Research on Identification Method of Apple Diseases in Southern Xinjiang Based on Deep Learning and Its System Implementation

Apple disease samples were collected from the southern Xinjiang and annotated to design a convolutional neural network model based on deep learning.The accuracy and robustness of the model was improved through training and optimization algorithms,and a complete apple disease identification system was developed with the model as the core,and evaluated for its performance in terms of accuracy,recall rate and speed.This study provides a reliable AI-based apple disease diagnosis solution for the apple planting industry in the southern Xinjiang,hoping to help farmers better manage and protect crop health.

Biochar alleviates apple replant disease by reducing the growth of Fusarium oxysporum and regulating microbial communities

Apple replant disease(ARD)negatively affects plant growth and reduces yields in replanted orchards.In this study,biochar was applied to apple replant soil with Fusarium oxysporum.Our aim was to investigate whether biochar could promote plant growth and alleviate apple replant disease by reducing the growth of harmful soil microorganisms,changing soil microbial community structure and improving the soil environment.This experiment included five treatments:apple replant soil(CK),methyl bromide fumigation apple replant soil(FM),replant soil with biochar addition(2%),replant soil with F.oxysporum spore solution(8×10^(7)spores·mL^(-1)),and replant soil with biochar and F.oxysporum spore solution addition.Seedling biomass,the activity of antioxidant enzymes in the leaves and roots,and soil environmental variables were measured.Microbial community composition and community structure were analyzed using 16SrDNA and ITS2 gene sequencing.Biochar significantly reduced the abundance of F.oxysporum and increased soil microbial diversity and richness.Biochar also increased the soil enzyme activities(urease,invertase,neutral phosphatase,and catalase),the biomass(plant height,fresh weight,dry weight)and the activity of antioxidant enzymes(superoxide dismutase,peroxidase,and catalase).The root indexes of apple seedlings was also increased in replant soil by biochar.In sum,biochar promoted the growth of plants,improved the replant soil environment,and alleviated apple replant disease.

Improved multi-scale inverse bottleneck residual network based on triplet parallel attention for apple leaf disease identification

Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small computational costs while the dimensional dependencies are improved. To verify the validity of the model in this paper, we uniformly enhance apple leaf disease images screened from the public data sets of Plant Village, Baidu Flying Paddle, and the Internet. The final processed image count is 14,000. The ablation study, pre-processing comparison, and method comparison are conducted on the processed datasets. The experimental results demonstrate that the proposed method reaches 98.73% accuracy on the adopted datasets, which is 1.82% higher than the classical ResNet-50 model, and 0.29% better than the apple leaf disease datasets before preprocessing. It also achieves competitive results in apple leaf disease identification compared to some state-ofthe-art methods.

Isolation of phloridzin-degrading,IAA-producing bacterium Ochrobactrum haematophilum and its effects on the apple replant soil environment

We isolated and identified a bacterium that could produce IAA and degrade phloridzin in the rhizosphere soil of healthy replanted apple(the rootstock is M9T337 and the scion is Yanfu 3),providing a theoretical basis for reducing the obstacles associated with apple replant disease(ARD).Isolates were screened using Salkowski colorimetry and screening medium for phloridzin.The isolate of interest(W6)was identified as Ochrobactrum haematophilum based on morphological analysis,physiological and biochemical tests,and 16S rDNA sequencing.In a laboratory experiment,W6 produced auxin and promoted the growth of Arabidopsis thaliana roots,and its degradation rate of 100 mg.L^(-1 )phloridzin was 62.0%.In a pot experiment,W6 significantly reduced the phenolic acid contents of replanted soil,lowered the abundance of the harmful fungus Fusarium solani,and increased soil enzyme activities,thereby improving the micro-ecological environment of replant soil.W6 increased the root antioxidant enzyme activity and leaf photosynthetic pigment content of replanted Malus hupehensis Rehd.seedlings,effectively alleviating the decrease in net photosynthetic rate,transpiration rate and stomatal conductance caused by ARD.In a field experiment,W6 also promoted the growth of replanted apple(the rootstock is M9T337 and the scion is Yanfu 3)saplings.Therefore,W6 can promote apple growth and degrade phenolic acids,and it can be used as an effective treatment for the reduction of ARD.

Effects of Soil Texture on the Growth of Young Apple Trees and Soil Microbial Community Structure Under Replanted Conditions

A two-year field experiment was carried out in order to study the occurrence degree and mechanism of apple replant disease(ARD)in the apple orchards with different soil textures.So we can adopt appropriate controlmeasures according to the severity of ARD.Healthy two-year-old seedlings with consistent growth were selected,of which the root stock was T337 and the scion was Yanfu 3.There were significant differences in biomass between methyl bromide fumigation and replanted treatments,and the difference was the largest in clay loam,followed by sandy loam,and loam,which verified ARD in clay loam was most serious,followed by sandy loam and loam.Based on high-throughput sequencing of fungi in soil samples,fungal richness and diversity were the highest in clay loam,followed by sandy loam,and loam.The relative abundance of Fusarium in SX,SL,FX,FL,WX and WL was 7.33%,19.32%,2.70%,4.24%,10.71%and 23.87%,respectively.Based on Real-time quantitative analysis,there were significant differences in the number of Fusarium oxysporum and Fusarium solani between methyl bromide fumigation and replanted treatments,i.e.,clay loam>sandy loam>loam.Fusarium was the main pathogen causing ARD.This shows that ARD is the most serious under replanted clay loam condition.High-throughput sequencing technology was used to prove the difference in Fusarium was one of the important reasons for ARD under different soil textures.This technology provides a new idea for the prevention and control of ARD.

Disease Recognition of Apple Leaf Using Lightweight Multi-Scale Network with ECANet

To solve the problem of difficulty in identifying apple diseases in the natural environment and the low application rate of deep learning recognition networks,a lightweight ResNet(LW-ResNet)model for apple disease recognition is proposed.Based on the deep residual network(ResNet18),the multi-scale feature extraction layer is constructed by group convolution to realize the compression model and improve the extraction ability of different sizes of lesion features.By improving the identity mapping structure to reduce information loss.By introducing the efficient channel attention module(ECANet)to suppress noise from a complex background.The experimental results show that the average precision,recall and F1-score of the LW-ResNet on the test set are 97.80%,97.92%and 97.85%,respectively.The parameter memory is 2.32 MB,which is 94%less than that of ResNet18.Compared with the classic lightweight networks SqueezeNet and MobileNetV2,LW-ResNet has obvious advantages in recognition performance,speed,parameter memory requirement and time complexity.The proposed model has the advantages of low computational cost,low storage cost,strong real-time performance,high identification accuracy,and strong practicability,which can meet the needs of real-time identification task of apple leaf disease on resource-constrained devices.

The effects of crop rotation combinations on the soil quality of old apple orchard

This study investigated the effects of six crop rotation combinations on the soil quality of old apple orchard and seedling growth of Malus hupehensis Rehd.(apple rootstock) under pot conditions. The inhibitory effects of crops such as Allium fistulosum, Brassica juncea, and Triticum aestivum on four species of Fusarium were observed and compared in six treatments. These were continuous cropping(CK), fumigation with the methyl bromide(FM), rotating A. fistulosum only(R1), rotating A. fistulosum and T. aestivum(R2), rotating A. fistulosum, B. juncea, and T. aestivum(R3), and fallow(FC) in a year. The results showed that the biomass of Malus hupehensis Rehd. seedlings increased significantly. The root length increased and the root architecture was optimized. The respiration rate of the root system was increased by about 1 time after rotation. The treatments of R1, R2, R3, and FC increased bacterial count by 232.17%, 96.04%, 316.21%, and 60.02%, respectively. However, the fungi were reduced in varying degrees and bacteria/fungi ratio was increased by 5–10 times. The enzyme activities, p H, and organic matter were increased, but soil bulk density was decreased. Phenolic acids such as phloridzin was decreased significantly. The copy number of four Fusarium species declined by 85.59%, 74.94%, 69.68%, and 54.41% after rotating three different crops(R3 treatment). The root volatiles of three plants inhibited mycelial growth and spore germination of four Fusarium species.

Silencing of early auxin responsive genes MdGH3-2/12 reduces the resistance to Fusarium solani in apple

Apple replant disease(ARD)has led to severe yield and quality reduction in the apple industry.Fusarium solani(F.solani)has been identified as one of the main microbial pathogens responsible for ARD.Auxin(indole-3-acetic acid,IAA),an endogenous hormone in plants,is involved in almost all plant growth and development processes and plays a role in plant immunity against pathogens.Gretchen Hagen3(GH3)is one of the early/primary auxin response genes.The aim of this study was to evaluate the function of MdGH3-2 and MdGH3-12 in the defense response of F.solani by treating MdGH3-2/12 RNAi plants with F.solani.The results show that under F.solani infection,RNAi of MdGH3-2/12 inhibited plant biomass accumulation and exacerbated root damage.After inoculation with F.solani,MdGH3-2/12 RNAi inhibited the biosynthesis of acid-amido synthetase.This led to the inhibition of free IAA combining with amino acids,resulting in excessive free IAA accumulation.This excessive free IAA altered plant tissue structure,accelerated fungal hyphal invasion,reduced the activity of antioxidant enzymes(SOD,POD and CAT),increased the reactive oxygen species(ROS)level,and reduced total chlorophyll content and photosynthetic ability,while regulating the expression of PR-related genes including PR1,PR4,PR5 and PR8.It also changed the contents of plant hormones and amino acids,and ultimately reduced the resistance to F.solani.In conclusion,these results demonstrate that MdGH3-2 and MdGH3-12 play an important role in apple tolerance to F.solani and ARD.

Apple leaf disease identification using genetic algorithm and correlation based feature selection method

Apple leaf disease is one of the main factors to constrain the apple production and quality.It takes a long time to detect the diseases by using the traditional diagnostic approach,thus farmers often miss the best time to prevent and treat the diseases.Apple leaf disease recognition based on leaf image is an essential research topic in the field of computer vision,where the key task is to find an effective way to represent the diseased leaf images.In this research,based on image processing techniques and pattern recognition methods,an apple leaf disease recognition method was proposed.A color transformation structure for the input RGB(Red,Green and Blue)image was designed firstly and then RGB model was converted to HSI(Hue,Saturation and Intensity),YUV and gray models.The background was removed based on a specific threshold value,and then the disease spot image was segmented with region growing algorithm(RGA).Thirty-eight classifying features of color,texture and shape were extracted from each spot image.To reduce the dimensionality of the feature space and improve the accuracy of the apple leaf disease identification,the most valuable features were selected by combining genetic algorithm(GA)and correlation based feature selection(CFS).Finally,the diseases were recognized by SVM classifier.In the proposed method,the selected feature subset was globally optimum.The experimental results of more than 90%correct identification rate on the apple diseased leaf image database which contains 90 disease images for there kinds of apple leaf diseases,powdery mildew,mosaic and rust,demonstrate that the proposed method is feasible and effective.