基于卷积神经网络的沙丘形态自动分类方法

为探究沙丘形态数据集构建及自动分类方法,解决沙丘形态信息数据库缺失等问题,以内蒙古西部典型沙丘为研究对象,通过无人机正射影像技术采集6种典型沙丘形态数据,并结合GF-2号遥感数据采用数据增强方式构建沙丘形态数据集。通过迁移学习策略的VGGNet和ResNet模型对沙丘形态的深层语义特征进行解析与学习,自动获取更具有代表性的图像纹理特征,以此提出一种基于卷积神经网络(CNN)提取不同沙丘形态特征自动分类的方法。结果表明,基于迁移学习的VGG16模型在四种模型中分类准确率最高,达到88.14%;优化后的ResNet18模型与ResNet50模型的分类精度分别从84.04%、85.25%提升到92.79%、88.91%;优化后的ResNet18+模型表现出最佳的分类效果,准确率达到92.79%,更适用于沙丘形态的高精度自动分类。     

基于卷积神经网络的昆虫和杂草标本智能全维识别方法初探

本文应用卷积神经网络技术研发了有害生物全维形态特征库和识别模型,采用激光合成干涉成像技术对100种昆虫和杂草标本进行全维高清特征进行信息获取,并进行全维整体轮廓特征和局部形态学特征识别。经过深度学习后测试识别结果,整理统计后得出该模型算法识别标本的正确率在86%～98%范围内,识别的正确率随着学习训练的样本数量增多而提高。表明卷积神经网络模型对标本的学习能力较好,利用全维立体识别技术对昆虫和杂草的鉴定具有可行性。     

基于图像处理的玉米叶片含水率诊断方法研究

研究了利用数字图像处理技术进行作物叶片含水率诊断的方法.以温室中培育的90株不同灌水量的盆栽玉米为研究对象,使用佳能IXUS110的1 210万像素数码相机采集离体抽穗期玉米叶片的图像信息,然后利用烘干法测量叶片样本的含水率;利用叶片图像的灰度直方图提取叶片图像的均值、峰态、方差、歪斜度、能量、熵六组特征值.利用提取的20组玉米叶片样本的数据,采用线性回归的方法建立均值与玉米叶片含水率之间的关系模型;使用其余20组样本对模型进行验证,其标准差为0.021.结果表明,利用作物叶片灰度直方图均值参数可以对玉米的叶片含水率进行预测.     

小麦苗期叶片发黄的诊断与防治

小麦是郧西县主要粮食作物,小麦苗期叶片发黄是生产实践中普片现象。根据近几年田间调查总结分析,小麦苗期叶片发黄主要有病害、虫害、药害及生理性缺素引起的生理性发黄。本文针对不同情况提出防治方法。     

基于小波神经网络和BP神经网络的麦蚜发生期预测对比

为建立更准确、稳定的病虫害预测预报模型,减少农作物病虫害损失、提高农作物产量与质量,运用主成分分析法从42个基础气象因子中整合形成8个新的自变量输入模型,采用试凑法对网络关键参数进行筛选,用2002-2011年数据进行网络训练,建立了以Morlet小波函数为传递函数的小波神经网络模型,并与以Sigmoid函数为传递函数的BP神经网络模型进行了比较.在小波神经网络训练过程中,有6年拟合精度在90％以上,平均拟合精度为89％,预测结果MAPE值为4.1939,MSE值为5.9764;在BP神经网络的训练过程中,有4年拟合精度超过90％,平均拟合精度仅为81.07％,预测结果中MAPE值为6.4694,MSE值为8.2457.从训练结果看,小波神经网络更能准确描述麦蚜发生期的变化规律,其拟合能力较BP神经网络好;从预测精度和模型的稳定性来看,小波神经网络好于BP神经网络.     

基于人工智能的作物病害识别研究进展

传统依靠人工经验的作物病害识别方式难以适应大规模种植环境,迫切需要寻求新的解决方案。近年来,人工智能技术在许多领域取得了丰硕成果,在作物病害识别领域也取得较好的效果。为深入了解人工智能技术在作物病害识别领域中的研究现状,该文主要从传统的机器学习方法和深度学习方法2个角度分析人工智能技术在作物病害识别领域的研究进展,主要包括这2种方法的技术理论、主要工作流程、应用现状及优缺点,同时展望了人工智能技术在未来作物病害识别领域的发展趋势。     

老瓜区西瓜病害的诊断

连江县丹阳镇是福州市西瓜主要产区,从1985年开始种植西瓜,至今有26年种瓜历史,由于瓜地连年重茬连作,各种病害发生严重,给瓜农造成极大损失。根据病因,西瓜病害分为两大类:一类是由真菌、细菌、病毒、线虫等生物因子引起的病害,这类病害可以传染,称为侵染性病害;另一类是     

基于多个高光谱参数的玉米叶片叶绿素含量估测模型

采用Field Spec Pro3光谱仪和SPAD-502叶绿素仪分别测定玉米叶片的光谱与其相对应的叶绿素含量,通过分析红边位置、蓝边位置以及绿峰位置等高光谱参数与叶绿素含量的关系,建立叶绿素含量的单、双和多变量光谱预测模型。结果表明:在可见光区域,玉米叶绿素含量高,光谱反射率低,而进入近红外区则刚好相反,叶绿素含量高,光谱反射率高;红边位置、绿峰位置及蓝边位置各高光谱参数与叶绿素含量的相关性均达极显著。其中红边位置与叶绿素含量的相关性最高,相关系数达0.84;利用所选的3个高光谱参数分别建立的单、双以及三变量模型,虽然大多数模型的精度R~2大于0.71,但分析对比得出利用红边、蓝边及绿峰位置3个变量建立的模型具有最大模型精度R~2、最小标准误差(S)和均方根误差(RMSE),因此其模型预测能力较优。     

基于BP神经网络的太阳辐射预测——以兰州市为例

采用常规气象观测资料建立了兰州市太阳总辐射BP神经网络预测模型,利用神经网络释义图和连接权法剔除了模型中的冗余变量,用优化的BP网络模型预测了兰州市1996-2000年的太阳辐射,并用实测数据验证了该模型。结果表明:该方法增加了模型的透明度,提高了模型的可靠性和鲁棒性,模拟结果与实测值非常吻合,模拟值的各项误差指标值均很小,模拟值与实测值的拟合优度R2达到0.987,通过与其他经验模型的模拟结果进行对比,优化的BP网络模型的模拟效果最好,精度明显高于其它经验模型。因此,对于无太阳辐射观测的地区,优化后的BP网络模型是预测当地太阳辐射的一种有效方法。     

基于混合蛙跳算法优化PCNN的马铃薯病害图像分割

为优化马铃薯病斑图像特征提取与病害识别的关键步骤——图像分割的精度,保证分割后的图像能够较好地保留原病斑图像的轮廓与细节,采用混合蛙跳算法优化脉冲耦合神经网络(pulse coupled neural network,PCNN)参数,建立一种高精度的用于马铃薯病斑图像分割的混合蛙跳算法(shuffled frog leaping algorithm,SFLA)-PCNN模型,该模型选用图像分割香农熵与图像分割紧凑度的加权和作为适用度函数,对马铃薯晚疫病害图像进行试探分割,分割正确率为95.41%,实现PCNN参数的自适应优化配置,并获得PCNN参数配置方案为:神经元交互连接系数β=0.38、脉冲激励衰减系数a_θ=0.24、激励脉冲幅度衰减系数V_θ=0.82。利用优化后的PCNN对马铃薯软腐病、环腐病、银腐病、粉痂病、灰霉病5种病害图像进行分割,分割正确率分别为94.41%、95.69%、93.89%、93.91%和93.21%,平均正确率为94.42%,证明SFLA-PCNN模型能有效地从背景区域提取马铃薯病斑,可用于马铃薯病斑检测。     

Image recognition and empirical application of desert plant species based on convolutional neural network

In recent years, deep convolution neural network has exhibited excellent performance in computer vision and has a far-reaching impact. Traditional plant taxonomic identification requires high expertise, which is time-consuming. Most nature reserves have problems such as incomplete species surveys, inaccurate taxonomic identification, and untimely updating of status data. Simple and accurate recognition of plant images can be achieved by applying convolutional neural network technology to explore the best network model. Taking 24 typical desert plant species that are widely distributed in the nature reserves in Xinjiang Uygur Autonomous Region of China as the research objects, this study established an image database and select the optimal network model for the image recognition of desert plant species to provide decision support for fine management in the nature reserves in Xinjiang, such as species investigation and monitoring, by using deep learning. Since desert plant species were not included in the public dataset, the images used in this study were mainly obtained through field shooting and downloaded from the Plant Photo Bank of China (PPBC). After the sorting process and statistical analysis, a total of 2331 plant images were finally collected (2071 images from field collection and 260 images from the PPBC), including 24 plant species belonging to 14 families and 22 genera. A large number of numerical experiments were also carried out to compare a series of 37 convolutional neural network models with good performance, from different perspectives, to find the optimal network model that is most suitable for the image recognition of desert plant species in Xinjiang. The results revealed 24 models with a recognition Accuracy, of greater than 70.000%. Among which, Residual Network X_8GF (RegNetX_8GF) performs the best, with Accuracy, Precision, Recall, and F1 (which refers to the harmonic mean of the Precision and Recall values) values of 78.33%, 77.65%, 69.55%, and 71.26%, respectively. Considering the demand factors of hardware equipment and inference time, Mobile NetworkV2 achieves the best balance among the Accuracy, the number of parameters and the number of floating-point operations. The number of parameters for Mobile Network V2 (MobileNetV2) is 1/16 of RegNetX_8GF, and the number of floating-point operations is 1/24. Our findings can facilitate efficient decision-making for the management of species survey, cataloging, inspection, and monitoring in the nature reserves in Xinjiang, providing a scientific basis for the protection and utilization of natural plant resources.     

Identification of tea foliar diseases and pest damage under practical field conditions using a convolutional neural network

Lesions of tea (Camellia sinensis) leaves are detrimental to the growth of tea crops. Their adverse effects include further disease of tea leaves and a direct reduction in yield and profit. Therefore, early detection and on-site monitoring of tea leaf lesions are necessary for effective management to control infections and prevent further yield loss. In this study, 1,822 images of tea leaves with lesions caused by three diseases (brown blight, Colletotrichum camelliae; blister blight, Exobasidium vexans; and algal leaf spot, Cephaleuros virescens) and four pests (leaf miner, Tropicomyia theae; tea thrip, Scirtothrips dorsalis; tea leaf roller, Homona magnanima; and tea mosquito bug, Helopeltis fasciaticollis) were collected from northern and central Taiwan. A faster region-based convolutional neural network (Faster R-CNN) was then trained to detect the locations of the lesions on the leaves and to identify the causes of the lesions. The trained Faster R-CNN detector achieved a precision of 77.5%, recall of 70.6%, an F1 score of 73.91%, and a mean average precision of 66.02%. An overall accuracy of 89.4% was obtained for identification of the seven classes of tea diseases and pests. The developed detector could assist tea farmers in identifying the causes of lesions in real time.     

基于相空间重构与RBF神经网络模型的面上干旱预测研究

条件植被温度指数(VTCI)是一种适合关中平原的近实时定量化的干旱监测方法,在前期基于以旬为单位的VTCI样本点上相空间重构与RBF神经网络干旱预测研究的基础上,进一步进行了VTCI遥感面上的干旱预测研究。通过分析样本点VTCI时间序列的延迟时间和重构维数,确定整个面上VTCI时间序列相空间维数为7,从而对面上VTCI数据进行了相空间重构。对重构后的VTCI数据应用RBF神经网络模型预测得到了2009年4月上旬到5月中旬的VTCI预测结果。结果表明,多旬预测结果都较好地反映了监测结果的特征,各旬预测结果的绝对误差频数分布主要集中在-0.2到0.2之间。应用Kappa系数评价预测结果与监测结果的一致性程度：5月中旬为显著,4月上旬和中旬为中度,4月下旬和5月上 旬的一致性为弱,但阳性一致率较高。该模型的面上预测精度较好,适合关中平原的干旱预测研究。     

Diagnosis of plant diseases using the Nanopore sequencing platform

Reliable detection and identification of plant pathogens are essential for disease control strategies. Diagnostic methods commonly used to detect plant pathogens have limitations such as requirement of prior knowledge of the genome sequence, low sensitivity and a restricted ability to detect several pathogens simultaneously. The development of advanced DNA sequencing technologies has enabled determination of total nucleic acid content in biological samples. The possibility of using the single-molecule sequencing platform of Oxford Nanopore as a general method for diagnosis of plant diseases was examined. It was tested by sequencing DNA or RNA isolated from tissues with symptoms from plants of several families inoculated with known pathogens (e.g. bacteria, viruses, fungi, phytoplasma). Additionally, samples of groups of 200 seeds containing one infected seed of each of two or three pathogens, as well as samples with symptoms but unidentified pathogens were tested. Sequencing results were analysed with Nanopore data analysis tools. In all the inoculated plants, pathogens were identified in real time within 1–2 h of running the Nanopore sequencer and were classified to the species or genus level. DNA sequencing or direct RNA sequencing of samples with unidentified disease agents were validated by conventional diagnostic procedures (e.g. PCR, ELISA, Koch test), which supported the results obtained by Nanopore sequencing. The advantages of this technology include: long read lengths, fast run times, portability, low cost and the possibility of use in every laboratory. This study indicates that adoption of the Nanopore platform will be greatly advantageous for routine laboratory diagnosis.     

辽宁省药用植物白鲜病害种类调查及病原鉴定

白鲜为我国传统药用植物,具有较高的经济价值和药用价值,近年来在辽宁省大面积人工种植。为明确白鲜主要病害种类及发生危害情况,2018年-2020年生长季在辽宁省本溪、清原和西丰等主要种植地区进行了病害系统调查。调查和鉴定结果发现,危害白鲜生产的主要病害有5种,分别为由Phoma dictamnicola引起的茎点霉叶斑病、由Paracercospora dictamnicola引起的灰斑病、由Rhizoctonia solani引起的立枯病、由Fusarium oxysporum引起的根腐病和由Meloidogyne hapla引起的根结线虫病,并对各病害症状进行了详细描述。其中茎点霉叶斑病、灰斑病和立枯病分布广且危害较重,病害种类和发病情况地区间差异较大。立枯病主要发生在一年生育苗田,病株率一般为0.6%～19.0%,灰斑病和茎点霉叶斑病主要发生在生产田,病株率分别为38.2%～100.0%和17.6%～99.0%。研究结果将为白鲜病害的准确识别诊断及综合防控策略制定提供科学依据。     

BP神经网络方法在土壤墒情预测中的应用

利用多年实测土壤水分资料和气象资料,建立了考虑多个因素如:外界气象因素及土壤特性、作物生长等对土壤墒情影响的BP人工神经网络模型。应用结果表明:所建立的模型具有较好的预测效果;用BP人工神经网络建立土壤墒情预测模型的方法是可行的。     

基于深度学习人工神经网络的青椒调亏灌溉水量预测

在2014—2018年,采用垄沟集雨覆盖种植滴灌技术与调亏灌溉技术相结合（MFR-RDI）对青椒进行试验研究,选取灌溉水利用效率最高的试验处理（即青椒结果后期重度亏水）进行灌水量预测。根据试验期间搜集的各项资料,在MFR-RDI种植方式下,以作物需水量、青椒生育期天数、作物生育期内的降水量、土壤含水率、前一天的灌水量作为模型输入因子,构建青椒作物灌水量的深度学习人工神经网络（DNN）预测模型。通过模型试验得到最佳DNN预测模型,该模型的隐含层包括4层,各隐含层神经元个数分别为：32、16、8、4。模型的激活函数采用“ReLU”,优化函数为“adam”,迭代次数为300。模型使用2018年的数据进行了测试。测试结果表明DNN模型的RMSE为0.898 mm,MAE为0.257 mm,NS为0.758,R²为0.7635,说明该预测模型具有较高的精度性能。通过预测结果可以得到此种植方式下青椒的灌溉制度,为实现高效智能节水灌溉提供参考。     

植原体引起雪花木小叶病在中国的首次报道

2022年首次在广州市发现园林植物雪花木小叶病病株, 采用分子生物学技术对其进行植原体的种类鉴定。以雪花木叶片总DNA为模板, 利用植原体16S rRNA通用引物P1/P7进行PCR扩增, 获得广东雪花木小叶病植原体(BLL-GD2022)16S rRNA基因片段(1 811 bp, GenBank登录号为OQ625536)。16S rRNA序列相似性显示, BLL-GD2022与16SrVI组植原体株系的相似性最高, 为97.05%~99.83%, 其中与隶属于16SrVI-D亚组的10个植原体株系相似性为99.21%~99.83%。系统进化分析显示, BLL-GD2022与16SrVI组各植原体株系聚类在一个大分支, 其中与16SrVI-D亚组成员聚类在一个小分支, 亲缘关系最近。基于16S rRNA序列的iPhyClassifier限制性内切酶虚拟RFLP分析表明, BLL-GD2022与16SrVI-D亚组的参考株系Brinjal little leaf phytoplasma (GenBank登录号为X83431)的酶切图谱一致, 相似系数为1.00。基于上述研究结果, 明确广州市雪花木小叶病植原体隶属16SrVI-D亚组成员。本研究首次在园林植物雪花木上检测到植原体, 通过16S rRNA序列分析明确为16SrVI-D亚组成员, 为开展16SrVI-D亚组植原体在蔬菜、花卉和园林植物的发生监测及病害防控提供科学依据。