首页期刊导航|Computers and Electronics in Agriculture
期刊信息/Journal information
Computers and Electronics in Agriculture
Elsevier Science Publishers
Computers and Electronics in Agriculture

Elsevier Science Publishers

0168-1699

Computers and Electronics in Agriculture/Journal Computers and Electronics in AgricultureSCIEIISTP
正式出版
收录年代

    Early diagnosis and pathogenesis monitoring of wheat powdery mildew caused by blumeria graminis using hyperspectral imaging

    Xuan G.Li Q.Shao Y.Shi Y....
    9页
    查看更多>>摘要：? 2022 Elsevier B.V.Powdery mildew caused by blumeria graminis is responsible for wheat yield losses in combination with a decline in quality. Hyperspectral imaging as a promising non-invasive sensor technique has potential for early diagnosis and pathogenesis monitoring of wheat powdery mildew, which is a practice that allows for precision crop protection. Hyperspectral images were first captured before inoculation as healthy samples and daily 2 to 5 days after inoculation (dai) as infected ones. Principal component analysis (PCA) was applied to observe the discrimination capability between samples at different infected stages, while a gray-level co-occurrence matrix (GLCM) was used to extract textural features from the first three principal component images. Then partial least squares discriminant analysis (PLS-DA) model was developed to evaluate the ability for early diagnosis of the disease using effective wavelengths, texture features and their fusion, respectively. Compared with the models using spectral or textural feature alone, PLS-DA model using the fused dataset obtained the best performances with classification accuracy of 91.4 % in validation sets. Furthermore, spectral angle mapping (SAM) was performed to identify the infected tissue in wheat leaves 2 dai, and to monitor the pathogenesis of powdery mildew over time. The results from this study could be used to develop a portable field monitoring sensor for wheat powdery mildew.
      原文链接:
    • NSTL
    • Elsevier

    Application and accuracy of smart technologies for measurements of roundwood: Evaluation of time consumption and efficiency

    Borz S.A.Proto A.R.
    13页
    查看更多>>摘要：? 2022 Elsevier B.V.Several options are currently available for wood measurement and grading and the manual ones are still widely used in many countries. In the last decade, LiDAR-based methods have been successfully tested in several forestry-related applications, in particular in forest inventory applications, with the main focus on data accuracy. Their usefulness for the quantitative assessment of the harvested wood was less investigated. In particular, studies on resource accounting, including the time needed for various log scanning options, are still missing. In the framework of the Hypercube 4.0 project, this study evaluated and compared the field measurement time consumption of manual (M) and LiDAR-based methods applied to logs characterized by various grouping degrees, namely individual logs, log bunches and piles. Two LiDAR-based platforms were tested, namely a smartphone (S) and a mobile laser scanner (MLS). As these platforms hold different sensing, data storing and processing capabilities, scanning procedures were designed and tested in accordance with their sensing distance capabilities and with the potential of using them in real-world applications. Scanning individual logs by smartphones returned an average cycle time which was lower, though close to that of a detailed manual measurement option, accounting for ca. 1.5 min. When scanning log bunches and piles, the cycle time increased to ca. 2.8 and 7 min, respectively; however, the scanning efficiency increased also as an effect of the scanning scale from ca. 92 s per log, when scanning individual logs, to ca. 67 and 46 s per log, when scanning log bunches and piles, respectively. The MLS option was tested for small and big groups of individual logs and log bunches scanned in one turn, as well as for scanning individual piles of logs; in general, these options returned the best efficiency rates, accounting in the best case for ca. 19 s per log. Depending on the type of wood measurement application, by their efficiency, smartphone and MLS scanning platforms hold the potential of replacing the manual measurement, particularly when the use of manual procedures is limited. While this study evaluated the time consumption and efficiency of several scanning options, the question on data accuracy remains open and needs to be approached by future studies, some of which are already running in the framework of the Hypercube 4.0 project.
      原文链接:
    • NSTL
    • Elsevier

    Untangling the effect of soil quality on rice productivity under a 16-years long-term fertilizer experiment using conditional random forest

    Garnaik S.Samant P.K.Mandal M.Mohanty T.R....
    12页
    查看更多>>摘要：? 2022 Elsevier B.V.In a 16-years long-term fertilizer experiment, an in-depth study was carried out to evaluate the changes in soil physical, chemical, and biological properties under long-term fertilizer application and establish cause and effect relationship between soil properties and rice productivity using interpretable machine learning. There were 12 treatments involving control (without fertilizer application), 100% N (recommended dose of nitrogen), 100% NP (recommended dose of nitrogen and phosphorus), 100% PK (recommended dose of phosphorus and potassium), 100% NPK (recommended dose of nitrogen, phosphorus, and potassium), 150% NPK (50% higher nitrogen, phosphorus, and potassium than recommended), 100% NPK + Zn (recommended nitrogen, phosphorus, and potassium along with Zinc), 100% NPK + FYM (recommended nitrogen, phosphorus, and potassium along with farmyard manure (FYM)), 100% NPK + FYM + LIME (recommended nitrogen, phosphorus, and potassium along with FYM and lime), 100% NPK + Zn + S (recommended nitrogen, phosphorus, and potassium along with zinc and sulphur), 100% NPK + Zn + B (recommended nitrogen, phosphorus, and potassium along with Zinc and Boron) and 100% NPK + Lime (recommended nitrogen, phosphorus, and potassium along with lime). At first, a conditional random forest model was built, based on which important variables were selected using the permutation-based variable importance approach. Further, the accumulated local effect plot was used to establish a cause and effect relationship between important soil properties and rice yield. Although most of the soil properties varied across the treatments, total potassium, protease, urease, and permanganate oxidisable carbon are the most important soil properties, individually accounting for up to 400 kg ha?1 variation in the rice productivity. The study demonstrated how interpretable machine learning techniques could be used in long-term fertilizer experiments to unravel the most meaningful information, and these techniques can be used in other similar long-term experiments.
      原文链接:
    • NSTL
    • Elsevier

    Cut-edge detection method for wheat harvesting based on stereo vision

    Zhang Z.Cao R.Zhang M.Li H....
    10页
    查看更多>>摘要：? 2022 Elsevier B.V.A cut-edge detection method for wheat based on stereo vision was proposed in this work to obtain the navigation path of a combine harvester. First, the point cloud was acquired by the stereo camera. The crop area was extracted with the threshold obtained by the Otsu method. Then, the point cloud of the crop area was gridded. The grids were clustered by the density-based spatial clustering of applications with noise method to classify the different crop areas. After filtering the noise caused by the ridge in the yield, the grids of interest were extracted. The edge point was extracted in each grid of interest. The polynomial fitting method was then used to acquire the straight or curved cut-edge. A total of 300 images were selected for the test of crop area extraction and crop areas classification. The results showed that the success rate of crop area extraction was 93.7% and the success rate of crop areas classification was 91.1%. 100 images were selected to extract the edge points and compare with the true value of manual measurement. Experiment results showed that the average deviation of the edge points was 8.47 cm, the maximum deviation was 23.1 cm, and the standard deviation was 5.97 cm. The proposed method is thus capable of providing support for the automatic navigation of combine harvesters.
      原文链接:
    • NSTL
    • Elsevier

    A comprehensive review of remote sensing platforms, sensors, and applications in nut crops

    Jafarbiglu H.Pourreza A.
    23页
    查看更多>>摘要：? 2022 The AuthorsBackground: Due to their high protein content, nuts (almond, walnut, and pistachio) are among the main substitutes for meat, with a growing share of the food basket in the United States. However, the rapidly growing acreage of these crops, new legislations, the necessity of minimizing the environmental footprint, and a cost-effective production demand certain managerial practices based on precision agriculture and remote sensing, which have shown promising results in food production. Scope and approach: This paper presents a comprehensive review of remote sensing platforms, sensors, applications, and analytic pipelines with a focus on nut crops, even though the materials are applicable for other specialty crops. In this regard, the paper is divided into five main sections: First, the problems and potential solutions are elaborated in the introduction. Second, the available platforms: satellites, manned aircraft, and UASs are discussed. Then the sensors used for remote sensing, their working principle, and the pros and cons of each are presented. Next, practiced and suggested applications of remote sensing data are reviewed. Finally, data processing and analytics needed to produce and interpret reliable results are highlighted. Key findings and conclusions: Key findings are listed as: 1) The acreage of the nut orchards and the purpose of the studies determine the fitting sensor and platform. 2) Although various sensors are available and reported to have promising results in other crops, they have not been used for nut crops. 3) Accurate sensor calibration is crucial for repeatable results as well as temporal and inter-field comparisons. 4) Except for water management, most remote sensing applications are limitedly studied in nut orchards, creating some research opportunities. 5) Finally, increasing data size requires new machine learning techniques and data fusion frameworks to handle all variables and fill the knowledge gap.
      原文链接:
    • NSTL
    • Elsevier

    Unmanned airboat technology and applications in environment and agriculture

    Liu Y.Wang J.Shi Y.He Z....
    13页
    查看更多>>摘要：? 2022The rapid development of new technologies such as automatic control technology, sensor technology, and artificial intelligence(AI) has contributed to the development of unmanned airboats(UA) and their applications in recent years. UA has the characteristics of lightness, flexibility, and little environmental interference. It has been significant for accomplishing automatic environmental monitoring and agricultural production tasks, especially when the water environment is complex and challenging for traditional unmanned surface vehicles(USVs). This review focuses on the challenges faced in the development of UA and proposes specific targeted countermeasures and suggestions. The structure of the UA was first presented systematically, then its applications in environmental monitoring and agricultural production were introduced and summarized comprehensively. Finally, the challenges and prospects of UA were examined in detail. This review can provide theoretical and technical support to promote the applications of UA for automated operation.
      原文链接:
    • NSTL
    • Elsevier

    A noncontact self-suction wheat shooting device for sustainable agriculture: A preliminary research

    Wang Y.Li H.He J.Wang Q....
    17页
    查看更多>>摘要：? 2022 Elsevier B.V.In this study, a noncontact self-suction wheat shooting device was developed through TRIZ theory to improve seed-filling performance and eliminate the contact between seed and device. A preliminary suction experiment was developed using FLUENT to simulate airflow velocity and evaluate the feasibility of self-suction performance of seeds. The DEM-CFD coupling simulation experiment was conducted to investigate the shooting performance. The simulation results showed the airflow velocity was over 6.5 m/s while rotational speed was more than 800 rpm, which could meet the seed-filling requirements. With the rotational speed increase, seed velocity and seed filling performance improves. On the contrary, a larger rotational speed and installation angle induced a higher CF (contact force). CF was significantly affected by rotational speed, window length and installation angle. The increasing window length resulted in the improvement of seed filling performance in a certain range. Meanwhile, the indicators of coefficient of variation for seeding uniformity (CVSU), coefficient of variation for seeding depth (CVSD) and seed damage rate (DR) were evaluated to investigate sowing performance of self-suction shooting device in validation experiment. Results from bench and field experiment showed the seed-filling and shooting performance of self-suction shooting device under optimized operation parameters could fully meet the sowing requirement of winter wheat in North China plain. The collision performance between seed and blades of optimized self-suction shooting device was superior to the mechanical one. In specific, CVSU, CVSD, ASD, ASS and seed germination rate of optimized self-suction shooting device were 11.3%, 8.7%, 31.0 m/s, 30.1 mm and 89.2%, respectively.
      原文链接:
    • NSTL
    • Elsevier

    Prediction and optimization of emission in an agricultural harvest engine with biodiesel-diesel blends by a method of ANN and CMA-ES

    Zheng B.Song Z.Mao E.Zhou Q....
    10页
    查看更多>>摘要：? 2022To address the current problems of high exhaust emission level of domestic agricultural equipments and serious human and environmental hazards of agricultural machinery engine emissions, in this study, an agricultural harvester diesel engine test platform was firstly built to conduct a biodiesel-diesel combustion emission test and collect data. In addition, an Artificial Neural Network high-precision model was designed and constructed for training and prediction of the outputs such as nitrogen oxides (NOx), hydrocarbons (HC), carbon monoxide (CO), opaque smoke, and post-turbo emission temperatures at different engine operating conditions and various biodiesel-diesel blend ratios, speed and engine load. The type of neural network selected is a feed-forward multi-layer perceptron network because of its advantage of reflecting the correlations between input and output. The model's regression coefficients of NOx, HC, CO, opaque smoke, and post-turbo emission temperatures R2 = 0.9822, 0.9934, 0.9937, 0.9967 0.9970, were close to 1; mean square error (MSE) = 9.79%, 7.73%, 6.48%, 9.58% 2.27%, root mean square error (RMSE) = 18.41 ppm, 3.21 ppm, 16.48 ppm, 0.39 m?1, 10.86 °C. The results show that the established models have high confidence and can be used for high-precision agricultural machinery engine emission prediction and calculation. Covariance Matrix Adaptation-Evolutionary Strategy (CMA-ES) was applied to obtain the best matching parameters for the optimum engine operating conditions with optimized emissions. The biodiesel-diesel blend ratio, engine speed, and engine load were optimized with different single-target emissions as the objective function, respectively. In addition, with multi-target emissions as the objective function, the values of the three optimization variables are 5%, 1850 rpm, 25% respectively. The error rate between the experimental data and predicted values is around 3%-10%, and thereby the method is considered practicable through experimental validation. The experimental results show that ANN supported by CMA-ES is a good method for predicting and optimizing emissions of diesel engines burning biodiesel-diesel blends in agricultural machinery.
      原文链接:
    • NSTL
    • Elsevier

    Multi-view real-time acquisition and 3D reconstruction of point clouds for beef cattle

    Li J.Ma W.Li Q.Zhao C....
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.Body size, weight, and body condition score parameters are key indicators for monitoring cattle growth and they can be utilized to predict beef cattle yield and evaluate economic traits. However, it is easy to lay intense stress on cattle while measuring livestock's body size manually, also along with giving negative effects on their feeding and weight gain. To resolve this problem, we design a real-time point cloud collection system for beef cattle with five depth cameras on a gantry structure. We developed point cloud preprocessing, registration, and 3D reconstruction algorithms, and quantitatively estimated the influence of light intensity during point cloud collection. The algorithms perform point cloud filtering, registration, segmentation, down-sampling, 3D reconstruction of the global point cloud, and target recognition. The maximum uncertainty of the calculated body width and length is 20 mm, and the acquisition time is within 0.08 s. We established a real-time system for 3D cattle point cloud- collection, which involves no stress on cattle when measuring. The point cloud collected by the system can provide technical support for the automatic extraction of key features during livestock body measurements.
      原文链接:
    • NSTL
    • Elsevier

    Agricultural E-commerce: Attitude segmentation of farmers

    Schulze Schwering D.Isabell Sonntag W.Kuhl S.
    11页
    查看更多>>摘要：? 2022 Elsevier B.V.E-commerce in agricultural trade is a growing market segment. Therefore, knowledge about the online purchasing behavior of farmers is increasingly important for several stakeholders. The purpose of this study is to explore agricultural online buying behavior from a multidimensional perspective. By means of an online survey among 371 German farmers, the attitudinal segmentation of online farmers is investigated using the tripartite model of attitudes. Four clusters were identified: business professionals, loyal offliners, online fans, and online hesitators. Results show that the advantageousness (convenience) was rated the highest and has the greatest separating power, while affective attributes are less important to farmers. Loyal offliners demonstrate that a positive emotional and cognitive evaluation does not necessarily increase the intention to use. In addition, the cluster of business professionals express that a lack of enjoyment does not automatically result in a lower intention to use e-commerce. The segmentation shows that there are different farmer groups needing an individual communication strategy and individual website features when buying agricultural inputs online. The results can help to make online offers more attractive and increase farmers’ usage intentions.
      原文链接:
    • NSTL
    • Elsevier