with a wide application prospect, and can be used as a biopesticide or a bio-fertilizer for preventing and treating crop leaf diseases containing one or more of the diseases like potato common scab, grape downy mildew, Chinese rose powdery mildew, and cucumber target leaf spot.

The invention discloses a plant leaf disease identification method based on a mask convolutional neural network, and mainly solves the problem of low plant leaf disease identification accuracy in theprior art. According to the scheme, an original data set is enhanced and expanded to obtain a training set and a test set; performing semantic segmentation on the training set and the test set to obtain corresponding mask sets; adding a disease feature screening module between a full convolution layer and a mask branch of the model, and inputting the training set and the mask set into a network for training to obtain a target classification and target detection result; taking the feature map belonging to the diseased leaf in the target classification result as the input of a mask branch, and obtaining a trained model after multiple iterations; and inputting the test set into the model, carrying out target classification and target detection on the leaves, and segmenting the leaves belonging to the disease category. According to the method, the leaf disease identification accuracy is improved on the basis of a traditional method, and the method can be used for plant disease leaf identification and segmentation in agricultural planting.

The invention relates to a plant disease detection method based on a residual network, and the method comprises the following steps: building a plant disease detection data set which adopts a brand new leaf disease image data set of AI Challenger; carrying out statistical analysis on the categories and the number of the data sets, separating each type of images from the complete data set, storingthe images in corresponding category folders, and then carrying out image preprocessing; performing enhancement processing on the image by using random angle rotation, random horizontal mirror rotation, random vertical mirror rotation and random affine transformation methods; setting hyper-parameters of deep convolutional neural network training; using pyTorch as a deep learning framework, using aresidual network as a deep learning model, and training the residual network deep learning model to obtain a plant disease detection result. The residual error network ResNet is used for training thedeep convolutional neural network, 27 diseases of up to 10 crops can be accurately identified, the speed is high, the precision is high, and the method has important significance for agricultural production.

The invention discloses a method for identifying plant leaf diseases by using GPCNNs and ELMs, which comprises the following three stages of learning multi-scale pyramid convergent features by using GPCNN, fusing extracted hierarchical features, and performing disease identification and classification. The method has the characteristics that (1) a global convergence layer is adopted to replace a full-connection layer, so that the network convergence speed is increased, and the network performance is improved; (2) compared with a traditional disease recognition method based on feature extraction, the method has the advantages that GPCNNs are utilized to automatically learn reliable features from the diseased leaf images, manual diseased leaf feature extraction is replaced, and reliability and efficiency are improved; and (3) compared with a traditional crop disease identification method based on deep learning, an ELM classifier is used for replacing a convolutional neural network (CNNs)to classify disease types, so that the identification performance is improved.

The invention provides a deconvolution-guided semi-supervised plant leaf disease identification and segmentation method, which uses a small amount of disease category labels and disease spot pixel-level labels to achieve disease category identification and disease spot region segmentation through deconvolution. According to the method, a category prediction label of an unmarked sample is generatedthrough a consistency regularization and entropy minimization method; image mixing is carried out on the marked sample and the unmarked sample, and semi-supervised disease classification is carried out by utilizing the newly generated image; and up-sampling is performed on the category information, and semi-supervised scab segmentation is performed by using a small number of pixel-level marks. Inthe process of model training, model parameters are updated by using exponential weighted average, so that the model is more robust in test data. The method is suitable for identifying and segmentingplant leaf diseases with insufficient label samples, integration of identification and segmentation is achieved, the model has high generalization capacity in leaf images with insufficient light andforeign matter shielding, and the identification and segmentation speed can meet the real-time requirement.

The invention discloses preparation and application for growth-promoting trichoderma and bacillus composite wettable powder. The preparation adopts a trichoderma asperegillum GDSF1009 strain and bacillus amyloliquefaciens ACCC11060 as fermentation strains of a composite preparation, and the trichoderma asperegillum GDSF1009 strain and the bacillus amyloliquefaciens ACCC11060 are respectively usedto prepare mother powder of the trichoderma asperegillum and mother powder of the bacillus amyloliquefaciens; and salt auxiliary agents such as magnesium sulfate, borax, potassium dihydrogen phosphateand potassium humate are added, mixing is performed, and therefore the final product is prepared. The composite wettable powder disclosed by the invention can be used for soaking seeds, mixing soil,irrigating roots and performing foliar spraying, and can improve a germination rate and a seedling emergence rate of the seeds; the composite wettable powder can promote seedling growth, and increasea seedling fresh weight; the composite wettable powder can increase yield and quality of melons, fruits and vegetables; and the composite wettable powder can effectively prevent and control leaf diseases such as cucumber anthracnose and gray mold and other soil-borne diseases such as rice sheath blight and corn stalk rot.

The invention discloses a special anti-cracking foliar fertilizer for a jujube tree, and a preparation method and an application thereof. The special anti-cracking foliar fertilizer for the jujube tree is composed of the following components in percentages by mass: 5% to 8% of potassium chloride, 7% to 15% of calcium chloride, 1% to 5% of borax, 1% to 5% of chelated magnesium, 1% to 3% of chelatediron, 0.5% to 1.5% of zinc sulfate, 0.2% to 0.6% of manganese sulfate and 3% to 4% of organosilicon, with the balance being water. The foliar fertilizer provided by the invention has low production cost, is safe and effective, and is beneficial for and harmless to human and livestock; mineral elements added in the foliar fertilizer are needed by animals, and can effectively prevent a variety of diseases like yellow-leaf disease and little-leaf disease caused by nutrient deficiency of a fruit tree; the disease resistance of a tree body is strengthened; the quality of a fruit is improved; the soluble sugar content of a fruit is improved by 14.3% to 43.5%, the weight of a single fruit is increased by 5% to 13.3%; the proportion of high-quality fruits is increased by 20.2% to 69.8%; the proportion of low-quality fruits is decreased by 28.9% to 76.9%; the fruit cracking rate of golden-silk jujube is significantly decreased by 30% to 45%; meanwhile, the contents of mineral elements in fruits and leaves are significantly improved; and the foliar fertilizer is free of any side effects, is safe and reliable, and is a green and environment-friendly product.

The invention provides a disease spot image segmentation method and system for a greenhouse vegetable leaf. The method comprises: vegetable leaf disease-spot images collected at a greenhouse field are divided into a training set and a testing set and enhancement processing is carried out on the images; initial color classification features and gradient features of the training set images after enhancement processing are extracted; the training set images after enhancement processing are classified into disease spot samples and leaf samples, and initial color classification feature data and gradient feature data of the disease spot samples and the leaf samples are obtained based on the extracted initial color classification features and gradient features; with a rough set method, color classification features are selected for the initial color classification feature data of the disease spot samples and leaf samples, thereby obtaining a color feature set; according to the color feature set and the gradient feature data of the disease spot samples and leaf samples, a condition random field model is constructed; and on the basis of the condition random field model, the testing set images after enhancement processing are segmented and disease-spot images are extracted. According to the invention, a disease-spot image can be extracted accurately and the speed is fast.

The invention relates to a heterocycle substituted 1,3,4-oxadiazole compound and a preparation method and application thereof. The compound includes the following steps shown in the general formula (I) in the description. The compound has a good inhibitory effect on pathogenic bacteria and fungi, such as rice white leaf diseases, citrus canker diseases, pepper wilt pathogenic bacteria, blueberry phytophthora lateralis, wheat gibberella saubinetii, potato phytophthora infestans, oilseed rape sclerotinia sclerotiorum, dragon-fruit colletotrichum orbiculare and the like.

The invention provides a method for realizing plant leaf scab segmentation and identification by using a multi-scale deconvolution network, which realizes end-to-end plant leaf scab segmentation and identification by using a small amount of pixel-level marks. The method comprises the following steps: firstly, constructing a multi-scale feature extraction module by utilizing a multi-scale residualblock, and extracting multi-scale disease features; then, introducing a classification and bridging module to obtain an activation graph of a specific class, wherein the activation graph comprises keyinformation of disease spots of the specific class, and conducting up-sampling on the activation graph, so segmentation of the disease spots is achieved; and finally, designing a deconvolution module, extracting a real position of a network concerned disease spot by combining a small amount of disease spot annotation guide features, and further optimizing an identification and segmentation effect. The method provided by the invention can be suitable for identifying and segmenting plant leaf diseases with insufficient pixel-level labeling samples, and realizes the integration of identificationand segmentation. The model has high robustness in disease images with insufficient light and noise interference.

The invention discloses a preparation method of pyraclostrobin microcapsules and belongs to the technical field of agricultural pesticides. The preparation method comprises the following steps: dissolving a crude drug at first, and then mixing the dissolved crude drug with isocyanate and polyethylene glycol; then dispersing the mixture in a water phase containing a surfactant and a colloid protecting agent, solidifying into capsules, and adjusting the pH value to obtain a microcapsule suspension; and on the basis of the suspension, adding a suspensions stabilizer to prepare a microcapsule suspension agent, or adding a solid auxiliary material to prepare microcapsule water dispersion granules. Diphenyl methane diisocyanate is particularly used as a material for preparing polyurethane capsule walls in the preparation method disclosed by the invention. The toxicity of the pyraclostrobin microcapsules prepared by the method disclosed by the invention to plant algae, daphnia magna and zebra fishes is obviously lower than that of pyraclostrobin missible oil, and the microcapsules can be used for preventing and treating plant leaf diseases of downy mildew, powdery mildew, late blight and the like of vegetables and can also be used for preventing and treating plant soil borne diseases of root rot, crown rot, southern blight and the like.

The invention relates to bacillus amyloliquefacien FS6 and application thereof. The preservation number of the bacillus amyloliquefacien FS6 is CGMCC No. 9538. The invention also provides a preparation method of the bacillus amyloliquefacien FS6 inoculant. The bacillus amyloliquefacien FS6 disclosed by the invention and an inoculant thereof have higher bacteriostatic activity on pathogenic bacteria in ginseng roots and leaves, and can induce the activity of ginseng peroxidase, polyphenol oxidase, phenylalnine ammonialyase and other enzymes relating to defense to rise so as to improve the resistance of ginseng to pathogenic bacteria. The bacillus amyloliquefacien FS6 and the inoculant thereof can be stably colonized in ginseng plants and soil, so that a protective film is formed on the surface of an object to be applied to prevent pathogenic bacteria from invasion, and the occurrence of ginseng roots and leaf diseases is effectively reduced. The bacillus amyloliquefacien FS6 has no phytotoxicity on ginseng and no environment pollution, and has a good biopesticide development potential and an application prospect.

The invention relates to an internet of things field crop leaf disease detection method based on the whole convolution network, which utilizes the internet of things to collect a plurality of images of the diseased leaves, labels the images, and then normalizes the scale of each image sample of the diseased leaves. The training set is expanded to 20 images by four preprocessing operations: translation, rotation, scaling and color shaking. All samples in the training sample set are averaged, and then each training sample in the training sample set is subtracted from the averaged value, and thenscrambled to form the averaged training set. The FCN is constructed by training the FCN with the samples from the training set after averaging. In the test, the full-size leaf image is used as the input to detect the disease on the FCN after training. The invention can learn the multi-level features from low to high, quickly realizes the disease detection with high precision, and is especially suitable for the leaf disease detection of crops based on the video leaf image of the Internet of Things.

The invention belongs to the field of plant specimen preparation, and particularly relates to a method for preparing cured specimens of a citrus leaf disease. The preparation method provided by the invention comprises the following steps: collecting specimens; adding solid copper oxide to 50% glacial acetic acid solution to obtain a copper acetate saturated solution, and diluting the solution withsterile water for 1 to 2.5 times to obtain a color retention liquid; adding the color retention liquid into the collected specimens after being heated for color retention treatment, and taking out the specimens after the leaves are changed from green to yellow-green or brown and to green again; evenly coating colorless nail polish on the surfaces of the specimens after the specimens through the color retention are pressed and dried, placing the specimens in a neat by resins after drying for embossing, and obtaining cured specimens of the citrus leaf disease after drying. The cured specimen ofthe citrus leaf disease prepared by the preparation method provided by the invention can be preserved for a long time, and can completely and truly reflect the characteristics of the citrus leaf disease, which is convenient for repeated use and observation, and has important significance in teaching and research.

The invention provides a maize leaf disease identification method, in particular to a maize leaf disease identification method based on a convolutional neural network model GoogleNet. The invention aims at solving the defects that the existing maize leaf disease identification technology is more in network model parameters and low in disease type identification accuracy. The maize leaf disease identification method comprises the following steps: 1, collecting a maize leaf image data set, expanding the collected maize leaf image data set, and then pre-processing image data set, wherein the pre-processed image data set is divided into a training set and a test set; 2, inputting the training set and the test set into the convolutional neural network model GoogleNet, and training and testing by using a first classifier so as to obtain an optimized convolutional neural network model GoogleNet; 3, inputting the test set into the optimized convolutional neural network model GoogleNet so as tocomplete the identification of types of maize leaf diseases. The maize leaf disease identification method is applied to the technical field of image identification.

The invention discloses a hyperspectral citrus leaf disease identification method based on a characteristic wavelength. According to the method, the characteristic wavelength is selected based on waveband operation by utilizing a hyperspectral technology to realize the discrimination and detection of various diseases of citrus leaves. By establishing a disease type discrimination model, a detection result of a disease type can be obtained only by acquiring a hyperspectral image of a to-be-detected sample for preprocessing and extracting a reflectivity data model under the corresponding characteristic wavelength, and the nondestructive, rapid and accurate identification of the citrus leaf disease type can be realized. The characteristic wavelength is selected by using the correlation coefficient of a waveband operation result and a mark value, the calculation is simple, and the judgment effect of the selected characteristic wavelength is good. After hyperspectral data of the to-be-detected sample is preprocessed, the spectral value of each pixel is substituted into the model, and the disease type and distribution can be visually displayed through colors, and the method is more intuitive.

The invention relates to a foliar top-dress fertilizer used for improving pear tree fruit setting rate. The fertilizer comprises potassium dihydrogen phosphate, borax, copper sulfate, quicklime, zinc sulfate, ferrous sulfate, urea, sucrose and ammonium molybdate. With the fertilizer provided by the invention, the properties of components are stable, and pear leaves are not damaged. With the cooperation of copper sulfate and quicklime, a sterilization effect is provided. Potassium dihydrogen phosphate, urea and ammonium molybdate can supplement nitrogen, phosphorus and potassium needed by pear trees. With borax, pear tree fruit shrink disease rate can be substantially reduced. Zinc sulfate has good treatment effect against pear tree leaf spot and little-leaf diseases. Ferrous sulfate helps in correcting pear tree iron-deficiency chlorotic yellowing. With sucrose, pear sweetness can be enhanced. With the components, pear tree fruit setting rate can be improved comprehensively. Pear yield can be improved, and grower income can be improved.