Investigation on Data Fusion of Multisource Spectral Data for Rice Leaf Diseases Identification Using Machine Learning Methods

YOLOv8-RMDA: Lightweight YOLOv8 Network for Early Detection of Small Target Diseases in Tea

In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development.

DC2Net: An Asian Soybean Rust Detection Model Based on Hyperspectral Imaging and Deep Learning

Asian soybean rust (ASR) is one of the major diseases that causes serious yield loss worldwide, even up to 80%. Early and accurate detection of ASR is critical to reduce economic losses. Hyperspectral imaging, combined with deep learning, has already been proved as a powerful tool to detect crop diseases. However, current deep learning models are limited to extract both spatial and spectral features in hyperspectral images due to the use of fixed geometric structure of the convolutional kernels, leading to the fact that the detection accuracy of current models remains further improvement. In this study, we proposed a deformable convolution and dilated convolution neural network (DC2Net) for the ASR detection. The deformable convolution module was used to extract the spatial features, while the dilated convolution module was applied to extract features from the spectral dimension. We also adopted the Shapley value and the channel attention methods to evaluate the importance of each wavelength during decision-making, thereby identifying the most contributing ones. The proposed DC2Net can realize early asymptomatic detection of ASR even when visual symptoms have not appeared. The results of the experiment showed that the detection performance of DC2Net dominated state-of-the-art methods, reaching an overall accuracy at 96.73%. Meanwhile, the experimental result suggested that the Shapley Additive exPlanations method was able to extract feature wavelengths correctly, thereby helping DC2Net achieve reasonable performance with less input data. The research result of this study could provide early warning of ASR outbreak in advance, even at the asymptomatic period.

Cloning of maize chitinase 1 gene and its expression in genetically transformed rice to confer resistance against rice blast caused by Pyricularia oryzae

Fungal pathogens are one of the major reasons for biotic stress on rice (Oryza sativa L.), causing severe productivity losses every year. Breeding for host resistance is a mainstay of rice disease management, but conventional development of commercial resistant varieties is often slow. In contrast, the development of disease resistance by targeted genome manipulation has the potential to deliver resistant varieties more rapidly. The present study reports the first cloning of a synthetic maize chitinase 1 gene and its insertion in rice cv. (Basmati 385) via Agrobacterium-mediated transformation to confer resistance to the rice blast pathogen, Pyricularia oryzae. Several factors for transformation were optimized; we found that 4-week-old calli and an infection time of 15 minutes with Agrobacterium before colonization on co-cultivation media were the best-suited conditions. Moreover, 300 μM of acetosyringone in co-cultivation media for two days was exceptional in achieving the highest callus transformation frequency. Transgenic lines were analyzed using molecular and functional techniques. Successful integration of the gene into rice lines was confirmed by polymerase chain reaction with primer sets specific to chitinase and hpt genes. Furthermore, real-time PCR analysis of transformants indicated a strong association between transgene expression and elevated levels of resistance to rice blast. Functional validation of the integrated gene was performed by a detached leaf bioassay, which validated the efficacy of chitinase-mediated resistance in all transgenic Basmati 385 plants with variable levels of enhanced resistance against the P. oryzae. We concluded that overexpression of the maize chitinase 1 gene in Basmati 385 improved resistance against the pathogen. These findings will add new options to resistant germplasm resources for disease resistance breeding. The maize chitinase 1 gene demonstrated potential for genetic improvement of rice varieties against biotic stresses in future transformation programs.

Design and Development of Large-Band Dual-MSFA Sensor Camera for Precision Agriculture

The optimal design and construction of multispectral cameras can remarkably reduce the costs of spectral imaging systems and efficiently decrease the amount of image processing and analysis required. Also, multispectral imaging provides effective imaging information through higher-resolution images. This study aimed to develop novel, multispectral cameras based on Fabry-Pérot technology for agricultural applications such as plant/weed separation, ripeness estimation, and disease detection. Two multispectral cameras were developed, covering visible and near-infrared ranges from 380 nm to 950 nm. A monochrome image sensor with a resolution of 1600 × 1200 pixels was used, and two multispectral filter arrays were developed and mounted on the sensors. The filter pitch was 4.5 μm, and each multispectral filter array consisted of eight bands. Band selection was performed using a genetic algorithm. For VIS and NIR filters, maximum RMS values of 0.0740 and 0.0986 were obtained, respectively. The spectral response of the filters in VIS was significant; however, in NIR, the spectral response of the filters after 830 nm decreased by half. In total, these cameras provided 16 spectral images in high resolution for agricultural purposes.

Characterization of Rice-Magnaporthe oryzae Interactions by Hyperspectral Imaging

Hyperspectral imaging has the potential to detect, characterize, and quantify plant diseases objectively and nondestructively to improve phenotyping in breeding for disease resistance. In this study, leaf spectral reflectance characteristics of five rice genotypes diseased with blast caused by three Magnaporthe oryzae isolates differing in virulence were compared with visual disease ratings under greenhouse conditions. Spectral information (140 wavebands, range 450 to 850 nm) of infected leaves was recorded with a hyperspectral imaging microscope at 3, 5, and 7 days postinoculation to examine differences in symptom phenotypes and to characterize the compatibility of host-pathogen interactions. Depending on the rice genotype × M. oryzae genotype interaction, blast symptoms varied from tiny necrosis to enlarged lesions with symptom subareas differing in tissue coloration and indicated gene-for-gene-specific interactions. The blast symptom types were differentiated based on their spectral characteristics in the visible/near-infrared range. Symptom-specific spectral signatures and differences in the composition of leaf blast symptom type(s) resulted in unique spectral and spatial patterns of the rice × M. oryzae interactions based on the size, shape, and color of the symptom subareas. Spectral angle mapper classification of spectra enabled (i) discrimination between healthy (green) and diseased tissue of rice genotypes, (ii) classification and quantification of different blast symptom subareas, and (iii) grading of the host-pathogen compatibility (low - intermediate - high). Hyperspectral imaging was more sensitive to small changes in disease resistance than visual disease assessments and enabled the characterization of various types of resistance/susceptibility reactions of tissue subjected to M. oryzae infection.

Soil carbon content prediction using multi-source data feature fusion of deep learning based on spectral and hyperspectral images

Visible near-infrared reflectance spectroscopy (VNIR) and hyperspectral images (HSI) have their respective advantages in soil carbon content prediction, and the effective fusion of VNIR and HSI is of great significance for improving the prediction accuracy. But the contribution difference analysis of multiple features in the multi-source data is inadequate, and there is a lack of in-depth research on the contribution difference analysis of artificial feature and deep learning feature. In order to solve the problem, soil carbon content prediction methods based on VNIR and HSI multi-source data feature fusion are proposed. The multi-source data fusion network under the attention mechanism and the multi-source data fusion network with artificial feature are designed. For the multi-source data fusion network based on the attention mechanism, the information are fused through the attention mechanism according to the contribution difference of each feature. For the other network, artificial feature are introduced to fuse multi-source data. The results show that multi-source data fusion network based on the attention mechanism can improve the prediction accuracy of soil carbon content, and multi-source data fusion network combined with artificial feature has better prediction effect. Compared with two single-source data from the VNIR and HSI, the relative percent deviation of Neilu, Aoshan Bay and Jiaozhou Bay based on multi-source data fusion network combined with artificial feature are increased by 56.81% and 149.18%, 24.28% and 43.96%, 31.16% and 28.73% respectively. This study can effectively solve the problem of the deep fusion of multiple features in the soil carbon content prediction by VNIR and HSI, so as to improve the accuracy and stability of soil carbon content prediction, promote the application and development of soil carbon content prediction in spectral and hyperspectral image, and provide technical support for the study of carbon cycle and the carbon sink.

Diagnosis and application of rice diseases based on deep learning

Background

Rice disease can significantly reduce yields, so monitoring and identifying the diseases during the growing season is crucial. Some current studies are based on images with simple backgrounds, while realistic scene settings are full of background noise, making this task challenging. Traditional artificial prevention and control methods not only have heavy workload, low efficiency, but are also haphazard, unable to achieve real-time monitoring, which seriously limits the development of modern agriculture. Therefore, using target detection algorithm to identify rice diseases is an important research direction in the agricultural field.

Methods

In this article a total of 7,220 pictures of rice diseases taken in Jinzhai County, Lu'an City, Anhui Province were chosen as the research object, including rice leaf blast, bacterial blight and flax leaf spot. We propose a rice disease identification method based on the improved YOLOV5s, which reduces the computation of the backbone network, reduces the weight file of the model to 3.2MB, which is about 1/4 of the original model, and accelerates the prediction speed by three times.

Results

Compared with other mainstream methods, our method achieves better performance with low computational cost. It solves the problem of slow recognition speed due to the large weight file and calculation amount of model when the model is deployed in mobile terminal.

Discrimination of Deoxynivalenol Levels of Barley Kernels Using Hyperspectral Imaging in Tandem with Optimized Convolutional Neural Network

Deoxynivalenol (DON) in raw and processed grain poses significant risks to human and animal health. In this study, the feasibility of classifying DON levels in different genetic lines of barley kernels was evaluated using hyperspectral imaging (HSI) (382-1030 nm) in tandem with an optimized convolutional neural network (CNN). Machine learning methods including logistic regression, support vector machine, stochastic gradient descent, K nearest neighbors, random forest, and CNN were respectively used to develop the classification models. Spectral preprocessing methods including wavelet transform and max-min normalization helped to enhance the performance of different models. A simplified CNN model showed better performance than other machine learning models. Competitive adaptive reweighted sampling (CARS) in combination with successive projections algorithm (SPA) was applied to select the best set of characteristic wavelengths. Based on seven wavelengths selected, the optimized CARS-SPA-CNN model distinguished barley grains with low levels of DON (<5 mg/kg) from those with higher levels (5 mg/kg < DON ≤ 14 mg/kg) with an accuracy of 89.41%. The lower levels of DON class I (0.19 mg/kg ≤ DON ≤ 1.25 mg/kg) and class II (1.25 mg/kg < DON ≤ 5 mg/kg) were successfully distinguished based on the optimized CNN model, yielding a precision of 89.81%. The results suggest that HSI in tandem with CNN has great potential for discrimination of DON levels of barley kernels.

Spectral characterization and severity assessment of rice blast disease using univariate and multivariate models

Rice is the staple food of more than half of the population of the world and India as well. One of the major constraints in rice production is frequent occurrence of pests and diseases and one of them is rice blast which often causes yield loss varying from 10 to 30%. Conventional approaches for disease assessment are time-consuming, expensive, and not real-time; alternately, sensor-based approach is rapid, non-invasive and can be scaled up in large areas with minimum time and effort.  In the present study, hyperspectral remote sensing for the characterization and severity assessment of rice blast disease was exploited. Field experiments were conducted with 20 genotypes of rice having sensitive and resistant cultivars grown under upland and lowland conditions at Almora, Uttarakhand, India. The severity of the rice blast was graded from 0 to 9 in accordance to International Rice Research Institute (IRRI).  Spectral observations in field were taken using a hand-held portable spectroradiometer in range of 350-2500 nm followed by spectral discrimination of different disease severity levels using Jeffires-Matusita (J-M) distance. Then, evaluation of 26 existing spectral indices (r≥0.8) was done corresponding to blast severity levels and linear regression prediction models were also developed. Further, the proposed ratio blast index (RBI) and normalized difference blast index (NDBI) were developed using all possible combinations of their correlations with severity level followed by their quantification to identify the best indices. Thereafter, multivariate models like support vector machine regression (SVM), partial least squares (PLS), random forest (RF), and multivariate adaptive regression spline (MARS) were also used to estimate blast severity. Jeffires-Matusita distance was separating almost all severity levels having values >1.92 except levels 4 and 5. The 26 prediction models were effective at predicting blast severity with R² values from 0.48 to 0.85. The best developed spectral indices for rice blast were RBI (R1148, R1301) and NDBI (R1148, R1301) with R² of 0.85 and 0.86, respectively. Among multivariate models, SVM was the best model with calibration R²=0.99; validation R²=0.94, RMSE=0.7, and RPD=4.10. The methodology developed paves way for early detection and large-scale monitoring and mapping using satellite remote sensors at farmers' fields for developing better disease management options.

Dual-branch collaborative learning network for crop disease identification

Crop diseases seriously affect the quality, yield, and food security of crops. redBesides, traditional manual monitoring methods can no longer meet intelligent agriculture's efficiency and accuracy requirements. Recently, deep learning methods have been rapidly developed in computer vision. To cope with these issues, we propose a dual-branch collaborative learning network for crop disease identification, called DBCLNet. Concretely, we propose a dual-branch collaborative module using convolutional kernels of different scales to extract global and local features of images, which can effectively utilize both global and local features. Meanwhile, we embed a channel attention mechanism in each branch module to refine the global and local features. Whereafter, we cascade multiple dual-branch collaborative modules to design a feature cascade module, which further learns features at more abstract levels via the multi-layer cascade design strategy. Extensive experiments on the Plant Village dataset demonstrated the best classification performance of our DBCLNet method compared to the state-of-the-art methods for the identification of 38 categories of crop diseases. Besides, the Accuracy, Precision, Recall, and F-score of our DBCLNet for the identification of 38 categories of crop diseases are 99.89%, 99.97%, 99.67%, and 99.79%, respectively. 811.

Spectroscopic technologies and data fusion: Applications for the dairy industry

Increasing consumer awareness, scale of manufacture, and demand to ensure safety, quality and sustainability have accelerated the need for rapid, reliable, and accurate analytical techniques for food products. Spectroscopy, coupled with Artificial Intelligence-enabled sensors and chemometric techniques, has led to the fusion of data sources for dairy analytical applications. This article provides an overview of the current spectroscopic technologies used in the dairy industry, with an introduction to data fusion and the associated methodologies used in spectroscopy-based data fusion. The relevance of data fusion in the dairy industry is considered, focusing on its potential to improve predictions for processing traits by chemometric techniques, such as principal component analysis (PCA), partial least squares regression (PLS), and other machine learning algorithms.

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

In this study, eight different painted stainless steel 304L specimens were laser-cleaned using different process parameters, such as laser power, scan speed, and the number of repetitions. Laser-induced breakdown spectroscopy (LIBS) was adopted as the monitoring tool for laser cleaning. Identification of LIBS spectra with similar chemical compositions is challenging. A convolutional neural network (CNN)-based deep learning method was developed for accurate and rapid analysis of LIBS spectra. By applying the LIBS-coupled CNN method, the classification CNN model accuracy of laser-cleaned specimens was 94.55%. Moreover, the LIBS spectrum analysis time was 0.09 s. The results verified the possibility of using the LIBS-coupled CNN method as an in-line tool for the laser cleaning process.

Maize disease detection based on spectral recovery from RGB images

Maize is susceptible to infect pest disease, and early disease detection is key to preventing the reduction of maize yields. The raw data used for plant disease detection are commonly RGB images and hyperspectral images (HSI). RGB images can be acquired rapidly and low-costly, but the detection accuracy is not satisfactory. On the contrary, using HSIs tends to obtain higher detection accuracy, but HSIs are difficult and high-cost to obtain in field. To overcome this contradiction, we have proposed the maize spectral recovery disease detection framework which includes two parts: the maize spectral recovery network based on the advanced hyperspectral recovery convolutional neural network (HSCNN+) and the maize disease detection network based on the convolutional neural network (CNN). Taking raw RGB data as input of the framework, the output reconstructed HSIs are used as input of disease detection network to achieve disease detection task. As a result, the detection accuracy obtained by using the low-cost raw RGB data almost as same as that obtained by using HSIs directly. The HSCNN+ is found to be fit to our spectral recovery model and the reconstruction fidelity was satisfactory. Experimental results demonstrate that the reconstructed HSIs efficiently improve detection accuracy compared with raw RGB image in tested scenarios, especially in complex environment scenario, for which the detection accuracy increases by 6.14%. The proposed framework has the advantages of fast, low cost and high detection precision. Moreover, the framework offers the possibility of real-time and precise field disease detection and can be applied in agricultural robots.

End-to-End Fusion of Hyperspectral and Chlorophyll Fluorescence Imaging to Identify Rice Stresses

Herbicides and heavy metals are hazardous substances of environmental pollution, resulting in plant stress and harming humans and animals. Identification of stress types can help trace stress sources, manage plant growth, and improve stress-resistant breeding. In this research, hyperspectral imaging (HSI) and chlorophyll fluorescence imaging (Chl-FI) were adopted to identify the rice plants under two types of herbicide stresses (butachlor (DCA) and quinclorac (ELK)) and two types of heavy metal stresses (cadmium (Cd) and copper (Cu)). Visible/near-infrared spectra of leaves (L-VIS/NIR) and stems (S-VIS/NIR) extracted from HSI and chlorophyll fluorescence kinetic curves of leaves (L-Chl-FKC) and stems (S-Chl-FKC) extracted from Chl-FI were fused to establish the models to detect the stress of the hazardous substances. Novel end-to-end deep fusion models were proposed for low-level, middle-level, and high-level information fusion to improve identification accuracy. Results showed that the high-level fusion-based convolutional neural network (CNN) models reached the highest detection accuracy (97.7%), outperforming the models using a single data source (<94.7%). Furthermore, the proposed end-to-end deep fusion models required a much simpler training procedure than the conventional two-stage deep learning fusion. This research provided an efficient alternative for plant stress phenotyping, including identifying plant stresses caused by hazardous substances of environmental pollution.

Challenges and Opportunities of Implementing Data Fusion in Process Analytical Technology—A Review

The release of the FDA’s guidance on Process Analytical Technology has motivated and supported the pharmaceutical industry to deliver consistent quality medicine by acquiring a deeper understanding of the product performance and process interplay. The technical opportunities to reach this high-level control have considerably evolved since 2004 due to the development of advanced analytical sensors and chemometric tools. However, their transfer to the highly regulated pharmaceutical sector has been limited. To this respect, data fusion strategies have been extensively applied in different sectors, such as food or chemical, to provide a more robust performance of the analytical platforms. This survey evaluates the challenges and opportunities of implementing data fusion within the PAT concept by identifying transfer opportunities from other sectors. Special attention is given to the data types available from pharmaceutical manufacturing and their compatibility with data fusion strategies. Furthermore, the integration into Pharma 4.0 is discussed.

Effects of Image Dataset Configuration on the Accuracy of Rice Disease Recognition Based on Convolution Neural Network

In recent years, the convolution neural network has been the most widely used deep learning algorithm in the field of plant disease diagnosis and has performed well in classification. However, in practice, there are still some specific issues that have not been paid adequate attention to. For instance, the same pathogen may cause similar or different symptoms when infecting plant leaves, while the same pathogen may cause similar or disparate symptoms on different parts of the plant. Therefore, questions come up naturally: should the images showing different symptoms of the same disease be in one class or two separate classes in the image database? Also, how will the different classification methods affect the results of image recognition? In this study, taking rice leaf blast and neck blast caused by Magnaporthe oryzae, and rice sheath blight caused by Rhizoctonia solani as examples, three experiments were designed to explore how database configuration affects recognition accuracy in recognizing different symptoms of the same disease on the same plant part, similar symptoms of the same disease on different parts, and different symptoms on different parts. The results suggested that when the symptoms of the same disease were the same or similar, no matter whether they were on the same plant part or not, training combined classes of these images can get better performance than training them separately. When the difference between symptoms was obvious, the classification was relatively easy, and both separate training and combined training could achieve relatively high recognition accuracy. The results also, to a certain extent, indicated that the greater the number of images in the training data set, the higher the average classification accuracy.

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R 2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.

Rice bacterial blight resistant cultivar selection based on visible/near-infrared spectrum and deep learning

BACKGROUND

Rice bacterial blight (BB) has caused serious damage in rice yield and quality leading to huge economic loss and food safety problems. Breeding disease resistant cultivar becomes the eco-friendliest and most effective alternative to regulate its outburst, since the propagation of pathogenic bacteria is restrained. However, the BB resistance cultivar selection suffers tremendous labor cost, low efficiency, and subjective human error. And dynamic rice BB phenotyping study is absent from exploring the pattern of BB growth with different genotypes.

RESULTS

In this paper, with the aim of alleviating the labor burden of plant breeding experts in the resistant cultivar screening processing and exploring the disease resistance phenotyping variation pattern, visible/near-infrared (VIS-NIR) hyperspectral images of rice leaves from three varieties after inoculation were collected and sent into a self-built deep learning model LPnet for disease severity assessment. The growth status of BB lesion at the time scale was fully revealed. On the strength of the attention mechanism inside LPnet, the most informative spectral features related to lesion proportion were further extracted and combined into a novel and refined leaf spectral index. The effectiveness and feasibility of the proposed wavelength combination were verified by identifying the resistant cultivar, assessing the resistant ability, and spectral image visualization.

CONCLUSIONS

This study illustrated that informative VIS-NIR spectrums coupled with attention deep learning had great potential to not only directly assess disease severity but also excavate spectral characteristics for rapid screening disease resistant cultivars in high-throughput phenotyping.

Study on the Classification Method of Rice Leaf Blast Levels Based on Fusion Features and Adaptive-Weight Immune Particle Swarm Optimization Extreme Learning Machine Algorithm

Leaf blast is a disease of rice leaves caused by the Pyricularia oryzae. It is considered a significant disease is affecting rice yield and quality and causing economic losses to food worldwide. Early detection of rice leaf blast is essential for early intervention and limiting the spread of the disease. To quickly and non-destructively classify rice leaf blast levels for accurate leaf blast detection and timely control. This study used hyperspectral imaging technology to obtain hyperspectral image data of rice leaves. The descending dimension methods got rice leaf disease characteristics of different disease classes, and the disease characteristics obtained by screening were used as model inputs to construct a model for early detection of leaf blast disease. First, three methods, ElasticNet, principal component analysis loadings (PCA loadings), and successive projections algorithm (SPA), were used to select the wavelengths of spectral features associated with leaf blast, respectively. Next, the texture features of the images were extracted using a gray level co-occurrence matrix (GLCM), and the texture features with high correlation were screened by the Pearson correlation analysis. Finally, an adaptive-weight immune particle swarm optimization extreme learning machine (AIPSO-ELM) based disease level classification method is proposed to further improve the model classification accuracy. It was also compared and analyzed with a support vector machine (SVM) and extreme learning machine (ELM). The results show that the disease level classification model constructed using a combination of spectral characteristic wavelengths and texture features is significantly better than a single disease feature in terms of classification accuracy. Among them, the model built with ElasticNet + TFs has the highest classification accuracy, with OA and Kappa greater than 90 and 87%, respectively. Meanwhile, the AIPSO-ELM proposed in this study has higher classification accuracy for leaf blast level classification than SVM and ELM classification models. In particular, the AIPSO-ELM model constructed with ElasticNet+TFs as features obtained the best classification performance, with OA and Kappa of 97.62 and 96.82%, respectively. In summary, the combination of spectral characteristic wavelength and texture features can significantly improve disease classification accuracy. At the same time, the AIPSO-ELM classification model proposed in this study has sure accuracy and stability, which can provide a reference for rice leaf blast disease detection.

Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection

Various rice diseases threaten the growth of rice. It is of great importance to achieve the rapid and accurate detection of rice diseases for precise disease prevention and control. Hyperspectral imaging (HSI) was performed to detect rice leaf diseases in four different varieties of rice. Considering that it costs much time and energy to develop a classifier for each variety of rice, deep transfer learning was firstly introduced to rice disease detection across different rice varieties. Three deep transfer learning methods were adapted for 12 transfer tasks, namely, fine-tuning, deep CORrelation ALignment (CORAL), and deep domain confusion (DDC). A self-designed convolutional neural network (CNN) was set as the basic network of the deep transfer learning methods. Fine-tuning achieved the best transferable performance with an accuracy of over 88% for the test set of the target domain in the majority of transfer tasks. Deep CORAL obtained an accuracy of over 80% in four of all the transfer tasks, which was superior to that of DDC. A multi-task transfer strategy has been explored with good results, indicating the potential of both pair-wise, and multi-task transfers. A saliency map was used for the visualization of the key wavelength range captured by CNN with and without transfer learning. The results indicated that the wavelength range with and without transfer learning was overlapped to some extent. Overall, the results suggested that deep transfer learning methods could perform rice disease detection across different rice varieties. Hyperspectral imaging, in combination with the deep transfer learning method, is a promising possibility for the efficient and cost-saving field detection of rice diseases among different rice varieties.

Rice Leaf Blast Classification Method Based on Fused Features and One-Dimensional Deep Convolutional Neural Network

Rice leaf blast, which is seriously affecting the yield and quality of rice around the world, is a fungal disease that easily develops under high temperature and humidity conditions. Therefore, the use of accurate and non-destructive diagnostic methods is important for rice production management. Hyperspectral imaging technology is a type of crop disease identification method with great potential. However, a large amount of redundant information mixed in hyperspectral data makes it more difficult to establish an efficient disease classification model. At the same time, the difficulty and small scale of agricultural hyperspectral imaging data acquisition has resulted in unrepresentative features being acquired. Therefore, the focus of this study was to determine the best classification features and classification models for the five disease classes of leaf blast in order to improve the accuracy of grading the disease. First, the hyperspectral imaging data were pre-processed in order to extract rice leaf samples of five disease classes, and the number of samples was increased by data augmentation methods. Secondly, spectral feature wavelengths, vegetation indices and texture features were obtained based on the amplified sample data. Thirdly, seven one-dimensional deep convolutional neural networks (DCNN) models were constructed based on spectral feature wavelengths, vegetation indices, texture features and their fusion features. Finally, the model in this paper was compared and analyzed with the Inception V3, ZF-Net, TextCNN and bidirectional gated recurrent unit (BiGRU); support vector machine (SVM); and extreme learning machine (ELM) models in order to determine the best classification features and classification models for different disease classes of leaf blast. The results showed that the classification model constructed using fused features was significantly better than the model constructed with a single feature in terms of accuracy in grading the degree of leaf blast disease. The best performance was achieved with the combination of the successive projections algorithm (SPA) selected feature wavelengths and texture features (TFs). The modeling results also show that the DCNN model provides better classification capability for disease classification than the Inception V3, ZF-Net, TextCNN, BiGRU, SVM and ELM classification models. The SPA + TFs-DCNN achieved the best classification accuracy with an overall accuracy (OA) and Kappa of 98.58% and 98.22%, respectively. In terms of the classification of the specific different disease classes, the F1-scores for diseases of classes 0, 1 and 2 were all 100%, while the F1-scores for diseases of classes 4 and 5 were 96.48% and 96.68%, respectively. This study provides a new method for the identification and classification of rice leaf blast and a research basis for assessing the extent of the disease in the field.