A Review on the Application of Deep Learning Methods in Detection and Identification of Rice Diseases and Pests

In rice production,the prevention and management of pests and diseases have always received special attention.Traditional methods require human experts,which is costly and time-consuming.Due to the complexity of the structure of rice diseases and pests,quickly and reliably recognizing and locating them is difficult.Recently,deep learning technology has been employed to detect and identify rice diseases and pests.This paper introduces common publicly available datasets;summarizes the applications on rice diseases and pests from the aspects of image recognition,object detection,image segmentation,attention mechanism,and few-shot learning methods according to the network structure differences;and compares the performances of existing studies.Finally,the current issues and challenges are explored fromthe perspective of data acquisition,data processing,and application,providing possible solutions and suggestions.This study aims to review various DL models and provide improved insight into DL techniques and their cutting-edge progress in the prevention and management of rice diseases and pests.

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning method.We demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model structure.However,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial obstacle.This issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data security.To address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

Development of an automatic monitoring system for rice light-trap pests based on machine vision

Monitring pest populations in paddy fields is important to effectively implement integrated pest management.Light traps are widely used to monitor field pests all over the world.Most conventional light traps still involve manual identification of target pests from lots of trapped insects,which is time-consuming,labor-intensive and error-prone,especially in pest peak periods.In this paper,we developed an automatic monitoring system for rice light-trap pests based on machine vision.This system is composed of an itelligent light trap,a computer or mobile phone client platform and a cloud server.The light trap firstly traps,kills and disperses insects,then collects images of trapped insects and sends each image to the cloud server.Five target pests in images are automatically identifed and counted by pest identification models loaded in the server.To avoid light-trap insects piling up,a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects.There was a close correlation(r=0.92)between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap.Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.

An Insect Imaging System to Automate Rice Light-Trap Pest Identification

Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast. Identification and counting of rice light-trap pests manually is time-consuming, and leads to fatigue and an increase in the error rate. A rice light-trap insect imaging system is developed to automate rice pest identification. This system can capture the top and bottom images of each insect by two cameras to obtain more image features. A method is proposed for removing the background by color difference of two images with pests and non-pests. 156 features including color, shape and texture features of each pest are extracted into an support vector machine （SVM） classifier with radial basis kernel function. The seven-fold cross-validation is used to improve the accurate rate of pest identification. Four species of Lepidoptera rice pests are tested and achieved 97.5% average accurate rate.

Effects of silicon amendment on the occurrence of rice insect pests and diseases in a field test

Rice is one of the most important staple foods for the world population,but it is attacked by a number of destructive pests.While evidence from greenhouse and laboratory tests has shown that silicon（Si）amendment can confer enhanced resistance to pests in rice,few studies have directly demonstrated the Si-mediated protection from pests in a field situation.In this study,field plots with silicon amendments at 0,75,150 and 300 kg SiO2 ha-1 in early-and late-season rice were employed to evaluate the effects of silicon amendment on the occurrence of major insect pests and diseases and rice yield.Compared with the control plots without silicon amendment,plant damage by stem borer and leaf folder and population size of planthopper were significantly lower in three to five of the seven monitoring observations in each season in the plots amended with 300 kg SiO2 ha-1.The disease index of rice blast in the early-season rice was lower in the plots amended with Si at 300 kg SiO2 ha-1 than in the control plots,while Si protection from rice blast in the late-season rice and from rice sheath blight in the early-season rice were not apparent.An insignificant increase of rice yield by 16.4%（604 kg ha-1）was observed in the plots amended with 300 kg SiO2 ha-1 over the control plots.Our results indicate that Si amendment at 300kg SiO2 ha-1 can provide substantial protection from some of the rice pests under field conditions.These findings support the recommendation of silicon amendment as a key component of integrated management of rice pests.

Effect of Nitrogen Fertilizer on Herbivores and Its Stimulation to Major Insect Pests in Rice

Nitrogen is one of the most important factors in development of herbivore populations. The application of nitrogen fertilizer in plants can normally increase herbivore feeding preference, food consumption, survival, growth, reproduction, and population density, except few examples that nitrogen fertilizer reduces the herbivore performances. In most of the rice growing areas in Asia, the great increases in populations of major insect pests of rice, including planthoppers （Nilaparvata lugens and Sogatella furcifera）, leaffolder （ Cnaphalocrocis rnedinalis）, and stem borers （Scirpophaga incertulas, Chilo suppressalis, S. innotata, C. polychrysus and Sesarnia inferens） were closely related to the long-term excessive application of nitrogen fertilizers. The optimal regime of nitrogen fertilizer in irrigated paddy fields is proposed to improve the fertilizer-nitrogen use efficiency and reduce the environmental pollution.

The Predatory Function of Three Spiders to Two Insect Pests in Rice Within a Multi-species Co-existence System

The prey-seeking behavior of three spiders (X1-Pirata subpiraticus, X2-Clubiona japonicola and X3-Tetragnatha japonica) for brown plant hopper (X4-Nilaparvata lugens) and rice spittle bug (X5-Cal-litettix versicolor) was investigated, as well as how interference between and within species occurred, by using a quadratic regression rotational composite design. Six predation models derived from the analysis of interactions among and within predators and preys were developed. The total predatory capacity of spiders on rice insect pests after coexistence for one day can be expressed as follows: Y3 = 32.795 + 2.25X1 + 1.083X2 + 0.5X3 + 10.167X4 + 3.167X5 - 1.67X12 - 2.42X22 - 3.295X32 - 0.045X42 + 0.455X52 - 3.125X1X2 + 0.375X1X3 -0.625X1X4 - 0.375X1X5 + 0.375X2X3 - 0.875X2X4 + 0.125X2X5 + 0.375X3X4 - 0.375X3X5 + 0.125X4X5. The principal efficiency analysis using this model indicated that increases in insect pest density significantly increased predation by predators; this was much greater than the effect of any single predator. X4 had a greater effect than X5; however, X4 and X5 demonstrated little interspecific interference and even promoted each other and increased predation rates as the densities of the two pests increased. Among the three predators, an increase in the density of X, had the greatest effect on the increase in predation, X3 had the second, X2 the third greatest effect. As predator density increased inter- and intra-species interference occurred, which were largely related to the size, activity, niche breadth, niche overlap and searching efficiency of the predators. X2 produced the greatest interference between different individuals and between any other predator species. X3 had the second greatest, which reduced predation levels at high predator densities. Because of these factors, the highest predation rate was obtained at a prey density of 120 per 4 rice-hills. The optimal proportion of the three predators in the multi-predator prey system was X1: X2: X3 = 5.6:1.3:4.1.

Sustainable Management of Rice Insect Pests by Non-Chemical-Insecticide Technologies in China

Chemical pesticides play crucial roles in the management of crop diseases and pests. However, excessive and irrational use of pesticides has become a major concern and obstacle to sustainable agriculture. As a result, the quality and security of agricultural products are reduced, and the ecological and environmental integrities are threatened. Recently, environment-friendly pest management measures have been introduced and adopted to manage rice insect pests and reduce the use of insecticides. This paper reviewed the advancements in development and application of non-chemical technologies for insect pest management during rice production in China.

水稻害虫:研究进展与展望

水稻是我国主要的粮食作物,病虫害的发生直接威胁水稻生产安全。水稻害虫种类多,灾变机制复杂,绿色防控新技术开发难度大。深入研究水稻害虫的监测和早期预警技术、发育与生殖调控机制、化学通信机制和新型防控技术等,不仅有助于阐明水稻害虫发生灾变机制,还将为害虫综合治理提供新的有效的防控靶点和防控技术。近年来,我国学者在水稻害虫研究领域取得显著进展,在多个研究方向取得重要成果,本专辑汇集了一些最新研究进展。本文概述了目前关于水稻害虫研究的最新进展,介绍了本专辑论文的主要研究内容,并提出了如下值得更深入关注的3个研究方向:(1)水稻害虫智能化监测和早期预警;(2)水稻害虫灾变机制及演变规律;(3)水稻害虫绿色防控靶点挖掘及可持续防控体系构建和应用。

滨海稻区节肢动物天敌种类调查分析

为明确滨海稻区天敌情况,2021~2023年,于滨海稻区调查了水稻节肢类捕食性天敌的种类,结果表明,滨海稻区共捕获水稻节肢类捕食性天敌57种,隶属5目,21科。其中蜘蛛目12科,43种;蜻蜓目1科,2种;脉翅目1科,3种;半翅目3科,3种;鞘翅目4科,7种,以期为稻田害虫生物防治提供科学数据。

带药移栽对水稻害虫防控的减药增效作用分析

【目的】以新型、高效、持效期长的杀虫剂三氟苯嘧啶和四唑虫酰胺为例,探究带药移栽对水稻害虫的防控效果及农药减量增效的实践意义。【方法】通过室内模拟秧苗带药移栽分别测定了1.95,5.85和9.75 mg a.i./m^(2)三氟苯嘧啶处理对褐飞虱Nilaparvata lugens和白背飞虱Sogatella furcifera成虫或若虫的毒力和持效期,并在浙江杭州和湖南衡阳两地评估了早、中、晚稻秧苗高剂量带药移栽处理对二化螟Chilo suppressalis和稻飞虱的田间防效以及不同施药模式对稻田寄生蜂种群动态的影响。【结果】室内经5.85和9.75 mg a.i./m^(2)三氟苯嘧啶处理的秧苗在移栽后35 d时使褐飞虱雌成虫和3龄若虫均能保持75%以上的校正死亡率,且5.85 mg a.i./m^(2)剂量处理在移栽后28 d时使白背飞虱雌成虫的校正死亡率大于80%;使用12.75和25.50 mg a.i./m^(2)四唑虫酰胺处理秧苗在移栽后35 d时对早稻二化螟为害的校正防效均在85%以上。综合浙江杭州和湖南衡阳两地中、晚稻田间试验结果表明,应用5.85 mg a.i./m^(2)三氟苯嘧啶和25.50 mg a.i./m^(2)四唑虫酰胺进行秧苗“送嫁药”处理可减少1~2次大田用药和98%以上的农药有效成分用量,同时还保持着与常规喷施相当的防效,并使寄生蜂总种类和总数量分别提高了29.0%~49.7%和61.2%~69.3%。【结论】秧苗移栽前施用防效优良且持效期长的杀虫剂能减少水稻前期的施药次数和用量,产生较好的经济和生态效益。本研究为利用带药移栽技术推行水稻病虫害的绿色防控提供了重要参考。

早熟高产杂交水稻组合两优7871的选育及其高产栽培和制种技术

两优7871是由178S和R71杂交选育的杂交水稻品种,具有早熟、抗倒伏、优质、高产和稳产等特点。本文总结分析了该品种的选育过程、特征特性、高产栽培及制种技术,该品种在2016—2017年长江中下游区域试验中,全生育期130 d,平均产量9.51 t/hm^(2),外观品质优,适口性、抗病性较好;其高产栽培注重培育壮秧,控制无效分蘖,争取有效穗数,促大穗,提高结实率,重点防治稻瘟病、稻飞虱等;制种技术要点包括合理安排播差期,培育壮秧,合理密植,加强田间管理和巧喷赤霉酸生长调节剂等。研究结果为该品种在长江中下游作为一季中稻、麦茬直播稻和再生稻种植提供参考。

Evaluation and screening for resistance of some varieties(lines)to major diseases and insect pests of rice

During 1984-1988,2,231 varieties(lines)from International Rice Testing Program(IRTP)were evaluated and screened for resistance to riceblast(Bl),bacterial blight(BB),sheath blight

基于多模态预训练模型的水稻病虫害图像描述生成研究

[目的]针对水稻病虫害图像分类技术缺少对病症描述的问题,本文提出一种轻量化的水稻病虫害图像描述模型,对水稻病虫害图像进行更为具体的描述。[方法]以白叶枯病、细菌性条斑病、恶苗病、三化螟虫、稻瘟病、稻曲病、纹枯病、飞虱、稻蓟马、胡麻斑病这十类常见的水稻病虫害开展研究,构建了水稻病虫害图像中文描述数据集。首先采用多模态预训练模型CLIP生成图像向量,其中包含基本的图像信息以及丰富的语义信息,采用映射网络将图像向量映射到文本空间里生成文本提示向量,语言模型GPT-2根据文本提示向量生成图像描述。[结果]在水稻病虫害图像描述数据集上,本文模型的指标总体明显优于其他模型,本文算法的BLEU-1、BLEU-2、BLEU-3、BLEU-4、ROUGE、METEOR指标较传统的CNN_LSTM模型分别提升0.26、0.27、0.24、0.22、0.22、0.14。生成的图像描述具有准确、详细、语义丰富等优点。另外使用实际稻田图片对模型进行测试,实际田间的场景更为复杂多样,生成的图像描述指标与数据集指标对比总体仅有轻微下降,仍高于其他对比模型。本文模型对水稻病虫害的总体识别准确率达97.28%。[结论]基于多模态预训练模型的水稻病虫害图像描述方法能够准确识别水稻病虫害病症并形成相应的病症描述,为水稻病虫害检测提供一种新思路。

施肥方式对水稻产量品质和病虫害发生情况的影响

为筛选合适的施肥方案,以甬优1540品种为例,分析在绿色食品标准之下,不同的施肥方案对水稻产量、品质以及病虫害发生的影响.结果表明,未经过施肥处理的稻田产量最低,在每亩施用纯N7.5kg、P_(2)O_(5)2.8kg、K_(2)O8.0kg的基础上加施20kg海藻肥处理的水稻产量最高,且品质好、病虫害发生少,可作为江浙地区绿色食品水稻生产的推荐用肥.

褐飞虱和白背飞虱混合饲养中的共生细菌转移

【目的】探究褐飞虱Nilaparvata lugens和白背飞虱Sogatella furcifera的种间互作是否会导致其共生细菌的变化。【方法】分别对褐飞虱和白背飞虱进行单独饲养或混合饲养,并基于16S rRNA基因测序,分析不同饲养褐飞虱和白背飞虱种群共生细菌的多样性。【结果】混合饲养的与单独饲养的相比,褐飞虱和白背飞虱的共生菌群落结构均发生明显变化且具有趋同现象;混合饲养的褐飞虱共生细菌多样性比单独饲养的显著增加;褐飞虱中的133个扩增子序列变异(amplicon sequence variants,ASVs)和白背飞虱中的143个ASVs被定义为潜在的水平转移物种。【结论】褐飞虱和白背飞虱的种间互作改变了其共生细菌群落,研究结果为深入研究基于共生细菌的稻飞虱种间互作提供了新视角。

水稻害虫管理专家系统(ESRICE)的设计与实现

水稻害虫管理专家系统(ESRICE)系用知识工程语言NEW、编译BASIC和dBASEⅢ等构筑。系统共由13个子系统组成。各子系统可对不同代次的褐飞虱、稻纵卷叶螟的种群动态进行监测,并提供决策方案。系统耦联了外部数学模型以帮助用户回答咨询过程中系统提出的问题,或进一步确认是否需要化防及其用药时间。应用表明,该系统在水稻害虫管理上已达到专家水平。

阿维菌素与井冈霉素混配对水稻主要病虫害的防治效果

随着生态和绿色农业建设不断推进,环保型低毒生物农药被广泛研发与利用。针对水稻主要病虫害,本研究探讨了不同有效成分用量阿维菌素和井冈霉素混配剂(以下简称阿•井混配剂)在室内试验和田间试验对水稻主要病虫害的防治效果。结果表明:阿•井混配剂对毒杀水稻纹枯病菌、稻飞虱(白背飞虱和褐飞虱)、二化螟、三化螟、黑尾叶蝉有显著的增效作用。其增效作用可部分中和病原菌和害虫的抗药性,从而延长药剂的使用期。使用阿•井混配剂对稻纵卷叶螟和稻螟蛉的毒杀效果与单独使用阿维菌素时的毒杀效果相当。综上所述,生物农药阿维菌素和井冈霉素混配具有提高对水稻主要病虫害防控能力的潜力,并且属于绿色防治方法,值得大力推广应用。

2013—2022年我国水稻病虫害发生特点与绿色防控技术集成

水稻是我国第一大粮食作物,水稻病虫害防治直接关系着粮食稳产增产。本文在对2013年至2022年全国植保专业统计资料的分析基础上,总结回顾了水稻病虫害发生种类和特点、发生面积和为害损失等情况,分类梳理了水稻病虫害防治面积、挽回损失以及主要措施应用等防控概况,尤其是针对近年来生态调控、天敌保护和利用等绿色防控技术应用面积和发展趋势进行了研判总结,同时分别从技术覆盖、内容集成等角度分析探讨了水稻病虫害绿色防控技术发展成效,并对下一步绿色防控工作提出了思考和建议,旨在为我国未来水稻安全生产提供相应参考。

水稻重要害虫防治的杀虫剂应用及关键技术研究进展

水稻作为我国重要的粮食作物,其害虫防治直接关系到国家粮食安全。化学杀虫剂作为当前水稻害虫防治中不可或缺的工具,对于控制害虫数量、减少作物损失和保障粮食产量发挥着关键作用。然而,长期不合理使用杀虫剂导致了害虫抗药性的产生,给水稻害虫的科学防控和粮食安全带来挑战。概述了我国水稻重要害虫稻飞虱、二化螟和稻纵卷叶螟的发生与危害,化学防治药剂的发展历程及抗药性现状,并对当前水稻田杀虫剂应用及关键技术进行了综述,以期为实现我国水稻害虫的科学防控、提高杀虫剂利用效率和防治效果,进而为推动水稻产业的可持续发展和保障我国粮食安全提供指导。