Research on precise phenotype identification and growth prediction of lettuce based on deep learning.

In recent years, precision agriculture, driven by scientific monitoring, precise management, and efficient use of agricultural resources, has become the direction for future agricultural development. The precise identification and assessment of phenotypes, which serve as external representations of a crop's growth, development, and genetic characteristics, are crucial for the realization of precision agriculture. Applications surrounding phenotypic indices also provide significant technical support for optimizing crop cultivation management and advancing smart agriculture, contributing to the efficient and high-quality development of precision agriculture.This paper focuses on lettuce and employs common nutritional stress conditions during growth as experimental settings. By collecting RGB images throughout the lettuce's complete growth cycle, we developed a deep learning-based computational model to tackle key issues in the lettuce's growth and precisely identify and assess phenotypic indices. We discovered that some phenotypic indices, including custom ones defined in this study, are representative of the lettuce's growth status. By dynamically monitoring the changes in phenotypic traits during growth, we quantitatively analyzed the accumulation and evolution of phenotypic indices across different growth stages. On this basis, a predictive model for lettuce growth and development was trained.The model incorporates MSE, SSIM, and perceptual loss, significantly enhancing the predictive accuracy of the lettuce growth images and phenotypic indices. The model trained with the reconstructed loss function outperforms the original model, with the SSIM and PSNR improving by 1.33% and 10.32%, respectively. The model also demonstrates high accuracy in predicting lettuce phenotypic indices, with an average error less than 0.55% for geometric indices and less than 1.7% for color and texture indices. Ultimately, it achieves intelligent monitoring and management throughout the lettuce's life cycle, providing technical support for high-quality and efficient lettuce production.

Design of IoT Gateway for Crop Growth Environmental Monitoring Based on Edge-Computing Technology.

With the extensive use of the Internet of Things (IoT) in agriculture, the number of terminals are also grow rapidly. This will increase the network traffic and computing pressure of the centralized server. The centralized data processing mode used in traditional agriculture cannot meet the needs of the Internet of everything era. This paper designs a gateway based on edge-computing technology for monitoring crop growth environment. It uses virtualized container technology to package long-range wide-area network (LoRaWAN) server, pest identification, and environmental information data fusion functions into images. It forms integrated operation mode of multiple function in agriculture. The gateway applies message-oriented middleware to standardize and customize the data transmission among functional modules, clouds, and edges. Through simulation and field test, the designed gateway can achieve the functions of each module at the same time, the resource utilization, and the transmission quality are stable. The edge-computing gateway has the advantages of low cost, low latency, and low power consumption which has practical significance.

A trace CH4 detection system based on DAS calibrated WMS technique.

We report the development of a compact near-infrared (NIR) laser-based trace methane (CH4) detection system. This detection system relied on a 2334 nm distributed feedback (DFB) fiber laser as the light source. A parallel dense light-spot pattern multipass gas cell (MGC) with 41.5 m effective absorption path length was utilized to improve the system sensitivity. A self-calibration approach based on direct absorption spectroscopy (DAS) calibrated wavelength modulation spectroscopy (WMS) technique was employed to solve the problem of extra concentration calibration requirement in traditional WMS technique, and to improve the accuracy and stability of the system. According to the Allan deviation analysis, 1-s measurement precision of 0.61 ppmv for DAS and 0.16 ppmv for WMS was obtained, which could be further reduced to 0.11 ppmv for DAS and 0.03 ppmv for WMS by averaging up to 80 s and 50 s, respectively. A week-long continuous atmospheric CH4 concentration measurement was also carried out to demonstrate the long-term performance of our CH4 detection system. With a fast dynamic response characteristics, high-accuracy and high-sensitivity, the proposed detection system is suitable for CH4 measurement in many fields such as atmospheric chemistry analyzation, industrial safety monitoring, agricultural information acquisition, etc.

Bionic Nonsmooth Drag Reduction Mathematical Model Construction and Subsoiling Verification.

In this study, a bionic nonsmooth drag-reducing surface design method was proposed; a mathematical model was developed to obtain the relationship between the altitude of the nonsmooth drag-reducing surface bulges and the spacing of two bulges, as well as the speed of movement, based on which two subsoiler shovel tips were designed and verified on field experiments. The mechanism of nonsmooth surface drag reduction in soil was analyzed, inspired by the efficient digging patterns of antlions. The nonsmooth surface morphology of the antlion was acquired by scanning electron microscopy, and a movement model of the nonsmooth surface in soil was developed, deriving that the altitude of the nonsmooth drag-reducing surface bulge is proportional to the square of the distance between two bulges and inversely proportional to the square of the movement speed. A flat subsoiler shovel tip and a curved tip were designed by applying this model, and the smooth subsoiler shovel tips and the pangolin scale bionic tips were used as controls, respectively. The effect of the model-designed subsoilers on drag reduction was verified by subsoiling experiments in the field. The results showed that the resistance of the model-designed curved subsoiler was the lowest, the resistance of the pangolin scale bionic subsoiler was moderate, and the resistance of the smooth surface subsoiler was the highest; the resistance of the curved subsoiler was less than the flat subsoilers; the resistance reduction rate of the model-designed curved subsoiler was 24.6% to 33.7% at different depths. The nonsmooth drag reduction model established in this study can be applied not only to the design of subsoilers but also to the design of nonsmooth drag reduction surfaces of other soil contacting parts.

Classification of soybean frogeye leaf spot disease using leaf hyperspectral reflectance.

In this study, the feasibility of classifying soybean frogeye leaf spot (FLS) is investigated. Leaf images and hyperspectral reflectance data of healthy and FLS diseased soybean leaves were acquired. First, image processing was used to classify FLS to create a reference for subsequent analysis of hyperspectral data. Then, dimensionality reduction methods of hyperspectral data were used to obtain the relevant information pertaining to FLS. Three single methods, namely spectral index (SI), principal component analysis (PCA), and competitive adaptive reweighted sampling (CARS), along with a PCA and SI combined method, were included. PCA was used to select the effective principal components (PCs), and evaluate SIs. Characteristic wavelengths (CWs) were selected using CARS. Finally, the full wavelengths, CWs, effective PCs, SIs, and significant SIs were divided into 14 datasets (DS1-DS14) and used as inputs to build the classification models. Models' performances were evaluated based on the classification accuracy for both the overall and individual classes. Our results suggest that the FLS comprised of five classes based on the proportion of total leaf surface covered with FLS. In the PCA and SI combination model, 5 PCs and 20 SIs with higher weight coefficient of each PC were extracted. For hyperspectral data, 20 CWs and 26 effective PCs were also selected. Out of the 14 datasets, the model input variables provided by five datasets (DS2, DS3, DS4, DS10, and DS11) were more superior than those of full wavelengths (DS1) both in support vector machine (SVM) and least squares support vector machine (LS-SVM) classifiers. The models developed using these five datasets achieved overall accuracies ranging from 91.8% to 94.5% in SVM, and 94.5% to 97.3% in LS-SVM. In addition, they improved the classification accuracies by 0.9% to 3.6% (SVM) and 0.9% to 3.7% (LS-SVM).

Sweet sorghum (Sorghum bicolor L.) SbSTOP1 activates the transcription of a ß-1,3-glucanase gene to reduce callose deposition under Al toxicity: A novel pathway for Al tolerance in plants.

Aluminum (Al) toxicity is a primary limiting factor for crop production in acid soils. Callose deposition, an early indicator and likely a contributor to Al toxicity, is induced rapidly in plant roots under Al stress. SbGlu1, encoding a ß-1,3-glucanase for callose degradation, showed important roles in sorghum Al resistance, yet its regulatory mechanisms remain unclear. The STOP1 transcription factors mediate Al signal transduction in various plants. Here, we identified their homolog in sweet sorghum, SbSTOP1, transcriptionally activated the expression of SbGlu1. Moreover, the DNA sequence recognized by SbSTOP1 on the promoter of SbGlu1 lacked the reported cis-acting element. Complementation lines of Atstop1 with SbSTOP1 revealed enhanced transcription levels of SbGlu1 homologous gene and reduced callose accumulation in Arabidopsis. These results indicate, for the first time, that SbSTOP1 is involved in the modulation of callose deposition under Al stress via transcriptional regulation of a ß-1,3-glucanase gene.

Characterization of microbial community succession during vermicomposting of medicinal herbal residues.

Large amounts of medicinal herbal residues (MHR) are produced in the world annually due to the increasing demand for herbal products. In this study, vermicomposting was used to stabilize MHR. Four inoculating density of earthworms was studied, specifically, 0 (W1), 60 (W2), 120 (W3) and 180 (W4) earthworms per kilogram of substrate. The C:N ratios of vermicomposts in W2, W3 and W4 were less than 20 by the end of the first week, while the value for W1 was 30.92. This indicates that earthworms promote the stabilization of MHR. In the initial stage, richness and diversity of the microbial community decreased due to earthworm inoculation, and then began to increase. The dominant phyla were Proteobacteria, Bacteroidetes, Basidiomycota and Ascomycota in the substrates. The abundance of the dominant phyla varied according to earthworm density, indicating that earthworms change the microbial composition. The results suggest that MHR can be stabilized by vermicomposting.

[Prediction of Greenhouse Cucumber Disease Based on Chlorophyll Fluorescence Spectrum Index].

The occurrence of greenhouse vegetable diseases and its epidemic seriously affect the production and management of facility agriculture, which greatly reduce the economic benefits of facility agriculture. In order to achieve nondestructive and accurate prediction of greenhouse vegetable diseases, this paper taking cucumber downy mildew disease as the research object, constructed spectrum characteristic index by using chlorophyll fluorescence induced by laser and established the prediction model of greenhouse vegetable diseases. In this paper, the experiment used comparative analysis method. The healthy leaves of the crops were inoculated with the pathogen spores, the spectrum curves of four groups of test samples: healthy, 2 d inoculated, 6 d inoculated and the ones with obvious symptoms were collected; then qualitative analysis was given to the variation regulation of the fluorescence intensity with the leaf samples infected with the pathogen spores. The chlorophyll fluorescence spectrum index k1=F685/F512 and k2=F734/F512 were created by using the peak and valley values of different bands. According to the range of values, set k1=20 and k2=10 as the characteristic value to judge the sample with obvious symptoms or with no obvious symptoms, and the accuracy rate of the judgment was 96% and 94% respectively. Based on spectrum index created and the classification results of sample health status, we selected the spectrum index F685/F512, F685-F734, F715/F612 to determine the health status of the sample and selected spectrum index F685/F512, F734/F512, F685-F734, F715/F612 as the inputs of quantitative analysis model. Regarding classification accuracy of prediction set as the evaluation criteria, we compared three data modeling methods: discriminant analysis, BP neural network and support vector machine. The results showed that the forecasting ability can reach 91.38% when the support vector machine was used as the modeling method for predicting the downy mildew disease. Use the method with chlorophyll fluorescence induced by laser to construct spectrum index to study the prediction of plant diseases, which has a good classification and identification effect.

[Prediction Model on Net Photosynthetic Rate of Soybean Plant Groups Based on Kernel Function and Visible Light Spectrum].

The paper uses MSR-16 portable multispectral radiometer made in the USA and computes the numbers of the test units by pulling the formula on the radiometer effective observation area, which solves the problem on the uncertain numbers of computing the times on region visible light band spectral radiation ratio M_D. The paper uses CI-310 portable photosynthesis measurement system made by American CID Company and measures the net photosynthetic rate of a group of soybean plant. M_D and C_D are normalized by the normalization method [0,1]. Then, the normalization data M_D1 and C_D1 are gained . Based on the different test time, M_D1 is divided of M_D11 and M_D12. C_D1 is divided of C_D11 and C_D12. The paper uses polynomial kernel function, gauss kernel function, sigmoid kernel function and bio-selfadaption kernel function constructed by us with Support Vector Machine. Penalty parameter c and parameter g separately are optimized with optimization algorithms such as grid-search，genetic algorithm and particle swarm optimization. Based on the formula epsilon-SVR and the formula nu-SVR with Support Vector Machine, the paper constructs the prediction model on the net photosynthetic rate of a group of soybean plant by using of the cross combination with four kernel functions, three optimization methods and two formulas. The test results are as follows: in the condition of S=17 m2 which is the test plan area of soybean plant and the H=2 m which is the high on MSR-16 portable multispectral radiometer above the canopy of soybean plant, the prediction accuracy is up to 85% on the No.1 prediction set C_D12 and the prediction accuracy is up to 82% on the No.2 prediction set C_D12 based on the model epsilon-SVR-bio-selfadaption-grid-search. In the condition of other combinations with S and H, the prediction accuracy is up to 81% on the No.2 prediction set C_D12 based on the model epsilon-SVR-bio-selfadaption-grid-search. The model epsilon-SVR-bio-selfadaption-grid-search indicates the validity of bio-selfadaption kernel functions which is constructed by our previous research with support vector machine. The model epsilon-SVR-bio-selfadaption-grid-search indicates the rationality of the measure method on visible spectral data in the test area. The model epsilon-SVR-bio-selfadaption-grid-search indicates the feasibility of the prediction method on net photosynthetic rate of soybean plant groups by using of visible spectrum.

[Rice blast prediction model based on analysis of chlorophyll fluorescence spectrum].

In order to detect rice blast more rapidly, accurately and nondestructively, the identification and early warning models of rice blast were established in the present research. First of all, rice blast was divided into three grades according to the relative area of disease spots in rice leaf and laser induced chlorophyll fluorescence spectra of rice leaves at different disease levels were measured in the paddy fields. Meanwhile, 502-830 nm bands of laser-induced chlorophyll fluorescence spectra were selected for the study of rice blast. Savitzky-Golay(SG) smoothing and First Derivative Transform(FDT) were applied for the pretreatment of laser-induced chlorophyll fluorescence spectra. Then the method of Principal Components Analysis (PCA) was used to achieve the dimension reduction on spectral information, three principal components whose variance are greater than 1 and cumulative credibility is 99.924% were extracted by this method. Furthermore, the tentative data were divided into calibration set and validation set, the levels of rice blast were taken as the predictors. Combined with the calibration set which contains the disease and spectral information of 133 leaves, Discriminant Analysis (DA), Multiple Logistic Regression Analysis (MLRA) and Multilayer Perceptron (MLP) were used respectively to establish the identification and early warning models of rice blast. The Prediction examinations of the three models were made based on the validation set which contains the disease and spectral information of 89 leaves. The results show that all the models of PCA-DA, PCA-MLRA and PCA-MLP can carry on the prediction of rice blast, and the average prediction accuracy of PCA-MLP prediction model is 91.7% which is improved compared with PCA- DA and PCA- MLRA.

[Fluorescence spectrum monitor for early warning of greenhouse cucumber aphis pests].

The infection and degree of cucumber aphis pests was studied by analyzing chlorophyllfluorescence spectrum in greenhouse. Based on the configuration of the spectrum, characteristic points were established, in which the intensity of waveband F632 was the first characteristic point between healthy and aphis pests leaves. The second characteristic point was K which was the change rate of spectral curve from waveband F512 to F632. The early warning could be executed on plants depending on these two points. The models of the infection and degrees of aphis pests were established for different wavebands by the least square support vector machine classification method (LSSVMR) radial basis function(RBF). The accuracy rate of classification and prediction of the models was compared by different peaks and valleys value in wavebands. The results indicated that the prediction accuracy of the model established by waveband F632 was the most perfect (96.34%).

[Chlorophyll fluorescence spectrum analysis of greenhouse cucumber disease and insect damage].

The present paper is based on chlorophyll fluorescence spectrum analysis. The wavelength 685 nm was determined as the primary characteristic point for the analysis of healthy or disease and insect damaged leaf by spectrum configuration. Dimensionality reduction of the spectrum was achieved by combining simple intercorrelation bands selection and principal component analysis (PCA). The principal component factor was reduced from 10 to 5 while the spectrum information was kept reaching 99.999%. By comparing and analysing three modeling methods, namely the partial least square regression (PLSR), BP neural network (BP) and least square support vector machine regression (LSSVMR), regarding correlation coefficient of true value and predicted value as evaluation criterion, eventually, LSSVMR was confirmed as the appropriate method for modeling of greenhouse cucumber disease and insect damage chlorophyll fluorescence spectrum analysis.

[Prediction model of net photosynthetic rate of ginseng under forest based on optimized parameters support vector machine].

Using K-fold cross validation method and two support vector machine functions, four kernel functions, grid-search, genetic algorithm and particle swarm optimization, the authors constructed the support vector machine model of the best penalty parameter c and the best correlation coefficient. Using information granulation technology, the authors constructed P particle and epsilon particle about those factors affecting net photosynthetic rate, and reduced these dimensions of the determinant. P particle includes the percent of visible spectrum ingredients. Epsilon particle includes leaf temperature, scattering radiation, air temperature, and so on. It is possible to obtain the best correlation coefficient among photosynthetic effective radiation, visible spectrum and individual net photosynthetic rate by this technology. The authors constructed the training set and the forecasting set including photosynthetic effective radiation, P particle and epsilon particle. The result shows that epsilon-SVR-RBF-genetic algorithm model, nu-SVR-linear-grid-search model and nu-SVR-RBF-genetic algorithm model obtain the correlation coefficient of up to 97% about the forecasting set including photosynthetic effective radiation and P particle. The penalty parameter c of nu-SVR-linear-grid-search model is the minimum, so the model's generalization ability is the best. The authors forecasted the forecasting set including photosynthetic effective radiation, P particle and epsilon particle by the model, and the correlation coefficient is up to 96%.

[Cucumber downy mildew prediction model based on analysis of chlorophyll fluorescence spectrum].

In order to achieve quick and nondestructive prediction of cucumber disease, a prediction model of greenhouse cucumber downy mildew has been established and it is based on analysis technology of laser-induced chlorophyll fluorescence spectrum. By assaying the spectrum curve of healthy leaves, leaves inoculated with bacteria for three days and six days and after feature information extraction of those three groups of spectrum data using first-order derivative spectrum preprocessing with principal components and data reduction, principal components score scatter diagram has been built, and according to accumulation contribution rate, ten principal components have been selected to replace derivative spectrum curve, and then classification and prediction has been done by support vector machine. According to the training of 105 samples from the three groups, classification and prediction of 44 samples and comparing the classification capacities of four kernel function support vector machines, the consequence is that RBF has high quality in classification and identification and the accuracy rate in classification and prediction of cucumber downy mildew reaches 97.73%.

[Diagnosis of cucumber diseases and insect pests by fluorescence spectroscopy technology based on PCA-sVM].

The diagnosis model of the cucumber diseases and insect pests was established by laser-induced chlorophyll fluorescence (LICF) spectroscopy technology combined with support vector machines (SVM) algorithm in the present research. This model would be used to realize the fast and exact diagnosis of the cucumber diseases and insect pests. The noise of original spectrum was reduced by three methods, including Savitzky-Golay smoothing (SG), Savitzky-Golay smoothing combined with fast Fourier transform (FFT) and Savitzy-Golay smoothing combined with first derivative transform (FDT). According to the accumulative reliabilities (AR) seven principal components (PCs) were selected to replace the complex spectral data. The one hundred fifty samples were randomly separated into the calibration set and the validation set. Support vector machines (SVM) algorithm with four kinds of kernel functions was used to establish diagnosis models of the cucumber diseases and insect pests based on the calibration set, then these models were applied to the diagnosis of the validation set. According to the best diagnosis accuracy of cross-validation method in calibration set, the parameters of four kinds of kernel function models were optimized, and the capabilities of SVM with different kernel function were compared. Results showed that SVM with the ploy kernel function had the best identification capabilities and the accuracy was 98. 3% after the original spectrum noise was reduced by SG+FDT+ PCA. This research indicated that the method of PCA-SVM had a good identification effect and could realize rapid diagnosis of the cucumber diseases and insect pests as a new method.