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

    Development of a computer vision approach as a useful tool to assist producers in harvesting yellow melon in northeastern Brazil

    Ripardo Calixto R.Ripardo de Alexandria A.Pinheiro Neto L.G.Nascimento Lopes F.G....
    9页
    查看更多>>摘要：? 2021 Elsevier B.V.This paper presents a Computer Vision (CV) approach to harvest decision of yellow melon (hybrid Natal?) based on prediction of Soluble Solids Content (SSC, as °Brix) from digital image. At this point, it is worth remembering that the minimum SSC for harvesting this type of melon is 9°Brix. In this context, melons with SSC ≥ 9°Brix should be classified as “suitable for harvesting” (SFH), whereas melons with SCC < 9°Brix should be classified as “unsuitable for harvesting” (UFH). Nonetheless, the visual decision of this harvest point is difficult due to the uniform yellow color of this melon's rind. To circumvent this problem and ensure quality (SSC ≥ 9°Brix), growers use the practice of taking pre-harvest melon samples to measure SSC by refractometry. However, this practice presents two problems: as it analyzes a limited number of samples, the result does not reflect the totality of the fruits; and because it is destructive, it causes the loss of marketable melons. Based on digital images, the hypothesis of this work states that it is possible to develop a non-destructive CV-based technique, which will allow growers to decide in real time whether each melon is suitable for harvesting or not. From the foregoing, the aim was to develop a simple, fast and inexpensive CV technique, based on the texture differences in the yellow color of this melon's rind, able of analyzing SSC (as °Brix) of all melons at harvest moment, classifying them as SFH or UFH. For this purpose, we used a digital camera to capture the image and a portable refractometer to quantify the SSC of each melon (n = 144). Melons were then divided into two classes with 72 melons each - SFH (SSC ≥ 9° Brix) or UFH (SSC < 9° Brix). In each image, we manually selected three (3) small regions (205 × 205 pixels), totaling 432 images (Image Database). From Image Database, 302 images (70%) were used for training, being one half (156 images) from SFH and the other half of the UFH. For the test, we used 130 images (30%) of the Image Database, being 67 images from SFH and 63 from UFH. Based on color filters (RGB average, Channel H, and Channel Y), textures (using Local Binary Pattern, LBP) and two classifiers (KNN or MLP), the developed CV-technique proved useful to predict SSC still in the field, as well as to classify melons into the two-kwon classes (SFH or UFH). The classifiers' performance has been verified by confusion matrix associated with the Receiver Operating Characteristics (ROC) analysis. The MLP obtained 95% accuracy, while the KNN obtained 94%. In addition, the combination of MLP (classifier) with the RGB average (color filter) presented the highest hits (accuracy), as well as the lowest false positive values. From the results obtained in this work, it is possible to conclude that the developed CV-method is useful for growers to classify yellow melon Natal? at the harvest moment.
      原文链接:
    • NSTL
    • Elsevier

    Delineation of cultivated land parcels based on deep convolutional networks and geographical thematic scene division of remotely sensed images

    Dong D.Zhou C.Xu L.Ming D....
    16页
    查看更多>>摘要：? 2021 Elsevier B.V.Extraction of cultivated land information from high spatial resolution remote sensing images is increasingly becoming an important approach to digitization and informatization in modern agriculture. The continuous development of deep learning technology has made it possible to extract information of cultivated land parcels by an intelligent way. Aiming at fine extraction of cultivated land parcels within large areas, this article builds a framework of geographical thematic scene division according to the rule of territorial differentiation in geography. A deep learning semantic segmentation network, improved U-net with depthwise separable convolution (DSCUnet), is proposed to achieve the division of the whole image. Then, an extended multichannel richer convolutional features (RCF) network is involved to delineate the boundaries of cultivated land parcels from agricultural functional scenes obtained by the former step. In order to testify the feasibility and effectiveness of the proposed methods, this article implemented experiments using Gaofen-2 images with different spatial resolution. The results show an outstanding performance using methods proposed in this article in both dividing agricultural functional scenes and delineating cultivated land parcels compared with other commonly used methods. Meanwhile, the extraction results have the highest accuracy in both the traditional evaluation indices (like Precision, Recall, F1, and IoU) and geometric boundary precision of cultivated land parcels. The methods in this article can provide a feasible solution to the problem of finely extracting cultivated land parcels information within large areas and complex landscape conditions in practical applications.
      原文链接:
    • NSTL
    • Elsevier

    Modelling and controlling dissolved oxygen in recirculating aquaculture systems based on mechanism analysis and an adaptive PID controller

    Zhou X.Li D.Duan Q.Wang J....
    14页
    查看更多>>摘要：? 2021 Elsevier B.V.In aquaculture, dissolved oxygen (DO) content is critical to the growth and development of aquatic products, and it must be precisely controlled. Based on the theory of microporous aeration mass transfer and mass conservation equations, this paper analyzed the influence of the four main factors of recirculating water flow, mechanical aeration, surface reaeration and respiration of shrimp on the dynamic changes of DO, and established a DO system dynamics model in the recirculating aquaculture system. Based on the established model, this paper proposed a fuzzy rule-optimized single neuron adaptive PID controller (FL-SN-PID) for precise control of DO. In order to verify the reliability of the established model, several aeration experiments with different aeration flows were conducted in Simulink and actual breeding system. All fitting R2 between simulated data and measured data of the DO response are above 0.94, indicating that the established dynamics model can accurately approximate the actual breeding system and can provide a basis for the design of the controller. In the simulation experiment, the proposed controller was applied to the DO tracking control in three scenarios, and its tracking performance was also compared with the traditional PID controller and the SN-PID controller. In performance analysis, the integral of absolute error (IAE) and the integral of squared error (ISE) of the FL-SN-PID controller are obviously smaller than the other two controllers, indicating this controller has better control accuracy and robustness, and can be competent for precise control of DO in aquaculture.
      原文链接:
    • NSTL
    • Elsevier

    Thermal and digital imaging information acquisition regarding the development of Aspergillus flavus in pistachios against Aspergillus carbonarius in table grapes

    Mastodimos N.Tsitsigiannis D.I.Lentzou D.Templalexis C....
    13页
    查看更多>>摘要：? 2021 Elsevier B.V.The phenotypic diagnostics in food mycology exhibit hysteresis in fungal detection during the early stages since hyphal and fruiting structures become visible only in advanced growth stage. Aspergillus flavus is a saprotrophic and pathogenic fungus colonizing cereal grains, legumes, and tree nuts. This fungus produces significant quantities of aflatoxins which have nephrotoxic, hepatotoxic, teratogenic and immunosuppressive effects on humans. The spatial temperature heterogeneity of A. flavus in infected pistachios was assessed by means of thermal imaging along with the digital RGB imaging analysis. The image analysis in terms of hue angle, exhibited not significant variation of non-infected pistachios compared to the infected ones at the early stages of fungal invasion but it became significantly different 72 h since infection. The fungal growth rate was assessed by comparing the Weibull shape factor of pistachios inoculated with A. flavus against grapes inoculated with A. carbonarius. The latter showed that the first 6 h since inoculation showed similar growth rate (?βˉ/?t=6.7) while between 6 and 20 h showed lesser but almost double growth rate of the infected grapes (?βˉgrapes/?t=5.4) against the infected pistachios (?βˉpistachios/?t=2.2). Infected pistachios and grapes were both stored at 28 °C and 60% RH, hence, the noted variation in growth rate should be fungus and substrate dependent. The peak of the temporal variation of the Weibull shape factor in pistachios and grapes extends between 15 and 20 h since inoculation, while for the infected grapes it is 71% higher than the one of the infected pistachios, revealing a distinctive fungal growth rate.
      原文链接:
    • NSTL
    • Elsevier

    An automatic phytopathometry system for chlorosis and necrosis severity evaluation of asian soybean rust infection

    da Silva D.A.Oliveira Nogueira A.P.Hamawaki C.L.Santos Nascimento L.D....
    11页
    查看更多>>摘要：? 2021 Elsevier B.V.The development of soybean cultivars resistant to Phakopsora pachyrhizi (also known as Asian Soybean Rust (ASR)) may be achieved through genetic breeding. In the stage of selecting the resistant genotypes, one factor that can be used is to observe visually the severity of the rust symptoms upon leaflets of sampled soybean plants. By being able to quantify the exact amounts of regions with chlorosis, necrosis, and unaffected of each sample an automatic method is developed to grade rust severity and to classify the samples accordingly. The proposed approach uses input images of soybean leaflets, in a range from healthy to different levels of ASR severity, sampled from controlled experiments in a farm in southeast Brazil. Images are then processed by channel transformation (RGB to CIELab), channel distribution analysis, and a clustering algorithm in order to segment the regions in three main areas. Those regions represent the main visual symptoms of the ASR severity, but still with ill-defined transitions between them. A post-processing superpixel algorithm is leveraged upon those results to arrive at a first rust intervals classification. A necrosis’ neighborhood analysis is proposed to compute the intermediate areas and to include them in a final rust index. Results are given upon four different experiments: 1) 200 acquired image samples taken directly from the field; 2) 67 detached leaflets at different evolved periods of infection; 3) 50 images from a previous open database, and 4) 10 images with the standards for diagrammatic scales. By grading rust severity, and separating chlorosis, and necrosis indexes this solution contributes to efforts in managing ASR in crops, and in breeding programs.
      原文链接:
    • NSTL
    • Elsevier

    Early detection and classification of fungal infection in garlic (A. sativum) using electronic nose

    Chayjan R.A.Ahmadi E.Zafari D.Makarichian A....
    10页
    查看更多>>摘要：? 2021 Elsevier B.V.Garlic (Allium sativum) is an important crop with numerous benefits and uses. This plant is highly exposed to various pathogenic factors, including fungi. Fungi are the most distinct group responsible for planting diseases the loss involved. In this respect, detection of fungal pathogens infection in the early stages is a major challenge in food security to minimize losses as much as possible. Aroma investigation to detect fungal pathogens infection has been widely welcomed in this regard. In the present study, an electronic nose (E-nose) is utilized as a non-destructive and fast method for early detection of fungal infection on garlic that was synthetically infected with Fusariumoxysporum f. sp. Cepae (FU), Alternariaembellisia (syn. Embellisiaallii) (AL), and Botrytis allii (BO). Statistical analyses including ANOVA, PCA, LDA, SVM, and BPNN were employed to evaluate the aroma profile obtained by the E-nose. According to the obtained results, degradation occurs more quickly in the presence of infection. Due to the different destructive effects of each type of infection, the response changes of each sensor toward the aroma of various infection treatments were not the same. Thus, the E-nose can be used as a practical and beneficial tool to detect fungal infection on garlic in the early stages.
      原文链接:
    • NSTL
    • Elsevier

    Estimation of biomass and nutritive value of grass and clover mixtures by analyzing spectral and crop height data using chemometric methods

    Sun S.Cen H.He Y.Li X....
    10页
    查看更多>>摘要：? 2021 Elsevier B.V.The study aims to estimate forage yield and quality parameters by fusing field spectroscopy data and crop height with regression-based mathematical models. Field experiments were carried out to obtain canopy spectral reflectance (CSR) of grass and clover mixtures. Additionally, grass height (Hgrass) and clover height (Hclover) were used as auxiliary explanatory variables with CSR to estimate forage yield and quality. Variable importance in projection (VIP) was utilized for sensitive wavelength selection. Two chemometric methods, namely partial least squares regression (PLSR) and support vector machine (SVM), were implemented to build models using full spectra and sensitive wavelengths for estimating dry matter yield (DMY), in vitro true digestibility (IVTD), neutral detergent fiber (NDF), neutral detergent fiber digestibility (NDFD), acid detergent fiber (ADF), acid detergent lignin (ADL), crude protein (CP), crude protein yield (CPY), and botanical composition (BC). Of the total 235 samples, 157 samples were randomly selected for model calibration while the remaining 78 samples were used for model validation. Results showed that both PLSR and SVM could reasonably estimate forage yield and quality variables, although performances of PLSR were more stable in terms of R2 and relative root mean square error (RRMSE) for both calibration and validation. Prediction performances of models using only full spectra data (PLSRspec) and models also using crop height information (PLSRspec+H) as model inputs were compared in this study. PLSRspec+H presented higher R2 and lower RRMSE than PLSRspec models (e.g. R2 improved from 0.83 to 0.90 for NDF and from 0.56 to 0.73 for IVTD, and RRMSE decreased from 8.14% to 6.58% for NDF and from 2.55% to 2.02% for IVTD). In addition, PLSR that used sensitive wavelengths and crop height (PLSRwave+H) as model inputs also had good performance, although slightly worse than PLSRspec+H. The results suggest that there is good potential to predict forage biomass and nutritive value by combining spectral and height variables with chemometric methods.
      原文链接:
    • NSTL
    • Elsevier

    Exploring the superiority of solar-induced chlorophyll fluorescence data in predicting wheat yield using machine learning and deep learning methods

    Liu Y.Wang S.Wang X.Chen B....
    11页
    查看更多>>摘要：? 2021 Elsevier B.V.Reliable forecasts of large-scale wheat yield are very important for global food security. Although solar-induced chlorophyll fluorescence (SIF) is more sensitive than traditional remotely sensed vegetation indices to photosynthetic capacity, the performance of SIF in wheat yield prediction should be further explored. In this study, five satellite variables (i.e., Global Ozone Monitoring Experiment-2 (GOME-2) SIF at 0.5° spatial resolution, global spatially contiguous SIF (CSIF) at 0.05° resolution, and three vegetation indices at 1 km resolution) from 2007 to 2018 were used to predict wheat yield using two linear regression methods (least absolute shrinkage and selection operator regression (LASSO) and ridge regression (RIDGE)), three machine learning methods (support vector regression (SVR), random forest regression (RF), and extreme gradient boosting (XGBoost)), and one deep learning method (long short-term memory (LSTM)) to predict wheat yield across the Indo-Gangetic Plains. The results showed that machine learning and deep learning methods outperformed the two linear regression methods in predicting wheat yield, while the LSTM did not perform better than SVR. The prediction using the high-resolution SIF product had better performance than that using the coarse-resolution SIF product among all years. Moreover, the high-resolution SIF had better performance than the three vegetation indices in yield prediction in 2010, which indicated that the SIF data had great superiority in predicting wheat yield under extreme weather events. Our findings highlight that developing high-quality SIF products in the future has the potential to improve crop yield predictions, and our method can predict wheat yield simply and effectively in cropping areas with limited data.
      原文链接:
    • NSTL
    • Elsevier

    Improving estimation of LAI dynamic by fusion of morphological and vegetation indices based on UAV imagery

    Qiao L.Gao D.Zhao R.Tang W....
    12页
    查看更多>>摘要：? 2021 Elsevier B.V.As an important indicator reflecting plant growth and canopy structure, accurate and rapid monitoring of the leaf area index (LAI) is very important for modern precision agriculture. The purpose of this study is to explore the potential of fusion of morphological information and spectral information in multiple growth periods of maize to improve the accuracy of LAI dynamic estimation. The multi-spectral sensor carried by the unmanned aerial vehicle (UAV) was used to collect remote sensing images of the maize canopy during the six growth stages. Three morphological parameters (canopy height, canopy coverage, and canopy volume) and two vegetation indices (normalized vegetation index (NDVI) and visible atmospheric vegetation index (VARI)) were extracted from image information and spectral information, respectively, and a LAI estimation model was constructed based on parameters fusion. The results showed that the morphological parameters and vegetation indices had the same time distribution law as LAI, and could be used to monitor crop LAI. At the same time, the study found that the fusion of canopy height, canopy coverage and canopy volume could further characterize the external morphological changes of crops and improved the accuracy of LAI dynamic estimation based on morphology, but there were still limitations in the seedling and milk stages. Furthermore, the fusion of canopy morphological parameters and vegetation indices could further improve the dynamic estimate accuracy of maize LAI, and showed better performance in all growth stages (Seedling stage: Rv2 = 0.688, RMSEP = 0.0493; Jointing stage: Rv2 = 0.860, RMSEP = 0.0847; Tasseling stage: Rv2 = 0.780, RMSEP = 0.1829; Silking stage: Rv2 = 0.794, RMSEP = 0.1981; Blister stage: Rv2 = 0.793, RMSEP = 0.1584; Milk stage: Rv2 = 0.708, RMSEP = 0.1396; All: Rv2 = 0.943, RMSEP = 0.2618). The results show that the fusion of image information and spectral information can improve the estimation accuracy of crop LAI and provide a feasible method for crop growth information monitoring based on UAV platform.
      原文链接:
    • NSTL
    • Elsevier

    Machine learning-based farm risk management: A systematic mapping review

    Ghaffarian S.van der Voort M.de Mey Y.Valente J....
    17页
    查看更多>>摘要：? 2021 The Author(s)Farms face various risks such as uncertainties in the natural growth process, obtaining adequate financing, volatile input and output prices, unpredictable changes in farm-related policy and regulations, and farmers‘ personal health problems. Accordingly, farmers have to make decisions to be prepared for such situations under risk or mitigate their impacts to maintain essential functions. Increasingly, a data-driven perspective is warranted where machine learning (ML) has become an essential tool for automatic extraction of useful information to support decision-making in farm management as well as risk management. ML's role in farm risk management (FRM) has recently increased with advances in technology and digitalization. This paper provides a literature review in the form of a systematic mapping study to identify the publications, trends, active research communities, and detailed reviews on the use of ML methods for FRM. Accordingly, nine research/mapping questions are designed to extract the required information. In total, we retrieved 1819 papers, of which 746 papers were selected based on the defined exclusion criteria for a detailed review. We categorized the studies based on the addressed risk types (e.g., production risk), assessments that addressed risk components (e.g., resilience), used ML types (e.g., supervised learning) and algorithms ranging from regression modeling to deep learning, addressed ML tasks (e.g., classification), data types (e.g., images), and farm types (e.g., crop-based farm). The results reveal that there is a significant increase in employing ML methods including deep learning and convolutional neural networks for FRM in recent years. The production risk and impact/damage assessment are the most frequently addressed risk type and assessment that addressed risk components in ML-FRM, respectively. In addition, research gaps and open problems are identified and accordingly insights and recommendations from risk management and machine learning perspectives are provided for future studies including the need for ML methods for different risk types (e.g., financial risk), assessments addressing different risk components (e.g., resilience assessment), and developing more advanced ML methods (e.g., reinforcement learning) for FRM.
      原文链接:
    • NSTL
    • Elsevier