Crop ProtectionPub Date : 2024-06-27DOI: 10.1016/j.cropro.2024.106828
YuYang Wang, Feng Jiang, Hui Zhou
{"title":"Lightweight convolutional neural network-based plant disease identification for protection and landscape design","authors":"YuYang Wang, Feng Jiang, Hui Zhou","doi":"10.1016/j.cropro.2024.106828","DOIUrl":"https://doi.org/10.1016/j.cropro.2024.106828","url":null,"abstract":"<div><p>Plant diseases significantly impact landscape design, necessitating comprehensive consideration and effective management measures to ensure the health, aesthetics, and sustainability of landscapes. Early detection and timely control of plant diseases are crucial, but traditional monitoring methods, which rely on manual observation and sample collection, are inadequate for covering large garden areas and may delay necessary treatments. This study addresses these challenges by constructing a small Rosa chinensis disease dataset through field collection and data augmentation techniques. We propose MixResCoAtNet, an improved model based on the lightweight MixNet framework, to identify and categorize diseases from plant leaf images using convolutional neural networks (CNNs). Comparison experiments with various classical convolutional network models demonstrate that MixResCoAtNet outperforms these models, offering more competitive performance. Additionally, due to its lighter structure, MixResCoAtNet shows greater potential for deployment on mobile devices, facilitating real-time and efficient plant disease monitoring and management in landscape design.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141540999","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}
Crop ProtectionPub Date : 2024-06-26DOI: 10.1016/j.cropro.2024.106827
Sidol Houngbo, Espérance Zossou, Edith D. Boko, Augustin Aoudji, Afio Zannou, Adam Ahanchede
{"title":"Farmers’ perceptions of innovation characteristics and adoption: Evidence from three fall armyworm (Spodoptera frugiperda) management methods in Benin","authors":"Sidol Houngbo, Espérance Zossou, Edith D. Boko, Augustin Aoudji, Afio Zannou, Adam Ahanchede","doi":"10.1016/j.cropro.2024.106827","DOIUrl":"10.1016/j.cropro.2024.106827","url":null,"abstract":"<div><p>Several methods have been developed to support farmers in the management of the fall armyworm (<em>Spodoptera</em> <em>frugiperda</em>), which is a serious threat to maize production in Africa. These include the local soap Palmida, neem oil, and the semi-synthetic pesticide Emacot 19 EC. Based on Rogers' innovation theory, this study aimed to analyze farmers' perceptions of the characteristics of these control methods in order to identify potential obstacles to their adoption. The study used a quantitative (individual survey) and qualitative (focus groups interviews) approach to collect data from maize farmers. The results showed that the success of a management method at the farmer level will depend on its potential to minimize protection costs, its speed in eliminating larvae in an infested field, its accessibility in the farmer's immediate environment and the simplicity of its preparation and application. Considering these factors, Emacot 19 EC and Palmida soap are more likely to be adopted by farmers. This suggests that an effective extension strategy in Benin should focus on these two control products.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463838","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}
Crop ProtectionPub Date : 2024-06-25DOI: 10.1016/j.cropro.2024.106825
Ermes Ivan Rovetto , Matteo Garbelotto , Salvatore Moricca , Marcos Amato , Federico La Spada , Santa Olga Cacciola
{"title":"A portable fluorescence-based recombinase polymerase amplification assay for the detection of mal secco disease by Plenodomus tracheiphilus","authors":"Ermes Ivan Rovetto , Matteo Garbelotto , Salvatore Moricca , Marcos Amato , Federico La Spada , Santa Olga Cacciola","doi":"10.1016/j.cropro.2024.106825","DOIUrl":"10.1016/j.cropro.2024.106825","url":null,"abstract":"<div><p>In this study, a new diagnostic assay to detect <em>Plenodomus tracheiphilus</em>, the causative agent of mal secco of citrus, was developed based on the recombinase polymerase amplification (RPA) technology. Mal secco is a well-known and damaging vascular disease, affecting primarily lemon (<em>Citrus limon</em>) and, to a lesser extent, other citrus species, including those in the genera <em>Citrus, Fortunella, Poncirus</em> and <em>Severina</em>. The disease poses a considerable threat to lemon production in most of the citrus-producing countries of the Mediterranean region and in the Black Sea area. RPA primers and probes were designed to amplify a 142 bp amplicon from the ITS regions of <em>P. tracheiphilus</em>. The inclusivity and specificity of the RPA assay were tested on gDNA isolated from a panel including 29 strains of various origin of <em>P. tracheiphilus</em> and 18 non-target fungal and oomycete plant pathogens typically isolated from citrus trees. The assay was specific to <em>P. tracheiphilus</em> and had a detection threshold of 1.0 pg of gDNA. Preliminary tests carried out on plant crude extract highlighted RPA's potential for the rapid, user-friendly, and cost-effective field diagnosis of mal secco.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0261219424002539/pdfft?md5=a1ff9a438a8820102181bff31d85731b&pid=1-s2.0-S0261219424002539-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Crop ProtectionPub Date : 2024-06-25DOI: 10.1016/j.cropro.2024.106824
Chuang Wang , Zhihuang Wang , Pengjiang Qian , Zhihua Lu , Wenjun Hu
{"title":"Knowledge correction and ε-insensitive criterion-leveraged zero-order TSK fuzzy system for rice leaf disease diagnosis","authors":"Chuang Wang , Zhihuang Wang , Pengjiang Qian , Zhihua Lu , Wenjun Hu","doi":"10.1016/j.cropro.2024.106824","DOIUrl":"10.1016/j.cropro.2024.106824","url":null,"abstract":"<div><p>The advent of complex application scenarios introduces new challenges for diagnosing rice leaf diseases using machine learning methods. Two critical requirements are identified: 1) The model must exhibit high interpretability to mitigate the adverse effects of incorrect diagnoses; and 2) practical applications often suffer from insufficient samples and noise in rice leaf disease datasets, which requires the model to have strong generalization ability and robustness. However, existing methods still have certain limitations in practical scenarios due to a lack of comprehensive consideration of interpretability, generalization ability, and robustness. To address this issue, this article proposes a novel knowledge correction and <span><math><mrow><mi>ε</mi></mrow></math></span>-insensitive criterion-leveraged zero-order TSK fuzzy system (0-TSK-FS), named KE-0-TSK-FS. The KE-0-TSK-FS method is developed with 0-TSK-FS as the baseline, enhancing the generalization ability of the model by introducing the knowledge correction method and its iterative learning strategy to extract more information from limited samples. In addition, the objective function based on the <span><math><mrow><mi>ε</mi></mrow></math></span>-insensitive criterion makes KE-0-TSK-FS exhibit robustness when the samples contain noise. On three rice leaf disease datasets and six real-world non-rice leaf disease datasets, experiments were conducted on three metrics, namely accuracy, GM, and rule complexity. The experimental results show that the KE-0-TSK-FS method outperforms other comparative algorithms in terms of generalization ability, interpretability, and robustness in the diagnosis of rice leaf diseases under insufficient samples and noise situations, and its average accuracy on rice leaf disease datasets is nearly 3% higher than that of other comparative algorithms.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141556814","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}
Crop ProtectionPub Date : 2024-06-25DOI: 10.1016/j.cropro.2024.106823
Xiaotong Kong , Teng Liu , Xin Chen , Peng Lian , Danlan Zhai , Aimin Li , Jialin Yu
{"title":"Exploring the semi-supervised learning for weed detection in wheat","authors":"Xiaotong Kong , Teng Liu , Xin Chen , Peng Lian , Danlan Zhai , Aimin Li , Jialin Yu","doi":"10.1016/j.cropro.2024.106823","DOIUrl":"https://doi.org/10.1016/j.cropro.2024.106823","url":null,"abstract":"<div><p>Computer vision-based precision spraying of herbicides presents a promising avenue for reducing herbicide input and weed control costs. Nonetheless, weed detection in wheat (<em>Triticum aestivum</em> L.) remains challenging. Developing an effective and reliable neural network for weed detection requires substantial labeled data for training. However, labeling data is time-consuming and labor-intensive. To address this challenge, the present study introduces semi-supervised learning (SSL) into the domain of weed detection in wheat. The performance of four SSL methods was thoroughly evaluated and compared with that of a fully supervised learning (FSL) method on a dataset with a limited amount of labeled images. Experimental results showed that the Fixmatch method, an SSL approach, outperformed the FSL method, exhibiting significantly higher accuracy (ACC) with a limited number of labeled images. The ACC of Fixmatch was 85.4%, which was 7.3% higher than the FSL method. In further analysis, the performance of models trained on a dataset containing 100, 200, 300, 400, 500, or 1000 labeled images per class was tested. Compared with FSL, SSL achieved the greatest improvement when the number of labels was 200. At the same time, Fixmatch achieved satisfactory performance, ACC, recall, and precision reached 94.8%, 94.8%, and 95.2%, respectively, and the F1 score was 95%. In summary, these results suggest that using the SSL method could yield a high-performing model when training with a limited number of labeled images, requiring less training costs and lower demands on manpower.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141596049","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}
Crop ProtectionPub Date : 2024-06-25DOI: 10.1016/j.cropro.2024.106826
Anne-Lise Boixel , Thierry Rouxel , Didier Andrivon , Manu Affichard , Christophe Le May
{"title":"Slipping through the cracks: Challenges and prospects for investigating fungal plant disease complexes","authors":"Anne-Lise Boixel , Thierry Rouxel , Didier Andrivon , Manu Affichard , Christophe Le May","doi":"10.1016/j.cropro.2024.106826","DOIUrl":"10.1016/j.cropro.2024.106826","url":null,"abstract":"<div><p>Plant pathogens frequently do not operate alone when causing diseases. Since the infection process is affected by the interaction between members of the parasite community, this question asks about the efficiency of disease control strategies which are usually tailored to manage only one microbial pathogen at a time. Fungi and oomycetes are among plant disease's most prevalent and damaging causal agents. With the increasing ability to distinguish individual species, thanks to new high-throughput molecular tools, numerous diseases once attributed to a single species are now recognized as being caused by complexes of fungal phytopathogens. How should we approach the study of these complexes? What tools and methodologies are needed to characterize them and decipher their functional interactions? How can we understand and master the drivers of these coinfections and their dynamics under field conditions? Here, we review the current literature on fungal disease complexes to define their commonalities and address some of the current challenges regarding the identification of preferential associations among fungal species indicative of a disease complex and its community dynamics and regulation. This review highlights that fungal species complexes are highly dynamic at geographic and temporal scales and that human actions contributed to the dissemination of new members of species complexes worldwide and to disequilibrium within species complexes, often resulting in more damaging diseases. This review also points to the generally insufficient (or lacking) knowledge of the diversity, dynamics, and functioning of fungal disease complexes, and the risks linked with inappropriate management strategies focusing on only one dominant member of the complex.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463774","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}
Crop ProtectionPub Date : 2024-06-23DOI: 10.1016/j.cropro.2024.106822
Helen Thompson , F. Javier Peris-Felipo , Natalia Peranginangin , Mike Pocock , Ana Lia Gayan-Quijano
{"title":"Cyclobutrifluram (TYMIRIUM® technology): Low risks of a soil applied nematicide and fungicide to non-target soil invertebrates and bees","authors":"Helen Thompson , F. Javier Peris-Felipo , Natalia Peranginangin , Mike Pocock , Ana Lia Gayan-Quijano","doi":"10.1016/j.cropro.2024.106822","DOIUrl":"10.1016/j.cropro.2024.106822","url":null,"abstract":"<div><p>Cyclobutrifluram (TYMIRIUM® technology) is a seed- and soil-applied nematicide and fungicide which protects the plant root mass. Cyclobutrifluram acts by inhibiting mitochondrial complex II electron transport and succinate dehydrogenase inhibition (SDHI). Concerns over the potential adverse effects on non-target species were addressed by assessing whether recommended field application rates of cyclobutrifluram would result in adverse impacts on soil invertebrates or honeybees. Studies conducted under laboratory conditions with the active ingredient and two formulations provided No Observed Effect Concentrations for earthworm (<em>Eisenia andreii</em>) reproduction of 71–171 mg a.i./kg dry soil with no effects on soil mite (<em>Hypoaspis aculifier)</em> reproduction. There were no effects on honeybee (<em>Apis mellifera</em>) adults or larvae following chronic exposure to doses up to 400 and 160 mg/kg diet respectively. Using Brazil as a target market (soybean seed treatment and in-furrow application in fruiting vegetables), our laboratory studies indicate that the risk to two species of soil invertebrates and honeybees of the use of cyclobutrifluram either in-furrow or as a seed treatment was orders of magnitude below any levels of concern.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463851","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}
{"title":"New management systems for northern root-knot nematode (Meloidogyne hapla Chitwood Tylenchida: Heteroderidae) in daylily (Hemerocallis spp.) ornamental plant production fields","authors":"Amanda Howland, Emilie Cole , Luisa Parrado, Marisol Quintanilla","doi":"10.1016/j.cropro.2024.106820","DOIUrl":"10.1016/j.cropro.2024.106820","url":null,"abstract":"<div><p>Michigan has the third largest floriculture industry in the United States, with the production of daylily (<em>Hemerocallis</em> spp.) a top commodity. Daylily is one of the most economically important ornamental plants, yet their production is plagued by plant-parasitic nematodes, especially the northern root-knot nematode, <em>Meloidogyne hapla</em>. Seven treatments in combination with a high-carbon, cow manure compost were selected for a three-year field trial at a commercial nursery in Zeeland, MI to discern the best <em>M. hapla</em> management strategies in daylily field production for its entire production cycle. Treatments included the compost manure by itself, Indemnify as a soil drench and as a pre-plant dip both together and separately, AzaGuard, TerraClean 5.0, and an untreated control. Additionally, a similar multi-year greenhouse trial was conducted and included a new treatment: Majestene 304. Results showed that the high-carbon, cow manure compost + Indemnify as a soil drench by itself and in combination as a pre-plant dip were the most effective treatments in reducing <em>M. hapla</em> population levels; in the greenhouse experiment, Indemnify reduced population levels by 83%. Majestene 304 provided the next best control of <em>M. hapla,</em> yet it had the highest gall ratings; the compost by itself was not effective, having higher <em>M. hapla</em> populations than the control in both experiments. Lastly, both trials emphasize the importance of applying these management strategies every year for the best <em>M. hapla</em> management. These results give the ornamental plant industry new, effective management systems to control <em>M. hapla</em> in ornamental plant field production.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463784","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}
Crop ProtectionPub Date : 2024-06-22DOI: 10.1016/j.cropro.2024.106819
Nai-Hong Hu , Wen-Xuan Zhou , Lin Zhu , Yan-Cheng Li , Xin-Yu Xie , Ru-Yan Hou , Cheng-Long Yin
{"title":"Most appropriate nozzle of six-rotor UAV for prescribed spraying liquid in tea plantation under effects of downwash flow structure in hover","authors":"Nai-Hong Hu , Wen-Xuan Zhou , Lin Zhu , Yan-Cheng Li , Xin-Yu Xie , Ru-Yan Hou , Cheng-Long Yin","doi":"10.1016/j.cropro.2024.106819","DOIUrl":"10.1016/j.cropro.2024.106819","url":null,"abstract":"<div><p>Downwash flow structure development has been an important challenge for Unmanned Aerial Vehicle (UAV) to spray tea although the UAV spray is commonly used in crops, dominantly due to the downwash flow structure development in tea plantations more severe than those in crops. Here the UAV spray for tea cultivation is improved through the relationship between nozzle and spraying liquid, or, by choosing the most appropriate nozzle for the prescribed spraying liquid. As a preliminary step, the UAV spray has been studied under effects of downwash flow structure in hover. The six-rotor UAV with four commonly-used nozzles (VP110-02, XR110-02, FPV110-02, and KZ80-04) is used as the representative. Bifenthrin, widely sprayed for tea cultivation, is used as the prescribed spraying liquid. A three-dimensional model of nozzle & flow fragmentation is developed to estimate the nozzle performances. This study demonstrates that nozzle KZ80-04 is the most suitable for Bifenthrin in tea plantation and provides insight into designing effective UAV spray in crops.</p></div>","PeriodicalId":10785,"journal":{"name":"Crop Protection","volume":null,"pages":null},"PeriodicalIF":2.5,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141463893","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}