水肥一体化技术在生姜生产中的应用

为了解决生姜生产中存在的费水、过度施肥、营养失衡、人工投入大、生姜产量低和品质不高的突出问题,本研究把水肥一体化技术和生姜生产实践结合起来,从生姜地块的土壤理化性状检测、设备选择与设计、水源选择、肥料选择以及生姜各生育期的水肥投入方案等方面,阐述了水肥一体化技术在生姜生产中的应用技术要点,形成了具有普遍指导性的水肥一体化技术规范。该技术要点体现了水肥一体化的技术优势,可为各生姜产区的生姜生产、广大农技推广人员农技推广服务和农业领域科研工作者提供技术指导和参考。     

猪群抗应激的营养解决方案综述

应激是动物机体在多种环境、生理和心理等因素的刺激下，出现的生理与心理等全身性的非特异性的适应性反应。随着我国生猪养殖业规模化和集约化程度的提高，养猪生产者都追求以有限的养殖空间来生产更多的猪只，这导致了养殖密度的增加、猪群应激发生的概率不断上升。应激导致的危害日益突出，成为了阻碍猪只健康生长的重要的因素之一。本文回顾了应激的病理学概念、应激的种类与危害、抗应激的营养支持理论；针对应激问题的解决，本文提出了对猪群添加功能性的维生素和氨基酸来的方法，并介绍了该方法在猪场实际应用的案例。     

基于声振信号对称极坐标图像的苹果霉心病早期检测

为实现苹果早期霉心病较高精度的检测，该研究采用对称极坐标法（Symmetrized Dot Pattern，SDP）将苹果声振信号变换为雪花图，然后采用AlexNet、VGG16和ResNet50卷积神经网络以迁移学习方式深度挖掘SDP雪花图像的特征信息，将其输入到支持向量机（Support Vector Machine，SVM）分类器，对霉心程度≤7%的苹果进行检测。研究结果表明，当时间间隔系数为25和角度放大因子为50°时，健康果与早期霉心果声振信号的SDP图形状特征差异最大，在此条件下获取的SDP图经卷积神经网络AlexNet、VGG16和ResNet50提取特征并构建了不同核函数的SVM霉心果检测模型，在各类SVM模型中，ResNet50-SVM-gaus（高斯基）模型用相对较少的训练时间和参数量可取得训练集霉心果较高分类准确率，经超参数优化训练该模型对健康果和早期霉心果测试集不平衡样本（10∶1）的总体分类准确率达到96.97%，平均查准率、平均查全率、平均加权调和均值、Kappa系数和马修斯相关系数值分别为80.19%、90.36%、86.21%，82.54%和82.68%，该模型不仅对多数类的健康果保持较高分类准确率，而且对少数类的早期霉心果也具有较高判别能力。这些研究结果为声振法应用于果蔬内部病害的早期在线检测系统研发提供了技术支撑。     

基于卷积神经网络的拖拉机工况识别

农机工况识别在细化农机作业状态和帮助掌握区域污染物排放趋势方面有着重要的研究价值。基于拖拉机不同运行状态下的行驶速度、发动机转速以及实时油耗等时间序列,首次提出将图像识别方法引入到拖拉机工况识别中的思路,并分别应用参数优化的支持向量机与卷积神经网络对实际作业拖拉机工况进行研究。结果表明:(1)基于参数优化的支持向量机可以较好地实现样本点的工况识别且识别准确度达到99.851 9%,但无法实现农机工况的连续性识别,同时无法对农机工况转换阶段进行有效识别。(2)以拖拉机运行速度与发动机转速等信息构建样本图像来描述农机工况变化的数据表达,并在此基础上应用卷积神经网络可以有效实现农机工况的连续性识别,且识别准确率可以达到93.3%。本研究在农机工况识别方面具有一定参考价值,并为后续农机不同工况下区域污染物排放研究提供技术支持。     

Adoption of improved crop varieties by involving farmers in the e-wallet program in Nigeria

The amount of improved seed used in Nigeria is extremely low. Overall, only 5–10% of cultivated land is planted with improved seeds, and about 10% of rural farmers use improved varieties. The objective of this investigation was to identify determinants of adoption of improved seed by farmers not participating in and those participating in the federal government’s e-wallet program in Nigeria. We determined the impact of the e-wallet program on adoption of improved seed in rural areas. A total of 1200 rural farmers were sampled across six geopolitical zones of Nigeria. Results from the use of a bivariate probit model indicated that the e-wallet program continued to become increasingly popular among rural farmers; and that farmers’ literacy, ownership of a mobile phone, value output, mobile network coverage, power for charging phone batteries and contact with extension agents were the positive determinants of farmer participation in the e-wallet program. Cultural obstacles to married women, growers’ age, and increased distance to registration and input collection centers reduced farmers’ tendency to participate in the e-wallet program. The results also showed that rural farmers depended on the e-wallet program for increased use and adoption of improved seed in Nigeria, to boost food security in sub-Saharan Africa. The results suggested the need for an improved e-wallet model by lessening constraints mostly associated with rural information and communication infrastructure, and distance to the registration and input collection centers.     

多措并举保障北京市昌平区设施草莓优质绿色生产

为了保障草莓的安全生产,打造昌平草莓产业的良性健康发展模式,主要从技术支撑、政府扶持及宣传3个方面阐述了其重要举措。具体措施包括通过注重提升田园清理、土壤消毒、田间管理等一系列技术措施,确保草莓安全生产;通过政府政策、资金支持及专业技术指导,打造强有力的后盾保障;建立绿色安全生产宣传模式,扩大品牌影响力,如多渠道、多方面进行宣传;组织培训,增强种植水平;充分利用互联网新媒体等。     

基于音频技术的肉鸡采食量检测方法研究

【目的】通过研究肉鸡采食音频提出一种基于音频技术的肉鸡采食量检测方法,以摆脱目前我国肉鸡采食量数据主要是人工测量群体采食量的现状,为准确获取肉鸡采食量信息提供技术支持。【方法】录音笔采集到的采食音频经分帧加窗、端点检测等预处理后,将有效声音片段提取出来,依托不同声音的功率谱密度曲线差异,使用单分类支持向量机(OC-SVM)对提取出的有效声音片段进行分类识别。利用音频技术检测肉鸡进食时的啄食次数,分析确定啄食次数与采食量的关系,利用啄食次数与采食量的高相关性计算肉鸡采食量。【结果】利用音频技术检测的肉鸡啄食次数与采食量高度相关,决定系数(R~2)=0.982 5。啄食次数计算正确率为94.58%,采食量计算正确率为91.37%。【结论】该方法可用于肉鸡采食量测定。     

中国出口葱属蔬菜技术性贸易措施状况与对策

分析了葱属蔬菜出口贸易结构、主要贸易国技术性贸易措施状况,阐明了噻虫嗪等农药残留超标为出口遇阻主要原因,结合中国葱属蔬菜产业投入品使用对产品质量影响的分析,提出了促进产业发展的对策建议。     

Comparison of multivariate models and variable selection algorithms for rapid analysis of the chemical composition of field crops

This study evaluates the use of visible and near-infrared spectroscopy for rapid prediction of total carbon, total nitrogen, and total phosphorus concentrations in field crop samples. Two multivariate models (partial least squares regression and support vector machine regression) were compared. In addition, four spectral variable selection algorithms (competitive adaptive reweighted sampling, genetic algorithm, uninformative variable elimination, and variable importance for projection) were applied with support vector machine regression to determine the most accurate predictions. The results showed that support vector machine regression performed better than partial least squares regression for predicting the three chemical compositions. The combination of competitive adaptive reweighted sampling and support vector machine regression outperformed the other models for the predictions of total carbon and total nitrogen with high coefficients of determination of 0.91 and 0.90, respectively. For the determination of total phosphorus, the prediction accuracy of competitive adaptive reweighted sampling was comparable with the best result obtained from genetic algorithm with the coefficients of determination of 0.73 and 0.77, respectively. In conclusion, the support vector machine regression combined with competitive adaptive reweighted sampling has great potential to accurately determine the chemical composition of field crops using the visible and near-infrared spectroscopy.     

福建省高素质农民发展跟踪分析

为反映福建省高素质农民的发展状况,探索高素质农民培育的更有效途径,采用比较分析方法,跟踪调查2015—2018年福建省高素质农民的总量、性别比例、年龄结构、文化程度等数据,并以此为基础,重点分析农业新型经营主体家庭农场经营者、农民合作社负责人等群体的发展情况,同时比较研究福建省高素质农民重点群体之间的发展特点。从文化程度、培育供求、产学矛盾、政策扶持等方面深入剖析当前高素质农民发展的制约因素,从加快推进福建省高素质农民培育工作、构建高素质农民终身学习体系、探索培育新型农业经营模式、推进线上线下融合培育、创设高素质农民扶持政策等方面提出相应的对策建议。