首页 > 最新文献

Crop Protection最新文献

英文 中文
Identification and fungicide sensitivity of Fusarium oxysporum, the cause of Fusarium wilt on Codonopsis pilosula in Shanxi Province (Lu Dangshen), China 山西党参枯萎病病原菌尖孢镰刀菌的鉴定及其对杀菌剂的敏感性
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-13 DOI: 10.1016/j.cropro.2024.107083
Yan Wang , Dainan Hao , Haozhe Jiang , Zhaoxiong Fei , Rui Zhao , Jiaxin Gao , Guangxin Li , Chunwei Wang
Codonopsis pilosula, an important genuine herb in Shanxi Province, is generally named Lu Dangshen, and is well-known for its high medicinal value. In 2023, Fusarium wilt, a newly observed severe disease on C. pilosula, is responsible for approximately 40% incidence in the field. It was noticed that the diseased C. pilosula roots were usually asymptomatic on the surface. The typical symptoms were vascular discoloration, wilt, and leaves chlorosis. A total of 87 Fusarium isolates were isolated from diseased samples, and identified as Fusarium oxysporum based on morphological features and partial sequences analyses of internal transcribed spacer region of ribosomal DNA (ITS-rDNA), translation elongation factor 1 alpha (TEF-1α) and endopolygalacturonase 1 (pg1). Of the 87 Fusarium oxysporum isolates, the causal agents were separated into three distinct groups (Groups I, II and III). The virulence of each F. oxysporum isolate to C. pilosula was determined by measuring the disease incidence and Fusarium wilt severity. All the 87 Fusarium oxysporum isolates could cause typical symptoms similar to that originally appeared on diseased plants, and present significantly different pathogenic to C. pilosula. All tested isolates were highly sensitive to jinggangmycin, azoxystrobin, fludioxonil and epoxiconazole (EC50 < 10 μg/mL), and insensitive to iprodione and hymexazol. Additionally, F. oxysporum isolates have a low risk for fungicide resistance to jinggangmycin, iprodione and epoxiconazole. Thus, jinggangmycin and epoxiconazole should be recommended for the control of this disease. Our finding in this study should be useful for the understanding of Fusarium wilt of C. pilosula caused by F. oxysporum.
党参是山西省重要的正宗草药,俗称陆党参,因其极高的药用价值而闻名。在2023年,新发现的一种严重病害镰刀菌枯萎病(Fusarium wilt)在田间的发病率约为40%。我们注意到患病的党参根部在表面上通常是无症状的。典型症状为血管变色、枯萎和叶片褪绿。从病株中分离到87株镰刀菌,通过形态特征和核糖体DNA内部转录间隔区(ITS-rDNA)、翻译延伸因子1α (TEF-1α)和内聚半乳糖酶1 (pg1)的部分序列分析,鉴定为尖孢镰刀菌。将87株尖孢镰刀菌分离物分为3组(I、II和III组),通过测定病原菌发病率和枯萎病严重程度来测定各分离物对党参的毒力。87株尖孢镰刀菌分离株均能引起与原病株相似的典型症状,对草梗镰刀菌的致病性存在显著差异。所有分离株均对井冈霉素、嘧菌酯、氟恶菌腈和环氧康唑高度敏感(EC50 <;10 μg/mL),对异丙酮和噻虫唑不敏感。此外,尖孢F. oxysporum菌株对井冈霉素、异丙二酮和环氧康唑的耐药风险较低。因此,应推荐使用井冈霉素和环氧康唑控制本病。本研究结果将有助于对尖孢镰刀菌引起的党参枯萎病的认识。
{"title":"Identification and fungicide sensitivity of Fusarium oxysporum, the cause of Fusarium wilt on Codonopsis pilosula in Shanxi Province (Lu Dangshen), China","authors":"Yan Wang ,&nbsp;Dainan Hao ,&nbsp;Haozhe Jiang ,&nbsp;Zhaoxiong Fei ,&nbsp;Rui Zhao ,&nbsp;Jiaxin Gao ,&nbsp;Guangxin Li ,&nbsp;Chunwei Wang","doi":"10.1016/j.cropro.2024.107083","DOIUrl":"10.1016/j.cropro.2024.107083","url":null,"abstract":"<div><div><em>Codonopsis pilosula</em>, an important genuine herb in Shanxi Province, is generally named Lu Dangshen, and is well-known for its high medicinal value. In 2023, Fusarium wilt, a newly observed severe disease on <em>C</em>. <em>pilosula</em>, is responsible for approximately 40% incidence in the field. It was noticed that the diseased <em>C. pilosula</em> roots were usually asymptomatic on the surface. The typical symptoms were vascular discoloration, wilt, and leaves chlorosis. A total of 87 <em>Fusarium</em> isolates were isolated from diseased samples, and identified as <em>Fusarium oxysporum</em> based on morphological features and partial sequences analyses of internal transcribed spacer region of ribosomal DNA (ITS-rDNA), translation elongation factor 1 alpha (<em>TEF-1α</em>) and endopolygalacturonase 1 (<em>pg1</em>). Of the 87 <em>Fusarium oxysporum</em> isolates, the causal agents were separated into three distinct groups (Groups I, II and III). The virulence of each <em>F</em>. <em>oxysporum</em> isolate to <em>C</em>. <em>pilosula</em> was determined by measuring the disease incidence and Fusarium wilt severity. All the 87 <em>Fusarium oxysporum</em> isolates could cause typical symptoms similar to that originally appeared on diseased plants, and present significantly different pathogenic to <em>C. pilosula</em>. All tested isolates were highly sensitive to jinggangmycin, azoxystrobin, fludioxonil and epoxiconazole (EC<sub>50</sub> &lt; 10 μg/mL), and insensitive to iprodione and hymexazol. Additionally, <em>F. oxysporum</em> isolates have a low risk for fungicide resistance to jinggangmycin, iprodione and epoxiconazole. Thus, jinggangmycin and epoxiconazole should be recommended for the control of this disease. Our finding in this study should be useful for the understanding of Fusarium wilt of <em>C</em>. <em>pilosula</em> caused by <em>F. oxysporum</em>.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107083"},"PeriodicalIF":2.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparative performance of biological formulations for the management of Meloidogyne enterolobii in chickpea (Cicer arietinum) 鹰嘴豆肠曲线虫生物制剂的防治效果比较
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-13 DOI: 10.1016/j.cropro.2024.107082
Dwillian Firmiano Cunha , Thávio Júnior Barbosa Pinto , Valdir Ribeiro Correia , Aldegundes Batista Miranda Júnior , Felipe Santos Rafael , Leandro Alves Santos , Érica Vicente dos Santos , Juvenil Enrique Cares , Leonardo Silva Boiteux , Jadir Borges Pinheiro
Meloidogyne enterolobii can reduce yield and quality of chickpea. Thus far, no resistant cultivars have been reported. Hence, a study was carried out to evaluate the relative performance of biological products for the management of M. enterolobii on chickpea. Greenhouse experiments were conducted with ten treatments (five formulations of antagonistic fungi and bacteria applied either individually or in mixtures) and four controls (non-inoculated and inoculated chickpea and tomato plants). Each plant was inoculated with 4000 eggs and second-stage M. enterolobii juveniles (J2). Evaluation was done 60 days after inoculation for gall index, number of eggs per gram of roots, reproduction factor (RF), plant height, shoot, and root weight. None of the treatments fully suppressed infection. However, a subset of formulation mixtures displayed significant reduction in the levels of damage when compared to the untreated check. The treatments with best performance were [Purpureocillium lilacinum + Trichoderma harzanium] (57–74% reduction) and [Pochonia chlamydosporia + P. lilacinum + Bacillus amyloliquefaciens + B. pumilus + B. subtilis] (58–65% reduction), whereas [P. chlamydosporia + P. lilacinum + T. harzanium] and [B. amyloliquefaciens + B. pumilus + B. subtilis + T. harzanium] displayed the lowest levels of suppression (0–42%). Higher plant height and fresh shoot weight were observed with [P. chlamydosporia + P. lilacinum + B. amyloliquefaciens + B. pumilus + B. subtilis]. Hence, considering the low efficiency of the currently available management methods, the employment of these microbiological products might help to reduce the negative impacts of M. enterolobii in infested fields.
肠孢霉属(Meloidogyne enterolobii)会降低鹰嘴豆的产量和质量。迄今为止,还没有关于抗性栽培品种的报道。因此,我们开展了一项研究,以评估生物产品在管理鹰嘴豆上的肠孢霉菌方面的相对性能。温室试验共进行了 10 个处理(单独或混合使用 5 种拮抗真菌和细菌制剂)和 4 个对照(未接种和接种鹰嘴豆和番茄植株)。每株植物都接种了 4000 个虫卵和第二阶段的肠杆菌幼虫(J2)。接种 60 天后,对虫瘿指数、每克根中的虫卵数、繁殖系数 (RF)、株高、芽和根的重量进行评估。没有一种处理能完全抑制感染。不过,与未处理的对照组相比,部分配方混合物的危害程度明显减轻。表现最好的处理是[紫孢蘑菇 + 哈氏毛霉](减少 57-74%)和[Pochonia chlamydosporia + P. lilacinum + Bacillus amyloliquefaciens + B. pumilus + B. subtilis](减少 58-65%)。而[P. chlamydosporia + P. lilacinum + T. harzanium]和[B. amyloliquefaciens + B. pumilus + B. subtilis + T. harzanium]的抑制程度最低(0-42%)。P. chlamydosporia + P. lilacinum + B. amyloliquefaciens + B. pumilus + B. subtilis]的植株高度和鲜芽重量更高。因此,考虑到目前可用的管理方法效率较低,使用这些微生物产品可能有助于减少肠孢霉对受侵染田块的负面影响。
{"title":"Comparative performance of biological formulations for the management of Meloidogyne enterolobii in chickpea (Cicer arietinum)","authors":"Dwillian Firmiano Cunha ,&nbsp;Thávio Júnior Barbosa Pinto ,&nbsp;Valdir Ribeiro Correia ,&nbsp;Aldegundes Batista Miranda Júnior ,&nbsp;Felipe Santos Rafael ,&nbsp;Leandro Alves Santos ,&nbsp;Érica Vicente dos Santos ,&nbsp;Juvenil Enrique Cares ,&nbsp;Leonardo Silva Boiteux ,&nbsp;Jadir Borges Pinheiro","doi":"10.1016/j.cropro.2024.107082","DOIUrl":"10.1016/j.cropro.2024.107082","url":null,"abstract":"<div><div><em>Meloidogyne enterolobii</em> can reduce yield and quality of chickpea. Thus far, no resistant cultivars have been reported. Hence, a study was carried out to evaluate the relative performance of biological products for the management of <em>M. enterolobii</em> on chickpea. Greenhouse experiments were conducted with ten treatments (five formulations of antagonistic fungi and bacteria applied either individually or in mixtures) and four controls (non-inoculated and inoculated chickpea and tomato plants). Each plant was inoculated with 4000 eggs and second-stage <em>M. enterolobii</em> juveniles (J2). Evaluation was done 60 days after inoculation for gall index, number of eggs per gram of roots, reproduction factor (RF), plant height, shoot, and root weight. None of the treatments fully suppressed infection. However, a subset of formulation mixtures displayed significant reduction in the levels of damage when compared to the untreated check. The treatments with best performance were [<em>Purpureocillium lilacinum</em> + <em>Trichoderma harzanium</em>] (57–74% reduction) and [<em>Pochonia chlamydosporia</em> + <em>P. lilacinum</em> + <em>Bacillus amyloliquefaciens</em> + <em>B. pumilus</em> + <em>B. subtilis</em>] (58–65% reduction), whereas [<em>P. chlamydosporia</em> + <em>P. lilacinum</em> + <em>T. harzanium</em>] and [<em>B. amyloliquefaciens</em> + <em>B. pumilus</em> + <em>B. subtilis</em> + <em>T. harzanium</em>] displayed the lowest levels of suppression (0–42%). Higher plant height and fresh shoot weight were observed with [<em>P. chlamydosporia</em> + <em>P. lilacinum</em> + <em>B. amyloliquefaciens</em> + <em>B. pumilus</em> + <em>B. subtilis</em>]. Hence, considering the low efficiency of the currently available management methods, the employment of these microbiological products might help to reduce the negative impacts of <em>M. enterolobii</em> in infested fields.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107082"},"PeriodicalIF":2.5,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancing site-specific weed detection using deep learning transformer architectures 使用深度学习转换器架构增强特定站点的杂草检测
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-12 DOI: 10.1016/j.cropro.2024.107075
Francisco Garibaldi-Márquez , Daniel A. Martínez-Barba , Luis E. Montañez-Franco , Gerardo Flores , Luis M. Valentín-Coronado
Detection of weeds is essential to implement an intelligent weed control system in natural corn fields. Then, to address this issue, the Swin-UNet, Segmenter, and SegFormer deep learning transformer architectures have been implemented and compared. Furthermore, a simple thresholding method has been performed to enhance the segmentation. Moreover, a large pixel-level annotated image dataset acquired under natural field conditions is introduced to train the models. In addition, the well-known Precision, Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and mean Intersection over Union (mIoU) metrics have been used to evaluate the implemented models’ performance. According to the experimental results, the SegFormer architecture was the best model on each of the three proposed weed detection approaches, achieving a macro performance of up to 94.49%, 95.30%, and 91.26% for Precision, DSC, and mIoU, respectively.
检测杂草对于在天然玉米田中实施智能杂草控制系统至关重要。为解决这一问题,我们采用了 Swin-UNet、Segmenter 和 SegFormer 深度学习变换器架构,并对其进行了比较。此外,还采用了一种简单的阈值处理方法来增强分割效果。此外,还引入了在自然野外条件下获取的大型像素级注释图像数据集来训练模型。此外,还使用了著名的精度、骰子相似系数(DSC)、联合交叉(IoU)和平均联合交叉(mIoU)指标来评估所实现模型的性能。实验结果表明,SegFormer 架构在三种杂草检测方法中都是最佳模型,其精确度、DSC 和 mIoU 的宏观性能分别高达 94.49%、95.30% 和 91.26%。
{"title":"Enhancing site-specific weed detection using deep learning transformer architectures","authors":"Francisco Garibaldi-Márquez ,&nbsp;Daniel A. Martínez-Barba ,&nbsp;Luis E. Montañez-Franco ,&nbsp;Gerardo Flores ,&nbsp;Luis M. Valentín-Coronado","doi":"10.1016/j.cropro.2024.107075","DOIUrl":"10.1016/j.cropro.2024.107075","url":null,"abstract":"<div><div>Detection of weeds is essential to implement an intelligent weed control system in natural corn fields. Then, to address this issue, the Swin-UNet, Segmenter, and SegFormer deep learning transformer architectures have been implemented and compared. Furthermore, a simple thresholding method has been performed to enhance the segmentation. Moreover, a large pixel-level annotated image dataset acquired under natural field conditions is introduced to train the models. In addition, the well-known Precision, Dice Similarity Coefficient (DSC), Intersection over Union (IoU), and mean Intersection over Union (mIoU) metrics have been used to evaluate the implemented models’ performance. According to the experimental results, the SegFormer architecture was the best model on each of the three proposed weed detection approaches, achieving a macro performance of up to 94.49%, 95.30%, and 91.26% for Precision, DSC, and mIoU, respectively.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107075"},"PeriodicalIF":2.5,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
First report of Fusarium concentricum and F. verticillioides causing leaf spot on Trachelospermum jasminoides in China 引起茉莉叶斑病的镰刀菌和黄萎病镰刀菌在国内首次报道
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-12 DOI: 10.1016/j.cropro.2024.107071
Mengting Jiang , Yifei Wang , Qiuqin Wang , Xiuyu Zhang , Yu Wan , Yinjuan Zhao
Trachelospermum jasminoides (Lindl.) Lem. Is widely used in landscaping. In August 2023, leaf spot disease in T. jasminoides was observed in the city parks and foresty districts of Nanjing, Jiangsu Province, China. Symptoms of the disease include gray‒white spots of different sizes and round or irregular shapes, and late leaf spots are very prone to crumbling, the formation of perforation symptoms, and leaf scorching and shedding. Pathogenic fungi were isolated from diseased leaves and identified as Fusarium concentricum and F. verticillioides on the basis of morphological features and multilocus phylogenetic analyses of the internal transcribed spacer (ITS) region, RNA polymerase II subunit B (RPB2), calmodulin (CaM), β-tubulin (TUB2) and translation elongation factor 1-alpha (TEF1-α) gene sequences. Pathogenicity tests revealed that F. concentricum and F. verticillioides can cause leaf spot on T. jasminoides. This study is the first report of F. concentricum and F. verticillioides causing leaf spot on T. jasminoides in China and provides a solid theoretical foundation for the scientific prevention and control of this disease.
茉莉花(英文)登月舱。广泛应用于园林绿化。2023年8月,在江苏省南京市城市公园和林区观察到茉莉叶斑病。该病的症状为大小不一、形状圆形或不规则的灰白色斑点,晚期叶斑极易碎裂,形成穿孔症状,叶片灼落。从病叶中分离到病原菌,通过形态学特征和内部转录间隔区(ITS)、RNA聚合酶II亚基B (RPB2)、钙调蛋白(CaM)、β-微管蛋白(TUB2)和翻译伸长因子1-α (TEF1-α)基因序列的多位点系统发育分析,鉴定为镰刀菌(Fusarium concentricum)和黄萎病菌(F. verticillioides)。致病性试验表明,集中镰刀菌和黄萎病镰刀菌可引起茉莉叶斑病。本研究是国内首次报道集中镰刀菌和黄萎病镰刀菌引起茉莉花叶斑病,为科学防治该病害提供了坚实的理论基础。
{"title":"First report of Fusarium concentricum and F. verticillioides causing leaf spot on Trachelospermum jasminoides in China","authors":"Mengting Jiang ,&nbsp;Yifei Wang ,&nbsp;Qiuqin Wang ,&nbsp;Xiuyu Zhang ,&nbsp;Yu Wan ,&nbsp;Yinjuan Zhao","doi":"10.1016/j.cropro.2024.107071","DOIUrl":"10.1016/j.cropro.2024.107071","url":null,"abstract":"<div><div><em>Trachelospermum jasminoides</em> (Lindl.) Lem. Is widely used in landscaping. In August 2023, leaf spot disease in <em>T. jasminoides</em> was observed in the city parks and foresty districts of Nanjing, Jiangsu Province, China. Symptoms of the disease include gray‒white spots of different sizes and round or irregular shapes, and late leaf spots are very prone to crumbling, the formation of perforation symptoms, and leaf scorching and shedding. Pathogenic fungi were isolated from diseased leaves and identified as <em>Fusarium concentricum</em> and <em>F. verticillioides</em> on the basis of morphological features and multilocus phylogenetic analyses of the internal transcribed spacer (ITS) region, RNA polymerase II subunit B (RPB2), calmodulin (CaM), β-tubulin (TUB2) and translation elongation factor 1-alpha (TEF1-α) gene sequences. Pathogenicity tests revealed that <em>F. concentricum</em> and <em>F. verticillioides</em> can cause leaf spot on <em>T. jasminoides</em>. This study is the first report of <em>F. concentricum</em> and <em>F. verticillioides</em> causing leaf spot on <em>T. jasminoides</em> in China and provides a solid theoretical foundation for the scientific prevention and control of this disease.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107071"},"PeriodicalIF":2.5,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142884074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Impact of Amaranthus spp. weed presence on the population abundance of Spodoptera cosmioides (Lepidoptera: Noctuidae) in genetically engineered soybean crops 苋属杂草存在对转基因大豆夜蛾种群丰度的影响
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-11 DOI: 10.1016/j.cropro.2024.107080
Jorge G. Hill , Paula G. Páez Jerez , Patricia C. Fernández , Facundo Herrera Linares , M Florencia Rocha , M Teresa Vera
The introduction of herbicide-resistant and Bt crops has led to significant disruption in weed and insect pest communities. Using pheromone-baited traps, we assessed the impact of varying levels of Amaranthus infestation on the population abundance of S. cosmioides in both Bt and non-Bt soybeans. Additionally, we monitored the abundance of S. cosmioides and other leaf-chewing larvae in these soybeans employing the vertical beat sheet method. There was no difference in the number of S. cosmioides adults captured by pheromone-baited traps in Bt and non-Bt soybeans. Traps placed in plots with high Amaranthus levels captured 68.3% more S. cosmioides males than those with low Amaranthus presence. Similarly, a higher number of S. cosmioides larvae were recorded in soybean plots with high Amaranthus levels. In Bt soybean, the larvae of S. cosmioides were the most abundant Lepidoptera, although its populations were surpassed in the second crop season by R. nu. In non-Bt soybean, C. includens was the dominant species throughout both crop seasons, and its larval abundance was unaffected by Amaranthus infestation levels. The presence of green bridges may facilitate the colonization of S. cosmioides in soybean crops, as adults and larvae were more abundant in soybeans with high levels of Amaranthus infestation. Moreover, the influence of other key species such as C. includens negatively affected the abundance of S. cosmioides in non-Bt soybean. A combined approach of constant monitoring and management of difficult-to-control weeds is crucial for managing polyphagous pests.
抗除草剂作物和 Bt 作物的引入极大地破坏了杂草和害虫群落。利用信息素诱捕器,我们评估了不同程度的苋属植物侵扰对 Bt 和非 Bt 大豆中宇宙大蝼蛄种群数量的影响。此外,我们还采用垂直拍片法监测了这些大豆中 S. cosmioides 和其他啃叶幼虫的数量。在 Bt 和非 Bt 大豆中,信息素诱饵诱捕器捕获的 S. cosmioides 成虫数量没有差异。在苋菜含量高的地块放置的诱捕器捕获的 S. cosmioides 雄性数量比苋菜含量低的地块多 68.3%。同样,在苋菜含量高的大豆地块中,记录到的 S. cosmioides 幼虫数量也更多。在 Bt 大豆中,S. cosmioides 幼虫是数量最多的鳞翅目昆虫,但其数量在第二季被 R. nu 超过。在非 Bt 大豆中,C. includens 在两个作物季节都是主要物种,其幼虫数量不受苋菜虫害水平的影响。由于成虫和幼虫在苋菜虫害程度较高的大豆中数量较多,绿桥的存在可能会促进 S. cosmioides 在大豆作物中的定殖。此外,其他关键物种(如 C. includens)的影响也对 S. cosmioides 在非 Bt 大豆中的数量产生了负面影响。持续监测和管理难以控制的杂草相结合的方法对于管理多食性害虫至关重要。
{"title":"Impact of Amaranthus spp. weed presence on the population abundance of Spodoptera cosmioides (Lepidoptera: Noctuidae) in genetically engineered soybean crops","authors":"Jorge G. Hill ,&nbsp;Paula G. Páez Jerez ,&nbsp;Patricia C. Fernández ,&nbsp;Facundo Herrera Linares ,&nbsp;M Florencia Rocha ,&nbsp;M Teresa Vera","doi":"10.1016/j.cropro.2024.107080","DOIUrl":"10.1016/j.cropro.2024.107080","url":null,"abstract":"<div><div>The introduction of herbicide-resistant and Bt crops has led to significant disruption in weed and insect pest communities. Using pheromone-baited traps, we assessed the impact of varying levels of <em>Amaranthus</em> infestation on the population abundance of <em>S. cosmioides</em> in both Bt and non-Bt soybeans. Additionally, we monitored the abundance of <em>S. cosmioides</em> and other leaf-chewing larvae in these soybeans employing the vertical beat sheet method. There was no difference in the number of <em>S. cosmioides</em> adults captured by pheromone-baited traps in Bt and non-Bt soybeans. Traps placed in plots with high <em>Amaranthus</em> levels captured 68.3% more <em>S. cosmioides</em> males than those with low <em>Amaranthus</em> presence. Similarly, a higher number of <em>S. cosmioides</em> larvae were recorded in soybean plots with high <em>Amaranthus</em> levels. In Bt soybean, the larvae of <em>S. cosmioides</em> were the most abundant Lepidoptera, although its populations were surpassed in the second crop season by <em>R. nu</em>. In non-Bt soybean, <em>C. includens</em> was the dominant species throughout both crop seasons, and its larval abundance was unaffected by <em>Amaranthus</em> infestation levels. The presence of green bridges may facilitate the colonization of <em>S. cosmioides</em> in soybean crops, as adults and larvae were more abundant in soybeans with high levels of <em>Amaranthus</em> infestation. Moreover, the influence of other key species such as <em>C. includens</em> negatively affected the abundance of <em>S. cosmioides</em> in non-Bt soybean. A combined approach of constant monitoring and management of difficult-to-control weeds is crucial for managing polyphagous pests.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107080"},"PeriodicalIF":2.5,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mealybug, Planococcus ficus, reduction through pavement ant, Tetramorium immigrans, management using polyacrylamide hydrogel baits in vineyards 粉蚧、榕树扁球菌、通过路面蚁、蚁笼移民的减少,管理使用聚丙烯酰胺水凝胶诱饵在葡萄园
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-09 DOI: 10.1016/j.cropro.2024.107078
Nathan H. Mercer , David R. Haviland , Kent M. Daane
The mealybug Planococcus ficus Signoret is an important vineyard pest, causing direct damage from feeding as well as vectoring important viral pathogens. Several species of ants tend P. ficus in California, including the pavement ant, Tetramorium immigrans Santschi. We tested the impact of polyacrylamide hydrogels loaded with a 25% sucrose solution and a variety of individual insecticide active ingredients (abamectin, boric acid, pyriproxyfen, spinosad, and thiamethoxam) on T. immigrans populations in vineyards. Additionally, we measured how a reduction of T. immigrans impacts densities of both P. ficus and its natural enemies. All insecticides tested reduced ant counts to some extent. Thiamethoxam was the most effective insecticide tested in both years. Boric acid was the least effective overall with pyriproxyfen and spinosad causing intermediate reductions in ant counts. In a separate trial, thiamethoxam loaded hydrogels reduced ant counts and significantly reduced P. ficus infested grape clusters, but did not reduce P. ficus vine trunk populations, nor increase parasitism rates. This is the first trial of hydrogel bait used for T. immigrans management and demonstrates the effectiveness of polyacrylamide hydrogels as ant baits and that T. immigrans reduction also lowers P. ficus abundance.
蚧壳虫 Planococcus ficus Signoret 是一种重要的葡萄园害虫,不仅会直接造成食害,还会传播重要的病毒病原体。在加利福尼亚州,有几种蚂蚁趋向于 P. ficus,包括人行道蚂蚁 Tetramorium immigrans Santschi。我们测试了含有 25% 蔗糖溶液和多种杀虫剂活性成分(阿维菌素、硼酸、吡虫啉、久效磷和噻虫嗪)的聚丙烯酰胺水凝胶对葡萄园中 T. immigrans 数量的影响。此外,我们还测量了 T. immigrans 的减少对榕树蚂蚁及其天敌密度的影响。所有测试的杀虫剂都在一定程度上减少了蚂蚁数量。噻虫嗪是这两年测试的最有效杀虫剂。硼酸的总体效果最差,吡虫啉和久效磷对蚂蚁数量的减少效果居中。在另一项试验中,含噻虫嗪的水凝胶减少了蚂蚁数量,并显著减少了受薜荔虫侵扰的葡萄簇,但没有减少薜荔虫的藤蔓数量,也没有提高寄生率。这是首次将水凝胶诱饵用于蚂蚁管理的试验,证明了聚丙烯酰胺水凝胶作为蚂蚁诱饵的有效性,而且减少蚂蚁也能降低榕树的数量。
{"title":"Mealybug, Planococcus ficus, reduction through pavement ant, Tetramorium immigrans, management using polyacrylamide hydrogel baits in vineyards","authors":"Nathan H. Mercer ,&nbsp;David R. Haviland ,&nbsp;Kent M. Daane","doi":"10.1016/j.cropro.2024.107078","DOIUrl":"10.1016/j.cropro.2024.107078","url":null,"abstract":"<div><div>The mealybug <em>Planococcus ficus</em> Signoret is an important vineyard pest, causing direct damage from feeding as well as vectoring important viral pathogens. Several species of ants tend <em>P. ficus</em> in California, including the pavement ant, <em>Tetramorium immigrans</em> Santschi. We tested the impact of polyacrylamide hydrogels loaded with a 25% sucrose solution and a variety of individual insecticide active ingredients (abamectin, boric acid, pyriproxyfen, spinosad, and thiamethoxam) on <em>T. immigrans</em> populations in vineyards. Additionally, we measured how a reduction of <em>T. immigrans</em> impacts densities of both <em>P. ficus</em> and its natural enemies. All insecticides tested reduced ant counts to some extent. Thiamethoxam was the most effective insecticide tested in both years. Boric acid was the least effective overall with pyriproxyfen and spinosad causing intermediate reductions in ant counts. In a separate trial, thiamethoxam loaded hydrogels reduced ant counts and significantly reduced <em>P. ficus</em> infested grape clusters, but did not reduce <em>P. ficus</em> vine trunk populations, nor increase parasitism rates. This is the first trial of hydrogel bait used for <em>T. immigrans</em> management and demonstrates the effectiveness of polyacrylamide hydrogels as ant baits and that <em>T. immigrans</em> reduction also lowers <em>P. ficus</em> abundance.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107078"},"PeriodicalIF":2.5,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142841515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Seed oil from Syagrus coronata has contact toxicity and reduces population growth of Sitophilus zeamais (Coleoptera: Curculionidae) 冠Syagrus coronata籽油具有接触毒性,可降低玉米象(鞘翅目:斑象科)的种群增长。
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-09 DOI: 10.1016/j.cropro.2024.107077
Antonia Ângela Bezerra , Patryck Érmerson Monteiro dos Santos , Quéren Hapuque Silva Pereira de Alcantara Vilarim , Fábio Henrique Galdino dos Santos , Daniela Maria do Amaral Ferraz Navarro , Patrícia Maria Guedes Paiva , Márcia Vanusa da Silva , Thiago Henrique Napoleão , Maria Tereza dos Santos Correia
The maize weevil, Sitophilus zeamais, is one of the main primary pests of stored grains in the world. Synthetic insecticides are the main means of controlling this pest, but environmental and health issues have been associated with their use. Therefore, natural insecticides have been sought to control pests like this. The objective of this work was to evaluate the insecticidal activity of fixed oil from S. coronata seeds (FOSc) against S. zeamais through ingestion and contact toxicity tests, influence on population growth rate and assessment of residual effect. The main compounds of FOSc were lauric acid (59.88%), myristic acid (13.13%) and capric acid (9.61%). FOSc presented ingestion toxicity with lethal concentrations for 50% (LC50) and 90% (LC90) of insects of 2.58 μL/g and 8.15 μL/g, respectively. The oil was able to inhibit in vitro α-amylase activity from gut extract. In the contact toxicity, LC50 and LC90 were 2.99 μL/g and 6.21 μL/g, respectively. Treating the grains with oil reduced the emergence of insects, reducing the population growth rate. However, FOSc showed low residual effect against the insect under study, being active only for 24 h after its application. In conclusion, S. coronata fixed oil can be used as an alternative to synthetic insecticides to control S. zeamais through ingestion and contact pathways.
玉米象甲(Sitophilus zeamais)是世界上主要的储粮害虫之一。合成杀虫剂是控制这一害虫的主要手段,但使用合成杀虫剂会产生环境和健康问题。因此,人们一直在寻求天然杀虫剂来控制这类害虫。通过食入毒性试验、接触毒性试验、对玉米螟种群生长率的影响及残留效应评价,评价了冠状花种子固定油对玉米螟的杀虫活性。FOSc主要成分为月桂酸(59.88%)、肉豆蔻酸(13.13%)和癸酸(9.61%)。FOSc对昆虫具有50% (LC50)和90% (LC90)的食入毒性,致死浓度分别为2.58 μL/g和8.15 μL/g。该油对体外α-淀粉酶活性有抑制作用。接触毒性LC50和LC90分别为2.99 μL/g和6.21 μL/g。用油处理谷物减少了昆虫的出现,降低了种群的增长率。然而,FOSc对所研究昆虫的残留作用较低,仅在施用后24 h内有效。综上所述,可通过食入途径和接触途径替代合成杀虫剂防治玉米玉米蚜。
{"title":"Seed oil from Syagrus coronata has contact toxicity and reduces population growth of Sitophilus zeamais (Coleoptera: Curculionidae)","authors":"Antonia Ângela Bezerra ,&nbsp;Patryck Érmerson Monteiro dos Santos ,&nbsp;Quéren Hapuque Silva Pereira de Alcantara Vilarim ,&nbsp;Fábio Henrique Galdino dos Santos ,&nbsp;Daniela Maria do Amaral Ferraz Navarro ,&nbsp;Patrícia Maria Guedes Paiva ,&nbsp;Márcia Vanusa da Silva ,&nbsp;Thiago Henrique Napoleão ,&nbsp;Maria Tereza dos Santos Correia","doi":"10.1016/j.cropro.2024.107077","DOIUrl":"10.1016/j.cropro.2024.107077","url":null,"abstract":"<div><div>The maize weevil, <em>Sitophilus zeamais</em>, is one of the main primary pests of stored grains in the world. Synthetic insecticides are the main means of controlling this pest, but environmental and health issues have been associated with their use. Therefore, natural insecticides have been sought to control pests like this. The objective of this work was to evaluate the insecticidal activity of fixed oil from <em>S. coronata</em> seeds (FOSc) against <em>S. zeamais</em> through ingestion and contact toxicity tests, influence on population growth rate and assessment of residual effect. The main compounds of FOSc were lauric acid (59.88%), myristic acid (13.13%) and capric acid (9.61%). FOSc presented ingestion toxicity with lethal concentrations for 50% (LC<sub>50</sub>) and 90% (LC<sub>90</sub>) of insects of 2.58 μL/g and 8.15 μL/g, respectively. The oil was able to inhibit <em>in vitro</em> α-amylase activity from gut extract. In the contact toxicity, LC<sub>50</sub> and LC<sub>90</sub> were 2.99 μL/g and 6.21 μL/g, respectively. Treating the grains with oil reduced the emergence of insects, reducing the population growth rate. However, FOSc showed low residual effect against the insect under study, being active only for 24 h after its application. In conclusion, <em>S. coronata</em> fixed oil can be used as an alternative to synthetic insecticides to control <em>S. zeamais</em> through ingestion and contact pathways.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107077"},"PeriodicalIF":2.5,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142804551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
First report of Fusarium proliferatum associated with pod rot of winged bean (Psophocarpus tetragonolobus (L.) DC.) in India 飞豆(Psophocarpus tetragonolobus (L.))荚果腐病相关的增殖镰刀菌(Fusarium proliferatum)初报华盛顿特区)
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-06 DOI: 10.1016/j.cropro.2024.107072
Sunil Kumar Sunani , Rubin Debbarma , Bishnu Maya Bashyal , S. Raghu , B. Jeevan
{"title":"First report of Fusarium proliferatum associated with pod rot of winged bean (Psophocarpus tetragonolobus (L.) DC.) in India","authors":"Sunil Kumar Sunani ,&nbsp;Rubin Debbarma ,&nbsp;Bishnu Maya Bashyal ,&nbsp;S. Raghu ,&nbsp;B. Jeevan","doi":"10.1016/j.cropro.2024.107072","DOIUrl":"10.1016/j.cropro.2024.107072","url":null,"abstract":"","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107072"},"PeriodicalIF":2.5,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142804535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advancing precision agriculture with computer vision: A comparative study of YOLO models for weed and crop recognition 用计算机视觉推进精准农业:YOLO模型用于杂草和作物识别的比较研究
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-06 DOI: 10.1016/j.cropro.2024.107076
Tomáš Zoubek , Roman Bumbálek , Jean de Dieu Marcel Ufitikirezi , Miroslav Strob , Martin Filip , František Špalek , Aleš Heřmánek , Petr Bartoš
In this study, we investigated the application of three convolutional neural network models YOLOv5, YOLOR, and YOLOv7 for precisely detecting individual radish plants, radish rows, and weeds. A comprehensive dataset was created, capturing diverse conditions and annotated for three target classes: radish, radish-line, and weed. Through extensive experimentation involving 39 combinations of model types, batch sizes (2, 4, 8), and learning rates (0.1, 0.01, 0.001), we determined that the YOLOv5-x model with a batch size of 4 and a learning rate of 0.01 offers superior performance. This configuration achieved a remarkable 99% accuracy for the radish class, 98% for radish-line, and 91% for weed, as confirmed by confusion matrices. Further analysis using the F1-score, Precision-Recall (PR) curves, and training progress plots underscored the model's robustness, particularly its high mAP_0.5:0.95 score. Despite the Weed class posing greater detection challenges, likely due to its lower representation in the dataset, the YOLOv5-x outperformed YOLOR-D6 and YOLOv7-D6 in critical metrics after 300 epochs. This research not only highlights the efficacy of YOLOv5-x in agricultural applications but also suggests potential enhancements in data annotation and model training strategies to further improve weed detection. Our findings provide significant insights for developing automated, high-precision plant-weed detection systems, contributing to more efficient and sustainable agricultural practices.
在这项研究中,我们研究了三种卷积神经网络模型YOLOv5、YOLOR和YOLOv7在萝卜单株、萝卜行和杂草精确检测中的应用。创建了一个全面的数据集,捕获了不同的条件,并对三个目标类进行了注释:萝卜、萝卜线和杂草。通过涉及39种模型类型、批大小(2、4、8)和学习率(0.1、0.01、0.001)组合的广泛实验,我们确定批大小为4、学习率为0.01的YOLOv5-x模型具有优越的性能。混淆矩阵证实,这种配置对萝卜类的准确率达到了惊人的99%,对萝卜线的准确率为98%,对杂草的准确率为91%。进一步分析使用f1分数,精确召回(PR)曲线和训练进度图强调了模型的稳健性,特别是它的高mAP_0.5:0.95分数。尽管Weed类带来了更大的检测挑战,可能是由于其在数据集中的代表性较低,但在300次epoch后,YOLOv5-x在关键指标上优于yolov5 - d6和YOLOv7-D6。本研究不仅突出了YOLOv5-x在农业应用中的有效性,而且还提出了在数据标注和模型训练策略方面的潜在改进,以进一步提高杂草检测水平。我们的发现为开发自动化、高精度的植物杂草检测系统提供了重要的见解,有助于提高农业实践的效率和可持续性。
{"title":"Advancing precision agriculture with computer vision: A comparative study of YOLO models for weed and crop recognition","authors":"Tomáš Zoubek ,&nbsp;Roman Bumbálek ,&nbsp;Jean de Dieu Marcel Ufitikirezi ,&nbsp;Miroslav Strob ,&nbsp;Martin Filip ,&nbsp;František Špalek ,&nbsp;Aleš Heřmánek ,&nbsp;Petr Bartoš","doi":"10.1016/j.cropro.2024.107076","DOIUrl":"10.1016/j.cropro.2024.107076","url":null,"abstract":"<div><div>In this study, we investigated the application of three convolutional neural network models YOLOv5, YOLOR, and YOLOv7 for precisely detecting individual radish plants, radish rows, and weeds. A comprehensive dataset was created, capturing diverse conditions and annotated for three target classes: radish, radish-line, and weed. Through extensive experimentation involving 39 combinations of model types, batch sizes (2, 4, 8), and learning rates (0.1, 0.01, 0.001), we determined that the YOLOv5-x model with a batch size of 4 and a learning rate of 0.01 offers superior performance. This configuration achieved a remarkable 99% accuracy for the radish class, 98% for radish-line, and 91% for weed, as confirmed by confusion matrices. Further analysis using the F1-score, Precision-Recall (PR) curves, and training progress plots underscored the model's robustness, particularly its high mAP_0.5:0.95 score. Despite the Weed class posing greater detection challenges, likely due to its lower representation in the dataset, the YOLOv5-x outperformed YOLOR-D6 and YOLOv7-D6 in critical metrics after 300 epochs. This research not only highlights the efficacy of YOLOv5-x in agricultural applications but also suggests potential enhancements in data annotation and model training strategies to further improve weed detection. Our findings provide significant insights for developing automated, high-precision plant-weed detection systems, contributing to more efficient and sustainable agricultural practices.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107076"},"PeriodicalIF":2.5,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142804550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Non-exemplar class-incremental learning for continual plant diagnosis 用于连续植物诊断的非范例类增量学习
IF 2.5 2区 农林科学 Q1 AGRONOMY Pub Date : 2024-12-05 DOI: 10.1016/j.cropro.2024.107069
Dasen Li, Zhendong Yin, Yanlong Zhao, Yaqin Zhao, Hongjun Zhang
Deep learning has been widely applied as a general technique for image classification in plant diagnosis. Despite the impressive performance verified by individual classification tasks, deep learning networks suffer from forgetting the knowledge of old-type when updating the input stream by new disease samples in the continual plant diagnosis. Recently, rehearsal-based class-incremental learning approaches for plant disease classification have been proposed to mitigate the effects of old-type forgetting. These methods stored parts of leaf images of old disease, then replayed old exemplars and trained jointly with the new disease data in a class-incremental task. However, privacy issues and a considerable amount of memory limit the application of these rehearsal-based methods. In this paper, we investigate non-exemplar class-incremental learning schemes for plant diagnosis to address the catastrophic forgetting problem without requiring extra memory space for stored exemplars. We introduce a new non-exemplar class-incremental learning scheme, NeCILPD, for continual plant diagnosis. In particular, we propose an improved self-supervision learning algorithm and a novel prototype inversion constraint strategy to mitigate the problem of prototype shifts, in order to further improve the performance of few-shot class-incremental learning tasks. Experimental results confirmed the effectiveness of the proposed class-incremental learning approach. Specifically, the proposed class-incremental learning scheme achieved 70.27% accuracy and 17.80% forgetting measure in the incremental classification of 30 categories, outperforming the current SOTA method, which attained 63.80% accuracy and a forgetting measure of 24.80%. The impressive performance of the proposed non-exemplar class-incremental learning scheme provides a reliable tool for continual plant diagnosis, laying a solid foundation for agricultural applications.
深度学习作为一种通用的图像分类技术在植物诊断中得到了广泛的应用。尽管单个分类任务验证了令人印象深刻的性能,但深度学习网络在持续的植物诊断中,当使用新的疾病样本更新输入流时,会忘记旧类型的知识。近年来,人们提出了一种基于预演的植物病害分类分级学习方法,以减轻旧式遗忘的影响。这些方法存储旧疾病的部分叶片图像,然后在类增量任务中重播旧样本并与新疾病数据联合训练。然而,隐私问题和大量内存限制了这些基于预演的方法的应用。在本文中,我们研究了用于植物诊断的非样本类增量学习方案,以解决灾难性遗忘问题,而不需要额外的存储样本的记忆空间。我们引入了一种新的非范例类增量学习方案NeCILPD,用于连续植物诊断。特别地,我们提出了一种改进的自监督学习算法和一种新的原型反演约束策略来缓解原型移位问题,以进一步提高少镜头类增量学习任务的性能。实验结果证实了所提出的类增量学习方法的有效性。具体而言,在30个类别的增量分类中,所提出的类增量学习方案的准确率为70.27%,遗忘量为17.80%,优于当前SOTA方法的准确率为63.80%,遗忘量为24.80%。所提出的非范例类增量学习方案的令人印象深刻的性能为连续植物诊断提供了可靠的工具,为农业应用奠定了坚实的基础。
{"title":"Non-exemplar class-incremental learning for continual plant diagnosis","authors":"Dasen Li,&nbsp;Zhendong Yin,&nbsp;Yanlong Zhao,&nbsp;Yaqin Zhao,&nbsp;Hongjun Zhang","doi":"10.1016/j.cropro.2024.107069","DOIUrl":"10.1016/j.cropro.2024.107069","url":null,"abstract":"<div><div>Deep learning has been widely applied as a general technique for image classification in plant diagnosis. Despite the impressive performance verified by individual classification tasks, deep learning networks suffer from forgetting the knowledge of old-type when updating the input stream by new disease samples in the continual plant diagnosis. Recently, rehearsal-based class-incremental learning approaches for plant disease classification have been proposed to mitigate the effects of old-type forgetting. These methods stored parts of leaf images of old disease, then replayed old exemplars and trained jointly with the new disease data in a class-incremental task. However, privacy issues and a considerable amount of memory limit the application of these rehearsal-based methods. In this paper, we investigate non-exemplar class-incremental learning schemes for plant diagnosis to address the catastrophic forgetting problem without requiring extra memory space for stored exemplars. We introduce a new non-exemplar class-incremental learning scheme, NeCILPD, for continual plant diagnosis. In particular, we propose an improved self-supervision learning algorithm and a novel prototype inversion constraint strategy to mitigate the problem of prototype shifts, in order to further improve the performance of few-shot class-incremental learning tasks. Experimental results confirmed the effectiveness of the proposed class-incremental learning approach. Specifically, the proposed class-incremental learning scheme achieved 70.27% accuracy and 17.80% forgetting measure in the incremental classification of 30 categories, outperforming the current SOTA method, which attained 63.80% accuracy and a forgetting measure of 24.80%. The impressive performance of the proposed non-exemplar class-incremental learning scheme provides a reliable tool for continual plant diagnosis, laying a solid foundation for agricultural applications.</div></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":"190 ","pages":"Article 107069"},"PeriodicalIF":2.5,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142911703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Crop Protection
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1