An experiment was carried out to examine the effects of low-protein diets supplemented with different levels of DL-methionine (Met) and Lysine (Lys) on growth performance of growing-furring blue foxes in order to find the optimal dietary supplementation levels of Met and Lys. For two protein levels, conventional 27 % (P27) and low 19 % (P19) on dry matter basis, respectively, and the low-protein diets were supplemented with Met (0.3 %, 0.5 %, 0.7 %) and Lys (0.4 %, 0.6 %, 0.8 %). An entirely random experimental design was adopted with two factors (3 × 3) and totally 10 groups (P27, L1M1, L1M2, L1M3, L2M1, L2M2, L2M3, L3M1, L3M2 and L3M3). From mid-September to pelting, based on the average daily gain, daily N retention, N retention ratio and the performance of blue foxes in different groups, 0.6 % Met supplementation in low-protein diet was optimum; based on the daily N retention, N biological value and the quality of the fur, 0.3 % and 0.5 % Lys supplementation were optimum; based on the N apparent digestibility and daily N output, 0.3 % Lys supplementation was optimum. In this experiment, the performance of blue foxes in L1M2 0.3 % Lys × 0.6 % Met group was better than that in the other groups, which indicates that low-protein diets supplemented with DL-methionine and lysine for blue foxes can be beneficial to reduce feed expenses and nitrogen emission to the environment.
Forest biomass could quantify the complex relationship between the change of forest carbon storage and the carbon cycle in the environment. The accurate estimation results of forest biomass are the basis for the analysis and evaluation of forest ecosystem structure, function, quality and benefit. The distribution of forest biomass is the result of the interaction of structural factors and random factors. A typical data flow processing framework had been adopted, and a new ecological tool: Multi-factor assisted forest biomass spatial interpolation software tool (MFA-SIS) had been designed and implemented. The MFA-SIS had implemented complex algorithm logic in the underlying code, and simplified the pre-processing process of multi-factor assisted modeling data and forest biomass sample data. And the visualization interface could provide a good software module for forest biomass estimation that is easy to learn, practical and has great application potential, and provide a good underlying model algorithm tool support for the "double carbon" strategy proposed by China.
In the domain of food science, apple grading holds significant research value and application potential. Currently, apple grading predominantly relies on manual methods, which present challenges such as low production efficiency and high subjectivity. This study marks the first integration of advanced computer vision, image processing, and machine learning technologies to design an innovative automated apple grading system. The system aims to reduce human interference and enhance grading efficiency and accuracy. A lightweight detection algorithm, FDNet-p, was developed to capture stem features, and a strategy for auxiliary positioning was designed for image acquisition. An improved DPC-AWKNN segmentation algorithm is proposed for segmenting the apple body. Image processing techniques are employed to extract apple features, such as color, shape, and diameter, culminating in the development of an intelligent apple grading model using the GBDT algorithm. Experimental results demonstrate that, in stem detection tasks, the lightweight FDNet-p model exhibits superior performance compared to various detection models, achieving an mAP@0.5 of 96.6%, with a GFLOPs of 3.4 and a model size of just 2.5 MB. In apple grading experiments, the GBDT grading model achieved the best comprehensive performance among classification models, with weighted Jacard Score, Precision, Recall, and F1 Score values of 0.9506, 0.9196, 0.9683, and 0.9513, respectively. The proposed stem detection and apple body classification models provide innovative solutions for detection and classification tasks in automated fruit grading, offering a comprehensive and replicable research framework for standardizing image processing and feature extraction for apples and similar spherical fruit bodies.
In order to ensure the best taste and maturity of the picked tomatoes during the market, this paper designed a facility tomato picking system based on shelf life prediction and fruit maturity discrimination. Use the deep learning method to predict the shelf life of tomatoes and distinguish the ripeness of tomato fruits, and calculate the best picking time of tomatoes through the shelf life and fruit ripeness. The use of this system avoids the uncertainty of empirical judgment of picking time, improves economic benefits, and is of great significance to the development of intelligent fruit and vegetable picking.
The collection, integration, analysis and sharing of digital specimens of wood canker is an important basic work for conducting relevant scientific research, education and teaching. In this study, for all kinds of users, such as scientific research, education, experts and the public, the architecture of Sharing platform of digital specimen of wood canker in Xinjiang province was designed by microservice architecture, the microservice function tree was constructed by domain-driven design method, the microservice cluster was built by using Spring Cloud technology components, and 8 kinds of microservices were developed based on WebGIS technology. The application results show that the platform is easy to use, provides data sharing and services through visualization and interactivity, and can provide decision-making data resources support for scientific research, education, monitoring, quarantine and prevention of wood canker.
From a global ecological management perspective, as a core tree species in the mountain ecosystem of Xinjiang, the study of the spatial distribution characteristics of Picea schrenkiana var. tianschanica is crucial for maintaining the ecological balance in the Tianshan region. This study focuses on the western section of the Tianshan mountains in Xinjiang and employs the variogram analysis technique to explore the spatial heterogeneity of Picea schrenkiana var. tianschanica biomass. Successively, the study implements ordinary kriging, multivariate linear regression, the random forest algorithm, and an innovative random forest residual kriging method to conduct a spatial interpolation analysis of Picea schrenkiana var. tianschanica biomass in the target area. The results indicate that the biomass of Picea schrenkiana var. tianschanica exhibits moderate spatial autocorrelation, with its distribution pattern being influenced by a combination of topography, climate, and soil conditions. After comparing multiple spatial interpolation methods, it is found that the hybrid model combining regression analysis and kriging, delivers the best performance (R2 = 0.642, RMSE = 40.18, RMSPE = 44.6). This model not only significantly improves the prediction accuracy, but also provides an intuitive and accurate spatial distribution map of Picea schrenkiana var. tianschanica biomass in the western section of the Tianshan mountains which reveals the global ecological importance of Picea schrenkiana var. tianschanica in an intuitive and accurate way, providing valuable scientific evidence and practical guidance for the field of international ecological protection and resource management.
The optimal fitting of variogram is the key to study the spatial variance law of heavy metals in soil, which can effectively improve the accuracy and reliability of spatial interpolation of heavy metals in soil. In this study, the framework of multi-scale nested model optimal fitting software for heavy metals spatial estimation variogram in soil was designed by using microservice architecture. Six kinds of microservices were designed and implemented by mixed programming of Java and Python. Experiments showed that the system interface is simple and friendly, and could substantially reduce the difficulty of optimal fitting of multi-scale nested model of spatial variogram through visualization and interaction. Moreover, the optimal fitting algorithm of multiscale nested model based on deep learning could effectively improve the accuracy of spatial interpolation, and could provide a good software tool for relevant research in the field of resources and environment.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)