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.

An online monitoring device for measuring the concentration of four types of in-situ microorganisms by using the near-infrared band.

Using optical density at 600 nm (OD600) to measure the microbial concentration is a popular approach due to its advantages like quick response and non-destructive. However, the OD600 measurement might be affected by the metabolic pigment, and it would become invalid when the solution dilution is insufficient. To overcome these issues, we proposed to adopt a more robust wavelength at 890 nm to quantify the attenuation of transmission light. After selecting this light source, we designed the light path and the circuit of the online monitoring device. Meanwhile, the random forest algorithm was introduced for temperature compensation and improving the stability of the device. This device was verified by monitoring the microbial concentration of four strains (Yeast, Bacillus, Arthrobacter, and Escherichia coli). The experimental result suggested that the mean absolute percentage error reached 4.11 %, 4.28 %, 4.49 %, and 4.53 % respectively, which is helpful to improve the accuracy of microbial concentration measurement.

A Novel Feature Selection Strategy Based on Salp Swarm Algorithm for Plant Disease Detection.

Deep learning has been widely used for plant disease recognition in smart agriculture and has proven to be a powerful tool for image classification and pattern recognition. However, it has limited interpretability for deep features. With the transfer of expert knowledge, handcrafted features provide a new way for personalized diagnosis of plant diseases. However, irrelevant and redundant features lead to high dimensionality. In this study, we proposed a swarm intelligence algorithm for feature selection [salp swarm algorithm for feature selection (SSAFS)] in image-based plant disease detection. SSAFS is employed to determine the ideal combination of handcrafted features to maximize classification success while minimizing the number of features. To verify the effectiveness of the developed SSAFS algorithm, we conducted experimental studies using SSAFS and 5 metaheuristic algorithms. Several evaluation metrics were used to evaluate and analyze the performance of these methods on 4 datasets from the UCI machine learning repository and 6 plant phenomics datasets from PlantVillage. Experimental results and statistical analyses validated the outstanding performance of SSAFS compared to existing state-of-the-art algorithms, confirming the superiority of SSAFS in exploring the feature space and identifying the most valuable features for diseased plant image classification. This computational tool will allow us to explore an optimal combination of handcrafted features to improve plant disease recognition accuracy and processing time.

Research of intelligent reasoning system of Arabidopsis thaliana phenotype based on automated multi-task machine learning.

Traditional machine learning in plant phenotyping research requires the assistance of professional data scientists and domain experts to adjust the structure and hy-perparameters tuning of neural network models with much human intervention, making the model training and deployment ineffective. In this paper, the automated machine learning method is researched to construct a multi-task learning model for Arabidopsis thaliana genotype classification, leaf number, and leaf area regression tasks. The experimental results show that the genotype classification task's accuracy and recall achieved 98.78%, precision reached 98.83%, and classification F 1 value reached 98.79%, as well as the R 2 of leaf number regression task and leaf area regression task reached 0.9925 and 0.9997 respectively. The experimental results demonstrated that the multi-task automated machine learning model can combine the benefits of multi-task learning and automated machine learning, which achieved more bias information from related tasks and improved the overall classification and prediction effect. Additionally, the model can be created automatically and has a high degree of generalization for better phenotype reasoning. In addition, the trained model and system can be deployed on cloud platforms for convenient application.

TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices.

Classification of rice disease is one significant research topics in rice phenotyping. Recognition of rice diseases such as Bacterialblight, Blast, Brownspot, Leaf smut, and Tungro are a critical research field in rice phenotyping. However, accurately identifying these diseases is a challenging issue due to their high phenotypic similarity. To address this challenge, we propose a rice disease phenotype identification framework which utilizing the transfer learning and SENet with attention mechanism on the cloud platform. The pre-trained parameters are transferred to the SENet network for parameters optimization. To capture distinctive features of rice diseases, the attention mechanism is applied for feature extracting. Experiment test and comparative analysis are conducted on the real rice disease datasets. The experimental results show that the accuracy of our method reaches 0.9573. Furthermore, we implemented a rice disease phenotype recognition platform based microservices architecture and deployed it on the cloud, which can provide rice disease phenotype recognition task as a service for easy usage.

Detecting Asymptomatic Infections of Rice Bacterial Leaf Blight Using Hyperspectral Imaging and 3-Dimensional Convolutional Neural Network With Spectral Dilated Convolution.

Rice is one of the most important food crops for human beings. Its total production ranks third in the grain crop output. Bacterial Leaf Blight (BLB), as one of the three major diseases of rice, occurs every year, posing a huge threat to rice production and safety. There is an asymptomatic period between the infection and the onset periods, and BLB will spread rapidly and widely under suitable conditions. Therefore, accurate detection of early asymptomatic BLB is very necessary. The purpose of this study was to test the feasibility of detecting early asymptomatic infection of the rice BLB disease based on hyperspectral imaging and Spectral Dilated Convolution 3-Dimensional Convolutional Neural Network (SDC-3DCNN). First, hyperspectral images were obtained from rice leaves infected with the BLB disease at the tillering stage. The spectrum was smoothed by the Savitzky-Golay (SG) method, and the wavelength between 450 and 950 nm was intercepted for analysis. Then Principal Component Analysis (PCA) and Random Forest (RF) were used to extract the feature information from the original spectra as inputs. The overall performance of the SDC-3DCNN model with different numbers of input features and different spectral dilated ratios was evaluated. Lastly, the saliency map visualization was used to explain the sensitivity of individual wavelengths. The results showed that the performance of the SDC-3DCNN model reached an accuracy of 95.4427% when the number of inputs is 50 characteristic wavelengths (extracted by RF) and the dilated ratio is set at 5. The saliency-sensitive wavelengths were identified in the range from 530 to 570 nm, which overlaps with the important wavelengths extracted by RF. According to our findings, combining hyperspectral imaging and deep learning can be a reliable approach for identifying early asymptomatic infection of the rice BLB disease, providing sufficient support for early warning and rice disease prevention.

Applying spectral fractal dimension index to predict the SPAD value of rice leaves under bacterial blight disease stress.

BACKGROUND: The chlorophyll content is a vital indicator for reflecting the photosynthesis ability of plants and it plays a significant role in monitoring the general health of plants. Since the chlorophyll content and the soil-plant analysis development (SPAD) value are positively correlated, it is feasible to predict the SPAD value by calculating the vegetation indices (VIs) through hyperspectral images, thereby evaluating the severity of plant diseases. However, current indices simply adopt few wavelengths of the hyperspectral information, which may decrease the prediction accuracy. Besides, few researches explored the applicability of VIs over rice under the bacterial blight disease stress. METHODS: In this study, the SPAD value was predicted by calculating the spectral fractal dimension index (SFDI) from a hyperspectral curve (420 to 950 nm). The correlation between the SPAD value and hyperspectral information was further analyzed for determining the sensitive bands that correspond to different disease levels. In addition, a SPAD prediction model was built upon the combination of selected indices and four machine learning methods. RESULTS: The results suggested that the SPAD value of rice leaves under different disease levels are sensitive to different wavelengths. Compared with current VIs, a stronger positive correlation was detected between the SPAD value and the SFDI, reaching an average correlation coefficient of 0.8263. For the prediction model, the one built with support vector regression and SFDI achieved the best performance, reaching R2, RMSE, and RE at 0.8752, 3.7715, and 7.8614%, respectively. CONCLUSIONS: This work provides an in-depth insight for accurately and robustly predicting the SPAD value of rice leaves under the bacterial blight disease stress, and the SFDI is of great significance for monitoring the chlorophyll content in large-scale fields non-destructively.

Influence of light intensity distribution characteristics of light source on measurement results of canopy reflectance spectrometers.

BACKGROUND: The characteristics of light source have an important influence on the measurement performance of canopy reflectance spectrometer. The size of the effective irradiation area and the uniformity of the light intensity distribution in the irradiation area determine the ability of the spectrometer to express the group characteristics of the measured objects. METHODS: In this paper, an evaluation method was proposed to theoretically analyze the influence of the light intensity distribution characteristics of the light source irradiation area on the measurement results. The light intensity distribution feature vector and the reflectance feature vector of the measured object were constructed to design reflectance difference coefficient, which could effectively evaluate the measurement performance of the canopy reflectance spectrometer. By using self-design light intensity distribution test system and GreenSeeker RT100, the evaluation method was applied to evaluate the measurement results. RESULTS: The evaluation results showed that the vegetation indices based on the arithmetic average reflectance of the measured object could be obtained theoretically only when the light intensity distribution of the light source detected by the spectrometer was uniform, which could fully express the group characteristics of the object. When the light intensity distribution of the active light source was not uniform, the measure value was difficult to fully express the group characteristics of the object. And the measured object reflectance was merely the weighted average value based on the light intensity distribution characteristics. CONCLUSIONS: According to the research results of this paper, sunlight is the most ideal detection light source. If the passive light source spectrometer can improve the measurement method to adapt to the change of sunlight intensity, its measurement performance will be better than any active-light spectrometer.