基于多尺度特征提取深度残差网络的水稻害虫识别

【目的】在水稻生产过程中,针对不同虫害需要采用不同的防治方案,水稻害虫的准确识别分类是制定针对性防治方案的前提。【方法】采用深度学习结合机器视觉的方法,基于Res2Net结构提出了一种多尺度特征提取的深度残差网络,通过准确地提取害虫特征实现复杂自然背景下的水稻害虫识别;采用改进的残差结构,使用等级制的类残差连接取代了原本的3×3卷积核,增加了每个网络层的感受野,可以更细粒度地提取多尺度特征。【结果】本网络训练的模型能够有效地识别自然背景下的水稻害虫,在自建的包含22类常见水稻害虫的图像数据集上,平均识别准确率达到了92.023%,优于传统的ResNet、VGG等网络。【结论】本文提出的模型可应用于水稻虫情自动监测系统,为实现水稻害虫虫情的机器视觉监测提供参考。     

Spatial patterns of fire occurrence in Catalonia,NE, Spain

In this paper, we analyse spatial patterns of fire occurrence in Catalonia (NE Spain) during 1975–98. Fire scar maps, discriminated by means of 30–60 m resolution remote sensing imagery, have been used as a source of fire occurrence. We employ several visual or analytical approaches to interpret fire occurrence in this region, such as those of Minnich and Chou (1997), Ricotta et al. (2001) or Krummel et al. (1987). Crucial spatial patterns such as fire size distribution, fire frequency distribution, spots and residual vegetation islands are documented. In addition, several geographical layers were overlaid with burned area maps in order to determine interactions between fire occurrence and environmental parameters such as altitude, slope, solar radiation, and burned land cover. Assuming that fire occurrence is well determined by such a posteriori empirical factors we detect areas most prone to fire in this region and aim to enhance the local forest management and conservation plans.     

The image recognition of urban greening tree species based on deep learning and CAMP-MKNet model

The information of urban tree species resources is of vital significance to the planning and design of urban green spaces. Tree organs, such as the bark are used as the primary features of identifying tree species. However, traditional tree identification methods need to consume a lot of manpower and time costs. In addition, the application of machine image recognition technology to tree species recognition still has problems such as heavy data preprocessing workload, small number of tree species images, uneven distribution of categories, and low recognition accuracy. In order to promote the intelligent management of urban forestry and solve the above problems, it is necessary to establish an automatic image recognition model for urban greening tree species. We captured bark images of 21 urban afforestation tree species in their natural environment and constructed a dataset that was divided into a train set, validation set, and test set in the ratio of 7:1:2. Combining Channel Attention Module (CAM) with algorithms such as Spatial Pyramid Pooling (SPP) and Mixed Depthwise Dilated Convolutional Kernels. The core algorithm is Mixed Convolution Kernel (MK), and a CAMP-MKNet Convolutional Neural Network (CNN) is constructed as a bark image classification model for urban greening tree species. The overall accuracy of the generic models ranged from 41.06% to 82.03%, whereas the overall accuracy of the experimental CAMP-MKNet model was 84.25%, with lower prediction cost. Our study shows that the CAMP-MKNet CNN model with better prediction performance and computational cost and can provide crucial insights and technical support for developing automated urban tree species image recognition systems.     

冻烤鳗抗生素残留量微生物分析法

本文叙述了农业部1997年批准的中华人民共和国冻烤鳗水产行业标准中以纸片扩散法检测烤鳗样品中抗生素残留量的原理,操作方法,最低检出量和对30份烤鳗样品的检验结果。同时探讨了制定烤鳗抗生素残留量的质量标准和检测方法的思路。     

Evaluation of thiacloprid and clothianidin (neonicotinoids) as alternative to fenthion (organophosphate) for control of Mediterranean fruit fly (Diptera: Tephritidae) in deciduous fruit orchards

Fenthion (organophosphate) was used in Australia to target adults, eggs and larvae of Mediterranean fruit fly (Medfly), Ceratitis capitata Wiedmann (Diptera: Tephritidae) in deciduous fruits. With its removal from use in 2015, clothianidin and thiacloprid (neonicotinoids) were evaluated for any adulticide, ovicide or larvicide (eggs, larvae) activity against Medfly in a series of laboratory and field-cage experiments in peach and nectarine. We included fenthion in all experiments as a positive control. As an adulticide, fenthion had the greatest residual toxicity on fruit, with 7 d old residues killing 44% of adults within 48 h compared to thiacloprid (17%) and clothianidin (30%). When applied as a larvicide to naturally infested peaches, none of the insecticides was 100% effective, though fewest pupae (1.18 ± 0.19 pupae/fruit) (indirect measurement of larval survival) were produced when treated with fenthion, followed by clothianidin (3.40 ± 0.33 pupae/fruit) and thiacloprid (6.88 ± 0.34 pupae/fruit); with 11.35 ± 0.30 pupae/fruit in control (water). In peaches treated 48 h post-infestation, fenthion was most effective in reducing numbers of pupae and adult emergence and with higher percentage of deformed adults, with thiacloprid=clothianidin. In nectarines treated 48 h post-infestation, fenthion was most effective in reducing numbers of pupae and adult emergence as well as with higher percentage of deformed adults, followed by clothianidin. Insecticides were least effective when applied as a preventative 24 h or 7 d prior to infestation, with fenthion more effective than clothianidin. Whilst our study shows that neither clothianidin nor thiacloprid are equivalent to fenthion, they are acceptable substitutes to growers for use for Medfly in deciduous fruits given that fenthion is no longer available to growers in Australia. We recommend that growers incorporate other controls to target the adult stage rather than rely only on new insecticides.     

65%桑虫净EC防效及残毒试验

桑园害虫防治应在确保蚕作安全的前提下进行,短残毒农药及其混配使用在生产中常见,但相应的桑园专用农药产品较少.本试验认为65%桑虫净EC对鳞翅目害虫有较好的防效,且残毒期短,适宜在养蚕前或蚕期中使用.     

耕层残膜回收机的研究

地膜覆盖技术已成为农业生产中不可或缺的技术,极大地促进了农业发展和进步。但是农用的塑料薄膜大都是不可分解的,长时间留在土壤里,不但会对作物造成严重的危害,影响作物正常的生长和产量,还会影响机械作业的质量。要在收获庄稼后,及时地回收残膜,避免造成"白色污染"和塑料资源浪费。为此介绍了残膜回收机在国内外的发展现状以及典型的残膜回收机的结构与工作原理,并提出存在的问题和未来的发展建议。     

Comparison of sulfurous acid generator and alternate amendments to improve the quality of saline-sodic water for sustainable rice yields

The prolonged irrigation with marginal quality water can cause secondary salinization of soils, which necessitates for better understanding of water management alternatives. Relative performance of sulfuric acid and gypsum is still controversial to counter sodium hazards in soil/water system. As an alternative, sulfurous acid generators (SAG) are also being marketed. But up-till-now, there is not even a single field study published in scientific journals about their efficiency and economical viability for the treatment of saline-sodic water. Therefore, a field study was carried out to compare the effectiveness of SAG and alternate amendments applied on an equivalent basis to grow rice crop. SAG treatment of saline-sodic tube well water decreased only residual sodium carbonate (RSC) from 5.4 to 3.6 mmol_c l⁻¹, and had no beneficial effect on its sodium adsorption ratio (SAR) or electrical conductivity (EC). All the treatments kept soil EC and SAR around their respective threshold levels. For paddy yield, SAG, sulfuric acid, and gypsum treatments depicted nonsignificant differences. SAG and sulfuric acid treatments of water were about six times expensive than that of gypsum. It was concluded that soil-applied gypsum, to counter sodic hazards of irrigation water, is economical to sustain irrigated rice in dry regions.     

~（15）N标记有机无机氮在莴苣设施土体系中的转化与分配

应用１５Ｎ标记硫铵及稻草，实施了两者单施、配施的盆栽试验。结果表明：施入物料的Ｃ／Ｎ、稻草用量与稻草１５Ｎ的矿化率及吸收利用率呈反相关，与残留率呈正相关；随着施入物料Ｃ／Ｎ及稻草用量的增加，硫铵１５Ｎ的固定率及残留率相应提高，而吸收率则下降。施用占土重０．３１％～０．４６％的稻草，能提高设施土壤的全氮量。     

麦田中绿磺隆残留对水稻的危害

研究了在麦田不同时期 (1 2月 1 1日、1 2月 2 3日、2月 1 3日和 3月 2 6日 )施用不同剂量 (1 2 0、1 5 0、30 0g/hm2 )的 1 0 %绿磺隆 ,其残留对后茬移栽水稻的危害性。结果表明 ,绿磺隆的残留对水稻茎蘖数的影响大于对株高的影响 ,最终导致减产 0 .6%～ 9.0 % ,但不同处理间株高、茎蘖数和产量的差异均未达到显著水平