Smart pest control is crucial for building farmresilience andensuringsustainable agriculture inthe faceof climate change and environmental challenges.To achieve effective intelligent monitoring systems,agricultural pe...Smart pest control is crucial for building farmresilience andensuringsustainable agriculture inthe faceof climate change and environmental challenges.To achieve effective intelligent monitoring systems,agricultural pest and disease detectionmust overcome three fundamental challenges:feature degradation in dense vegetation environments,limited detection capability for sub-32×32 pixel targets,and inadequate bounding box regression for irregular pest morphologies.This study proposes YOLOv12-KMA,a novel detection framework that addresses these limitations through four synergistic architectural innovations,specifically optimized for agricultural environments.First,we introduce efficient multi-head attention(C3K2-EMA),which reduces noise interference by 41%through selective regional attention while maintaining O(k⋅n⋅d)computational complexity vs.O(n2⋅d)for standard attention.Second,we develop A2C2f-KAN modules embedding Kolmogorov-Arnold networks(KAN)with B-spline activation functions,achieving 15%better feature representation for small targets without global distortion.Third,we propose minimum point distance intersection over union(MPDIoU)loss that resolves aspect ratio degeneration issues in complete intersection over union(CIoU),accelerating convergence by 23%for irregular pest shapes.Fourth,we implement the dynamic sampling(DySample)module that reduces computational overhead by 72%while preserving 94%feature fidelity compared to conventional interpolation methods.Comprehensive validation on 8742 annotated agricultural images demonstrates significant improvements:2.6 percentage point increase in mean average precision(mAP)@0.5(91.0%→93.6%),3.2 percentage point gain in mAP@0.5:0.95,with precision and recall improvements of 4.8%and 2.4%,respectively.Statistical analysis confirms significance(p<0.001)with large effect sizes(η2=0.78).The optimized architecture maintains real-time performance at 159 frames per second(FPS)on consumer hardware,enabling practical deployment in precision agriculture monitoring systems.展开更多
Cruciferous vegetables are important edible vegetable crops.However,they are susceptible to various pests during their growth process,which requires real-time and accurate monitoring of these pests for pest forecastin...Cruciferous vegetables are important edible vegetable crops.However,they are susceptible to various pests during their growth process,which requires real-time and accurate monitoring of these pests for pest forecasting and scientific control.Hanging yellow sticky boards is a common way to monitor and trap those pests which are attracted to the yellow color.To achieve real-time,low-cost,intelligent monitoring of these vegetable pests on the boards,we established an intelligent monitoring system consisting of a smart camera,a web platform and a pest detection algorithm deployed on a server.After the operator sets the monitoring preset points and shooting time of the camera on the system platform,the camera in the field can automatically collect images of multiple yellow sticky boards at fixed places and times every day.The pests trapped on the yellow sticky boards in vegetable fields,Plutella xylostella,Phyllotreta striolata and flies,are very small and susceptible to deterioration and breakage,which increases the difficulty of model detection.To solve the problem of poor recognition due to the small size and breaking of the pest bodies,we propose an intelligent pest detection algorithm based on an improved Cascade R-CNN model for three important cruciferous crop pests.The algorithm uses an overlapping sliding window method,an improved Res2Net network as the backbone network,and a recursive feature pyramid network as the neck network.The results of field tests show that the algorithm achieves good detection results for the three target pests on the yellow sticky board images,with precision levels of 96.5,92.2 and 75.0%,and recall levels of 96.6,93.1 and 74.7%,respectively,and an F_(1) value of 0.880.Compared with other algorithms,our algorithm has a significant advantage in its ability to detect small target pests.To accurately obtain the data for the newly added pests each day,a two-stage pest matching algorithm was proposed.The algorithm performed well and achieved results that were highly consistent with manual counting,with a mean error of only 2.2%.This intelligent monitoring system realizes precision,good visualization,and intelligent vegetable pest monitoring,which is of great significance as it provides an effective pest prevention and control option for farmers.展开更多
Background Cotton crop is infested by numerous arthropod pests from sowing to harvesting,causing substantial direct and indirect yield losses.Knowledge of seasonal population trends and the relative occurrence of pest...Background Cotton crop is infested by numerous arthropod pests from sowing to harvesting,causing substantial direct and indirect yield losses.Knowledge of seasonal population trends and the relative occurrence of pests and their natural enemies is required to minimize the pest population and yield losses.In the current study,analysis of the seasonal population trend of pests and natural enemies and their relative occurrence on cultivars of three cotton species in Central India has been carried out.Results A higher number and diversity of sucking pests were observed during the vegetative cotton growth stage(60 days after sowing),declining as the crop matured.With the exception of cotton jassid(Amrasca biguttula biguttula Ishida),which caused significant crop damage mainly from August to September;populations of other sucking insects seldom reached economic threshold levels(ETL)throughout the studied period.The bollworm complex populations were minimal,except for the pink bollworm(Pectinophora gossypiella Saunders),which re-emerged as a menace to cotton crops during the cotton cropping season 2017–2018 due to resistance development against Bt-cotton.A reasonably good number of predatory arthropods,including coccinellids,lacewings,and spiders,were found actively preying on the arthropod pest complex of the cotton crop during the early vegetative growth stage.Linear regression indicates a significant relationship between green boll infestations and pink bollworm moths in pheromone traps.Multiple linear regression analyse showed mean weekly weather at one-or two-week lag periods had a significant impact on sucking pest population(cotton aphid,cotton jassid,cotton whitefly,and onion thrips)fluctuation.Gossypium hirsutum cultivars RCH 2 and DCH 32,and G.barbadense cultivar Suvin were found susceptible to cotton jassid and onion thrips.Phule Dhanvantary,an G.arboreum cotton cultivar,demonstrated the highest tolerance among all evaluated cultivars against all sucking pests.Conclusion These findings have important implications for pest management in cotton crops.Susceptible cultivars warrant more attention for plant protection measures,making them more input-intensive.The choice of appropriate cultivars can help minimize input costs,thereby increasing net returns for cotton farmers.展开更多
Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate ide...Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate identification of both pest developmental stages and their natural predators is crucial for effective pest control and maintaining ecological balance.However,conventional field surveys are often subjective,inefficient,and lack traceability.To overcome these limitations,this study proposed RiceInsectID,a two-stage cascaded detection method designed to identify and count tiny rice pests and their natural predators from white flat plate images captured by head-worn AR glasses.The method recognizes 25 insect classes,including 17 instars of rice planthoppers,2 instars of leafhoppers,4 spider species(Araneae),as well as Miridae and rove beetles(Staphylinidae Latreille).At the first coarse-grained detection stage,16 visually similar classes are consolidated into 6 broader categories and detected using an enhanced YOLOv6 model.To improve small object detection and address class imbalance,the fullregion overlapping sliding slices and target pasting(FOSTP)algorithm was applied,increasing the mean average precision at a 50%IoU threshold(mAP50)by 35.46%over the baseline YOLOv6.Feature extraction and fusion were further improved by incorporating an efficient channel attention path aggregation feature pyramid network(ECA-PAFPN)and adaptive structure feature fusion(ASFF)modules,while the balanced classification mosaic(BCM)enhanced detection of minority classes.With test-time augmentation(TTA),mAP50 improved by an additional 2.06%,reaching 84.71%.At the second fine-grained classification stage,each of the six broad classes from the first stage is further classified using individual ResNet50 models.Online data augmentation and transfer learning were employed to significantly enhance generalization.Compared with the baseline YOLOv6,the two-stage cascaded method improved recall by 4.06%,precision by 3.79%,and the F1-score by 3.92%.Overall,RiceInsectID achieved 82.85%recall,80.62%precision,and an F1-score of 81.72%,demonstrating an efficient and practical solution for monitoring tiny rice pests and their natural predators in paddy fields.This study provides valuable insights for ecosystem monitoring and supporting sustainable pest management in rice agriculture.展开更多
Cowpea, Vigna unguiculata L. Walp, is an important food grain legume in Niger facing production losses due to insect pests. This study aims to determine the efficiency of non-chemical methods for managing these pests....Cowpea, Vigna unguiculata L. Walp, is an important food grain legume in Niger facing production losses due to insect pests. This study aims to determine the efficiency of non-chemical methods for managing these pests. A trial was conducted during the 2020 and 2022 cropping seasons at the INRAN station in the Maradi region. A Fischer experimental design with 6 repetitions was used to compare 4 treatments: synthetic chemical pesticide;the entomopathogenic fungus Beauveria bassiana;aqueous extracts of neem seeds, and control. Observations were carried out every three days. The cowpea pod-sucking bug, pod borer, and thrips were the main insect pests recorded. In terms of effectiveness, the synthetic pesticide was the best treatment. It reduced insect pest densities by 71.35% to 90.40% in 2020 and by 35.11% to 42.13% in 2022. Grain yields varied between treatments. Neem seed extract followed the synthetic pesticide and significantly reduced insect infestations in both years. The synthetic pesticide and neem seed extract resulted in yields 3 to 5 times higher than the control treatment in 2020. By contrast, B. bassiana 115 and neem seed extract produced similar yields in 2022. Therefore, the results of this study showed that B. bassiana 115 and neem seed extract have insecticidal potential and could be used as an ecological alternative for managing cowpea insect pests in the Sahel.展开更多
Cowpea, Vigna unguiculata (L.) Walp. is an economically important seed legume that helps combat food and nutrition insecurity in the Sahel, particularly Niger. However, its yield remains low due to insect pest attacks...Cowpea, Vigna unguiculata (L.) Walp. is an economically important seed legume that helps combat food and nutrition insecurity in the Sahel, particularly Niger. However, its yield remains low due to insect pest attacks. This study was conducted at a station and in seven villages in the Maradi and Tahoua regions. It aimed to test the effectiveness of neem seed biopesticides [Azadirachta indica A. Juss] and sanitized human urine for integrated insect pest management. The cowpea variety UAM09 1055-6 was used for the experiments. The experimental trial was a Fisher block design consisting of five treatments: neem oil, neem seed extract (NSE), hygienized human urine (HHU), chemical pesticide, and a control, replicated five times at the station and twice in farmers’ environments. The study shows that Megalurothrips sjostedti Trybom, Clavigralla tomentosicollis Stål and Maruca vitrata Fabricius are the main insect pests. Plots treated with synthetic pesticides were the least infested by C. tomentosicollis. They were followed by neem seed extract and HHU treatments, which recorded an infestation level of 2.44 and 20.5 times lower than controls at the station and in farming environments. The density of thrips was 1.06 to 32.6 times lower in treated plots compared to controls. The proportion of pods damaged by M. vitrata was 1.95, 2.55, and 2.77 times lower in plots treated with HHU, NSE, and synthetic pesticide, respectively, compared to controls. Grain yields were 1.80 and 2.62 times higher in UHH and NSE treatments compared to control plots, both at the station and in farmers’ environments. A yield increase of 44.58% and 61.92% was noted for these treatments at the station and in farmers’ environments, respectively. These results may promote the dissemination of NSE and HHU biopesticide technologies in rural areas as an alternative method for integrated pest management of cowpeas.展开更多
Cotton production faces significant challenges from insect pests,with chemical pesticide use becoming increasingly limited by resistance and environmental concerns.This study explores the potential use of caffeine,a n...Cotton production faces significant challenges from insect pests,with chemical pesticide use becoming increasingly limited by resistance and environmental concerns.This study explores the potential use of caffeine,a natural plant alkaloid,as an environmentally friendly insect resistance strategy in cotton.Exogenous caffeine application demonstrated potent insecticidal effects against cotton bollworm(Helicoverpa armigera)larvae,with concentrations≥2 mg mL−1 causing near-complete feeding cessation and up to 70%larval mortality.Building on this,we engineered transgenic cotton(Gossypium hirsutum cv.Jin668)for heterologous caffeine biosynthesis by introducing three key N-methyltransferase genes(CaXMT1,CaMXMT1,CaDXMT1)by multiple gene transformation.Transgenic lines expressing all three genes showed remarkable caffeine accumulation(up to 3.59 mg g−1 dry weight),whereas two-gene combinations exhibited wild-type-level production.Feeding preference assays revealed that caffeine-enriched cotton strongly deterred feeding by H.armigera.Non-choice feeding trials demonstrated reduced leaf consumption and reduced larval growth in H.armigera fed on caffeine-producing cotton.The study highlights the effectiveness of synthetic biology approaches using the TGSII-UNiE multigene stacking system,despite challenges in transgene stability.This work advances plant-derived insect resistance research and provides a sustainable framework for reducing chemical pesticide reliance in cotton production,while underscoring unique potential of cotton as a synthetic biology platform for secondary metabolite engineering.展开更多
To further enhance the yield and quality of kiwifruit and promote the sustainable development of the kiwifruit industry,this paper summarized the characteristics,damage sites,and control methods of major kiwifruit dis...To further enhance the yield and quality of kiwifruit and promote the sustainable development of the kiwifruit industry,this paper summarized the characteristics,damage sites,and control methods of major kiwifruit diseases and pests.It pointed out the main issues in current kiwifruit pest and disease management and proposed corresponding solutions.The prevention and control of kiwifruit pests should adhere to the principle of"prevention first,integrated management",and standardized planting modes should be implemented.In this process,priority should be given to agricultural,physical,and biological control methods to effectively reduce the use of chemical pesticides.展开更多
Chak-hao,the Forbidden Rice from Manipur,India,is an aromatic,purplish-black rice variety that has been awarded a geographical indication tag to preserve and promote its traditional cultivation in Manipur,India.Althou...Chak-hao,the Forbidden Rice from Manipur,India,is an aromatic,purplish-black rice variety that has been awarded a geographical indication tag to preserve and promote its traditional cultivation in Manipur,India.Although Chak-hao is a hardy landrace with field tolerance to biotic stress,its grains are highly susceptible to storage pest infestations,particularly those caused by the rice weevil(Sitophilus oryzae).This severely compromises its commercial storage quality,as pest damage reduces both nutritional value and quantity.展开更多
In addition to the negative consequences of climate change,sucking pest complexes severely limited cotton yields in the recent past.Although the damage caused by bollworms was much reduced by utilizing Bt cotton,the e...In addition to the negative consequences of climate change,sucking pest complexes severely limited cotton yields in the recent past.Although the damage caused by bollworms was much reduced by utilizing Bt cotton,the emergence of sucking pests(such as aphids,thrips,and whiteflies)poses a serious threat to cotton production,as they reduce lint yield by 40%–60%finally.Additionally,these pests also caused yield losses by spreading viral diseases.Promoting innovative and thorough control methods is necessary to counter the threat posed by these sucking pests.Such initiatives necessitate a multifaceted strategy that combines next-generation breeding technology and pest management techniques to produce novel cotton cultivars that are resistant to sucking pests.The discovery of novel genes and regulatory factors linked to cotton’s resistance to sucking pests will be possible by the combination of next-generation breeding technologies and omics approaches and employing those tools on special resistant donors.Continuous research aimed at understanding the genetic basis of insect resistance and improving integrated pest management(IPM)techniques is crucial to the sustainability and resilience of cotton cropping systems.To this end,a sustainable and viable strategy to protect cotton fields from sucking pests is outlined.展开更多
Leveraging the achievements of the smart meteorological system nationwide,a meteorological monitoring and early warning system for alfalfa pests and diseases can be formed through the establishment of four systems,nam...Leveraging the achievements of the smart meteorological system nationwide,a meteorological monitoring and early warning system for alfalfa pests and diseases can be formed through the establishment of four systems,namely,"real-time monitoring system,forecasting and prediction system,monitoring and early warning system,and smart service system".It will enable intelligent,dynamic meteorological monitoring,early warning,and forecasting services for the occurrence and development of alfalfa pests and diseases,providing technical support for scientifically controlling their harm and improving yield and quality.展开更多
Citrus is the highest-yielding fruit crop globally,with China ranking first in both cultivation area and production worldwide.During citrus growth,the crop is often damaged by various pests such as Diaphorina citri,sc...Citrus is the highest-yielding fruit crop globally,with China ranking first in both cultivation area and production worldwide.During citrus growth,the crop is often damaged by various pests such as Diaphorina citri,scale insects,and aphids.Among these,D.citri,the vector of Huanglongbing(citrus greening disease),is particularly severe and has caused substantial economic losses globally.Currently,chemical pesticides remain the primary method for controlling citrus pests.However,their overuse can lead to pest resistance and excessive pesticide residues,posing threats to human health and the environment.Therefore,utilizing natural enemy insects for biological control is of significant importance.This paper systematically reviewed the research progress in artificial rearing of natural enemy insects for citrus pests,aiming to provide references for green pest management in citrus cultivation and promote the healthy and sustainable development of the citrus industry.展开更多
Chief Editor:Lai Zhongxiong,male,born in December 1966,Ph.D.,researcher,doctoral supervisor.Deputy dean of New Rural Deve lopment Research Institute,Fujian Agricultura1 and Forestry University;director of Horticultura...Chief Editor:Lai Zhongxiong,male,born in December 1966,Ph.D.,researcher,doctoral supervisor.Deputy dean of New Rural Deve lopment Research Institute,Fujian Agricultura1 and Forestry University;director of Horticultural Plant Bio-eng ineering Institute(Subtropical Fruit Research Institute).展开更多
文摘Smart pest control is crucial for building farmresilience andensuringsustainable agriculture inthe faceof climate change and environmental challenges.To achieve effective intelligent monitoring systems,agricultural pest and disease detectionmust overcome three fundamental challenges:feature degradation in dense vegetation environments,limited detection capability for sub-32×32 pixel targets,and inadequate bounding box regression for irregular pest morphologies.This study proposes YOLOv12-KMA,a novel detection framework that addresses these limitations through four synergistic architectural innovations,specifically optimized for agricultural environments.First,we introduce efficient multi-head attention(C3K2-EMA),which reduces noise interference by 41%through selective regional attention while maintaining O(k⋅n⋅d)computational complexity vs.O(n2⋅d)for standard attention.Second,we develop A2C2f-KAN modules embedding Kolmogorov-Arnold networks(KAN)with B-spline activation functions,achieving 15%better feature representation for small targets without global distortion.Third,we propose minimum point distance intersection over union(MPDIoU)loss that resolves aspect ratio degeneration issues in complete intersection over union(CIoU),accelerating convergence by 23%for irregular pest shapes.Fourth,we implement the dynamic sampling(DySample)module that reduces computational overhead by 72%while preserving 94%feature fidelity compared to conventional interpolation methods.Comprehensive validation on 8742 annotated agricultural images demonstrates significant improvements:2.6 percentage point increase in mean average precision(mAP)@0.5(91.0%→93.6%),3.2 percentage point gain in mAP@0.5:0.95,with precision and recall improvements of 4.8%and 2.4%,respectively.Statistical analysis confirms significance(p<0.001)with large effect sizes(η2=0.78).The optimized architecture maintains real-time performance at 159 frames per second(FPS)on consumer hardware,enabling practical deployment in precision agriculture monitoring systems.
基金supported by the Collaborative Innovation Center Project of Guangdong Academy of Agricultural Sciences,China(XTXM202202).
文摘Cruciferous vegetables are important edible vegetable crops.However,they are susceptible to various pests during their growth process,which requires real-time and accurate monitoring of these pests for pest forecasting and scientific control.Hanging yellow sticky boards is a common way to monitor and trap those pests which are attracted to the yellow color.To achieve real-time,low-cost,intelligent monitoring of these vegetable pests on the boards,we established an intelligent monitoring system consisting of a smart camera,a web platform and a pest detection algorithm deployed on a server.After the operator sets the monitoring preset points and shooting time of the camera on the system platform,the camera in the field can automatically collect images of multiple yellow sticky boards at fixed places and times every day.The pests trapped on the yellow sticky boards in vegetable fields,Plutella xylostella,Phyllotreta striolata and flies,are very small and susceptible to deterioration and breakage,which increases the difficulty of model detection.To solve the problem of poor recognition due to the small size and breaking of the pest bodies,we propose an intelligent pest detection algorithm based on an improved Cascade R-CNN model for three important cruciferous crop pests.The algorithm uses an overlapping sliding window method,an improved Res2Net network as the backbone network,and a recursive feature pyramid network as the neck network.The results of field tests show that the algorithm achieves good detection results for the three target pests on the yellow sticky board images,with precision levels of 96.5,92.2 and 75.0%,and recall levels of 96.6,93.1 and 74.7%,respectively,and an F_(1) value of 0.880.Compared with other algorithms,our algorithm has a significant advantage in its ability to detect small target pests.To accurately obtain the data for the newly added pests each day,a two-stage pest matching algorithm was proposed.The algorithm performed well and achieved results that were highly consistent with manual counting,with a mean error of only 2.2%.This intelligent monitoring system realizes precision,good visualization,and intelligent vegetable pest monitoring,which is of great significance as it provides an effective pest prevention and control option for farmers.
基金Funding support for the Crop Pest Surveillance and Advisory Project(CROPSAP)。
文摘Background Cotton crop is infested by numerous arthropod pests from sowing to harvesting,causing substantial direct and indirect yield losses.Knowledge of seasonal population trends and the relative occurrence of pests and their natural enemies is required to minimize the pest population and yield losses.In the current study,analysis of the seasonal population trend of pests and natural enemies and their relative occurrence on cultivars of three cotton species in Central India has been carried out.Results A higher number and diversity of sucking pests were observed during the vegetative cotton growth stage(60 days after sowing),declining as the crop matured.With the exception of cotton jassid(Amrasca biguttula biguttula Ishida),which caused significant crop damage mainly from August to September;populations of other sucking insects seldom reached economic threshold levels(ETL)throughout the studied period.The bollworm complex populations were minimal,except for the pink bollworm(Pectinophora gossypiella Saunders),which re-emerged as a menace to cotton crops during the cotton cropping season 2017–2018 due to resistance development against Bt-cotton.A reasonably good number of predatory arthropods,including coccinellids,lacewings,and spiders,were found actively preying on the arthropod pest complex of the cotton crop during the early vegetative growth stage.Linear regression indicates a significant relationship between green boll infestations and pink bollworm moths in pheromone traps.Multiple linear regression analyse showed mean weekly weather at one-or two-week lag periods had a significant impact on sucking pest population(cotton aphid,cotton jassid,cotton whitefly,and onion thrips)fluctuation.Gossypium hirsutum cultivars RCH 2 and DCH 32,and G.barbadense cultivar Suvin were found susceptible to cotton jassid and onion thrips.Phule Dhanvantary,an G.arboreum cotton cultivar,demonstrated the highest tolerance among all evaluated cultivars against all sucking pests.Conclusion These findings have important implications for pest management in cotton crops.Susceptible cultivars warrant more attention for plant protection measures,making them more input-intensive.The choice of appropriate cultivars can help minimize input costs,thereby increasing net returns for cotton farmers.
基金supported by the National Key Research Program of China during the 14th Five-Year Plan Period(Grant No.2021YFD1401100)the Zhejiang Provincial Natural Science Foundation of China(Grant No.LTGN24C140007)the‘San Nong Jiu Fang’Sciences and Technologies Cooperation Project of Zhejiang Province,China(Grant No.2024SNJF010)。
文摘Rice crops are frequently threatened by pests such as rice planthoppers(Nilaparvata lugens,Sogatella furcifera,and Laodelphax striatellus)and leafhoppers(Cicadellidae),which cause significant yield losses.Accurate identification of both pest developmental stages and their natural predators is crucial for effective pest control and maintaining ecological balance.However,conventional field surveys are often subjective,inefficient,and lack traceability.To overcome these limitations,this study proposed RiceInsectID,a two-stage cascaded detection method designed to identify and count tiny rice pests and their natural predators from white flat plate images captured by head-worn AR glasses.The method recognizes 25 insect classes,including 17 instars of rice planthoppers,2 instars of leafhoppers,4 spider species(Araneae),as well as Miridae and rove beetles(Staphylinidae Latreille).At the first coarse-grained detection stage,16 visually similar classes are consolidated into 6 broader categories and detected using an enhanced YOLOv6 model.To improve small object detection and address class imbalance,the fullregion overlapping sliding slices and target pasting(FOSTP)algorithm was applied,increasing the mean average precision at a 50%IoU threshold(mAP50)by 35.46%over the baseline YOLOv6.Feature extraction and fusion were further improved by incorporating an efficient channel attention path aggregation feature pyramid network(ECA-PAFPN)and adaptive structure feature fusion(ASFF)modules,while the balanced classification mosaic(BCM)enhanced detection of minority classes.With test-time augmentation(TTA),mAP50 improved by an additional 2.06%,reaching 84.71%.At the second fine-grained classification stage,each of the six broad classes from the first stage is further classified using individual ResNet50 models.Online data augmentation and transfer learning were employed to significantly enhance generalization.Compared with the baseline YOLOv6,the two-stage cascaded method improved recall by 4.06%,precision by 3.79%,and the F1-score by 3.92%.Overall,RiceInsectID achieved 82.85%recall,80.62%precision,and an F1-score of 81.72%,demonstrating an efficient and practical solution for monitoring tiny rice pests and their natural predators in paddy fields.This study provides valuable insights for ecosystem monitoring and supporting sustainable pest management in rice agriculture.
文摘Cowpea, Vigna unguiculata L. Walp, is an important food grain legume in Niger facing production losses due to insect pests. This study aims to determine the efficiency of non-chemical methods for managing these pests. A trial was conducted during the 2020 and 2022 cropping seasons at the INRAN station in the Maradi region. A Fischer experimental design with 6 repetitions was used to compare 4 treatments: synthetic chemical pesticide;the entomopathogenic fungus Beauveria bassiana;aqueous extracts of neem seeds, and control. Observations were carried out every three days. The cowpea pod-sucking bug, pod borer, and thrips were the main insect pests recorded. In terms of effectiveness, the synthetic pesticide was the best treatment. It reduced insect pest densities by 71.35% to 90.40% in 2020 and by 35.11% to 42.13% in 2022. Grain yields varied between treatments. Neem seed extract followed the synthetic pesticide and significantly reduced insect infestations in both years. The synthetic pesticide and neem seed extract resulted in yields 3 to 5 times higher than the control treatment in 2020. By contrast, B. bassiana 115 and neem seed extract produced similar yields in 2022. Therefore, the results of this study showed that B. bassiana 115 and neem seed extract have insecticidal potential and could be used as an ecological alternative for managing cowpea insect pests in the Sahel.
文摘Cowpea, Vigna unguiculata (L.) Walp. is an economically important seed legume that helps combat food and nutrition insecurity in the Sahel, particularly Niger. However, its yield remains low due to insect pest attacks. This study was conducted at a station and in seven villages in the Maradi and Tahoua regions. It aimed to test the effectiveness of neem seed biopesticides [Azadirachta indica A. Juss] and sanitized human urine for integrated insect pest management. The cowpea variety UAM09 1055-6 was used for the experiments. The experimental trial was a Fisher block design consisting of five treatments: neem oil, neem seed extract (NSE), hygienized human urine (HHU), chemical pesticide, and a control, replicated five times at the station and twice in farmers’ environments. The study shows that Megalurothrips sjostedti Trybom, Clavigralla tomentosicollis Stål and Maruca vitrata Fabricius are the main insect pests. Plots treated with synthetic pesticides were the least infested by C. tomentosicollis. They were followed by neem seed extract and HHU treatments, which recorded an infestation level of 2.44 and 20.5 times lower than controls at the station and in farming environments. The density of thrips was 1.06 to 32.6 times lower in treated plots compared to controls. The proportion of pods damaged by M. vitrata was 1.95, 2.55, and 2.77 times lower in plots treated with HHU, NSE, and synthetic pesticide, respectively, compared to controls. Grain yields were 1.80 and 2.62 times higher in UHH and NSE treatments compared to control plots, both at the station and in farmers’ environments. A yield increase of 44.58% and 61.92% was noted for these treatments at the station and in farmers’ environments, respectively. These results may promote the dissemination of NSE and HHU biopesticide technologies in rural areas as an alternative method for integrated pest management of cowpeas.
基金supported by the National Natural Science Foundation of China (32325039)
文摘Cotton production faces significant challenges from insect pests,with chemical pesticide use becoming increasingly limited by resistance and environmental concerns.This study explores the potential use of caffeine,a natural plant alkaloid,as an environmentally friendly insect resistance strategy in cotton.Exogenous caffeine application demonstrated potent insecticidal effects against cotton bollworm(Helicoverpa armigera)larvae,with concentrations≥2 mg mL−1 causing near-complete feeding cessation and up to 70%larval mortality.Building on this,we engineered transgenic cotton(Gossypium hirsutum cv.Jin668)for heterologous caffeine biosynthesis by introducing three key N-methyltransferase genes(CaXMT1,CaMXMT1,CaDXMT1)by multiple gene transformation.Transgenic lines expressing all three genes showed remarkable caffeine accumulation(up to 3.59 mg g−1 dry weight),whereas two-gene combinations exhibited wild-type-level production.Feeding preference assays revealed that caffeine-enriched cotton strongly deterred feeding by H.armigera.Non-choice feeding trials demonstrated reduced leaf consumption and reduced larval growth in H.armigera fed on caffeine-producing cotton.The study highlights the effectiveness of synthetic biology approaches using the TGSII-UNiE multigene stacking system,despite challenges in transgene stability.This work advances plant-derived insect resistance research and provides a sustainable framework for reducing chemical pesticide reliance in cotton production,while underscoring unique potential of cotton as a synthetic biology platform for secondary metabolite engineering.
基金Supported by College-level Scientific Research Project of Guizhou Industry Polytechnic College(2023ZK112023ZK10)Scientific and Technological Innovation Team Project of Guizhou Industry Polytechnic College(2023CXTD03).
文摘To further enhance the yield and quality of kiwifruit and promote the sustainable development of the kiwifruit industry,this paper summarized the characteristics,damage sites,and control methods of major kiwifruit diseases and pests.It pointed out the main issues in current kiwifruit pest and disease management and proposed corresponding solutions.The prevention and control of kiwifruit pests should adhere to the principle of"prevention first,integrated management",and standardized planting modes should be implemented.In this process,priority should be given to agricultural,physical,and biological control methods to effectively reduce the use of chemical pesticides.
文摘Chak-hao,the Forbidden Rice from Manipur,India,is an aromatic,purplish-black rice variety that has been awarded a geographical indication tag to preserve and promote its traditional cultivation in Manipur,India.Although Chak-hao is a hardy landrace with field tolerance to biotic stress,its grains are highly susceptible to storage pest infestations,particularly those caused by the rice weevil(Sitophilus oryzae).This severely compromises its commercial storage quality,as pest damage reduces both nutritional value and quantity.
基金M/s.RASI Seeds Pvt.Ltd.,Attur,Tamil Nadu,India for their generous financial assistance in setting up a MAS study in cotton for genetic improvement of sucking pest resistance.
文摘In addition to the negative consequences of climate change,sucking pest complexes severely limited cotton yields in the recent past.Although the damage caused by bollworms was much reduced by utilizing Bt cotton,the emergence of sucking pests(such as aphids,thrips,and whiteflies)poses a serious threat to cotton production,as they reduce lint yield by 40%–60%finally.Additionally,these pests also caused yield losses by spreading viral diseases.Promoting innovative and thorough control methods is necessary to counter the threat posed by these sucking pests.Such initiatives necessitate a multifaceted strategy that combines next-generation breeding technology and pest management techniques to produce novel cotton cultivars that are resistant to sucking pests.The discovery of novel genes and regulatory factors linked to cotton’s resistance to sucking pests will be possible by the combination of next-generation breeding technologies and omics approaches and employing those tools on special resistant donors.Continuous research aimed at understanding the genetic basis of insect resistance and improving integrated pest management(IPM)techniques is crucial to the sustainability and resilience of cotton cropping systems.To this end,a sustainable and viable strategy to protect cotton fields from sucking pests is outlined.
文摘Leveraging the achievements of the smart meteorological system nationwide,a meteorological monitoring and early warning system for alfalfa pests and diseases can be formed through the establishment of four systems,namely,"real-time monitoring system,forecasting and prediction system,monitoring and early warning system,and smart service system".It will enable intelligent,dynamic meteorological monitoring,early warning,and forecasting services for the occurrence and development of alfalfa pests and diseases,providing technical support for scientifically controlling their harm and improving yield and quality.
基金Supported by National Innovation and Entrepreneurship Training Program for College Students(202410580010)Construction Project of the Zhaoqing Citrus Comprehensive Experimental Station Platform under the National Modern Agricultural Industry Technology System(202413004)+1 种基金Key Projects of the Second Round Project of High-quality Development in Hundred Counties,Thousands Towns and Ten Thousand Villages for Rural Science and Technology Special Commissioners Dispatched by the Guangdong Provincial Department of Science and Technology(KTP20240684)Doctoral Scientific Research Initiation Fund Project of Zhaoqing University(611/230009).
文摘Citrus is the highest-yielding fruit crop globally,with China ranking first in both cultivation area and production worldwide.During citrus growth,the crop is often damaged by various pests such as Diaphorina citri,scale insects,and aphids.Among these,D.citri,the vector of Huanglongbing(citrus greening disease),is particularly severe and has caused substantial economic losses globally.Currently,chemical pesticides remain the primary method for controlling citrus pests.However,their overuse can lead to pest resistance and excessive pesticide residues,posing threats to human health and the environment.Therefore,utilizing natural enemy insects for biological control is of significant importance.This paper systematically reviewed the research progress in artificial rearing of natural enemy insects for citrus pests,aiming to provide references for green pest management in citrus cultivation and promote the healthy and sustainable development of the citrus industry.
文摘Chief Editor:Lai Zhongxiong,male,born in December 1966,Ph.D.,researcher,doctoral supervisor.Deputy dean of New Rural Deve lopment Research Institute,Fujian Agricultura1 and Forestry University;director of Horticultural Plant Bio-eng ineering Institute(Subtropical Fruit Research Institute).
