This work uses cloud-resolving simulations to study mock-Walker cells driven by a specified sea surface temperature(SST).The associated precipitation in the mock-Walker cells exhibits three different modes,including a...This work uses cloud-resolving simulations to study mock-Walker cells driven by a specified sea surface temperature(SST).The associated precipitation in the mock-Walker cells exhibits three different modes,including a single peak of precipitation over the SST maximum(mode 1),symmetric double peaks of precipitation straddling the SST maximum(mode 2),and a single peak of precipitation on one side of the SST maximum(mode 3).The three modes are caused by three distinct convective activity center migration traits.Analyses indicate that the virtual effect of water vapor plays an important role in differentiating the three modes.When the SST gradient is large,the virtual effect may be strong enough to overcome the temperature effect,generating a low-level low-pressure anomaly below the ascending branch of the Walker cell off the center.The results here highlight the importance of the virtual effect of water vapor and its interaction with convection and large-scale circulation in the Walker circulation.展开更多
在原木木材材积检测中,由于端面伐痕、开裂和阴影等因素容易影响智能检测系统的准确性和稳定性,一直以来,端面识别定位属于一个难点问题。对多个YOLO(You Only Look Once)版本模型的原理分析和试验验证,融合这些YOLO版本模型优点,在yolo...在原木木材材积检测中,由于端面伐痕、开裂和阴影等因素容易影响智能检测系统的准确性和稳定性,一直以来,端面识别定位属于一个难点问题。对多个YOLO(You Only Look Once)版本模型的原理分析和试验验证,融合这些YOLO版本模型优点,在yolo3主干网络基础上,采用数据增强、特征融合和损失函数等优化手段,构建更加适用于原木检测的端到端深度学习模型YOLO-Raw Wood(YOLO-RW),用于原木木材材积图像的准确识别和定位。为检验YOLO-RW模型性能,设计多组数据试验。结果表明,同比基准模型,YOLO-RW模型具有更高的端面识别精度和鲁棒性,在准确率和召回率评价指标平均值上,分别高出基准模型6.95%和2.38%以上。研究表明,YOLO-RW模型在原木木材材积检测领域有着较好的应用价值,亦可为相关目标识别领域的研究提供借鉴。展开更多
Thosea sinensis Walker(TSW)rapidly spreads and severely damages the tea plants.Therefore,finding a reliable operational method for identifying the TSW-damaged areas via remote sensing has been a focus of a research co...Thosea sinensis Walker(TSW)rapidly spreads and severely damages the tea plants.Therefore,finding a reliable operational method for identifying the TSW-damaged areas via remote sensing has been a focus of a research community.Such methods also enable us to calculate the precise application of pesticides and prevent the subsequent spread of the pests.In this work,based on the unmanned aerial vehicle(UAV)platform,five band images of multispectral red-edge camera were obtained and used for monitoring the TSW in tea plantations.By combining the minimum redundancy maximum relevance(mRMR)with the selected spectral features,a comprehensive spectral selection strategy was proposed.Then,based on the selected spectral features,three classic machine learning algorithms,including random forest(RF),support vector machine(SVM),and k-nearest neighbors(KNN)were used to construct the pest monitoring model and were evaluated and compared.The results showed that the strategy proposed in this work obtained ideal monitoring accuracy by only using the combination of a few optimized features(2 or 4).In order to differentiate the healthy and TSW-damaged areas(2-class model),the monitoring accuracies of all the three models were computed,which were above 96%.The RF model used the least number of features,including only SAVI and Bandred.In order to further discriminate the pest incidence levels(3-class model),the monitoring accuracies of all the three models were computed,which were above 80%,among which the RF algorithm based on SAVI,Band_(red),VARI__(green),and Band_(red_edge) features achieve the highest accuracy(OAA of 87%,and Kappa of 0.79).Considering the computational cost and model accuracy,this work recommends the RF model based on a few optimal feature combinations to monitor and distinguish the severity of TSW in tea plantations.According to the UAV remote sensing mapping results,the TSW infestation exhibited an aggregated distribution pattern.The spatial information of occurrence and severity can offer effective guidance for precise control of the pest.In addition,the relevant methods provide a reference for monitoring other leaf-eating pests,effectively improving the management level of plant protection in tea plantations,and guaranting the yield and quality of tea plantations.展开更多
针对输送带表面纹理复杂且缺乏边缘设备实时准确识别损伤的现状,提出一种基于RW-YOLOv3的输送带表面损伤实时检测算法。首先,采用结构重参数化RepVGG网络替换YOLOv3算法原主干网络DarkNet53,实现输送带表面损伤快速精准检测;然后将交并...针对输送带表面纹理复杂且缺乏边缘设备实时准确识别损伤的现状,提出一种基于RW-YOLOv3的输送带表面损伤实时检测算法。首先,采用结构重参数化RepVGG网络替换YOLOv3算法原主干网络DarkNet53,实现输送带表面损伤快速精准检测;然后将交并比(Intersection over Union,IoU)损失、分类置信度损失和SIFI相似度加权求和构建预测框与目标框,并进行匹配生成代价矩阵,再通过计算最小代价矩阵,找到最优Wasserstein传输距离实现最优标签分配,从而减少正负样本不平衡造成的误差;最后,基于多尺度检测和结果融合,完成输送带表面损伤实时准确检测。实验结果表明,提出的算法较YOLOv3算法,检测精度均值提升了8.36%,检测速度提高了51.36 FPS,与其他算法相比,所提算法精度高、速度快,满足高带速下输送带表面损伤实时检测需求。展开更多
[Objectives]This study was conducted to screen high-efficiency formula pesticides and precise and efficient application techniques for the prevention and control of Sesamia inferens Walker and Ceratovacuna lanigera Ze...[Objectives]This study was conducted to screen high-efficiency formula pesticides and precise and efficient application techniques for the prevention and control of Sesamia inferens Walker and Ceratovacuna lanigera Zehntner.[Methods]Field efficacy trials were conducted using different combinations of 70%directed enhanced thiamethoxam seed treatment dispersible powder and 46%monosultap·Bacillus thuringiensis wettable powder.[Results]70%directed enhanced thiamethoxam ZF 450 g/hm^(2)+46%monosultap·B.thuringiensis WP 2250 g/hm^(2)had good control effects on both S.inferens and C.lanigera,so it was an ideal high-efficiency formula pesticide for controlling sugarcane S.inferens and C.lanigera.From January to May,combining with new plant or perennial root cultivation management,70%directed enhanced thiamethoxam ZF 450 g/hm^(2)can be evenly spread on sugarcane ditches and sugarcane stumps after being well mixed with fertilizers applied per hectare,and covered with soil in a timely manner,and during the peak incubation period of the first and second generation of S.inferens eggs from March to May,46%monosultap·B.thuringiensis WP 2250 g/hm^(2)was sprayed to the leaf surface in the mixture with water 675 kg with an electric backpack or a motorized sprayer.In such a way,the control efficacy on dead heart seedlings could reach over 89.8%,and that on C.lanigera could reach 100%.Meanwhile,it could effectively and concurrently control thrips,and the increases in yield and sugar content could reach 29310 kg/hm^(2)and 5.9 percentage points,respectively.[Conclusions]The promotion and application of the formula pesticide could achieve precise application and control of sugarcane pests,and improvement of sugarcane quality and planting efficiency,and help promote green prevention and control of sugarcane diseases and pests and the sustained high-quality development of the sugar industry.展开更多
基金the National Key R&D Program of China(Grant No.2022YFC3003902)the National Natural Science Foundation of China(Grant No.42075146).
文摘This work uses cloud-resolving simulations to study mock-Walker cells driven by a specified sea surface temperature(SST).The associated precipitation in the mock-Walker cells exhibits three different modes,including a single peak of precipitation over the SST maximum(mode 1),symmetric double peaks of precipitation straddling the SST maximum(mode 2),and a single peak of precipitation on one side of the SST maximum(mode 3).The three modes are caused by three distinct convective activity center migration traits.Analyses indicate that the virtual effect of water vapor plays an important role in differentiating the three modes.When the SST gradient is large,the virtual effect may be strong enough to overcome the temperature effect,generating a low-level low-pressure anomaly below the ascending branch of the Walker cell off the center.The results here highlight the importance of the virtual effect of water vapor and its interaction with convection and large-scale circulation in the Walker circulation.
文摘在原木木材材积检测中,由于端面伐痕、开裂和阴影等因素容易影响智能检测系统的准确性和稳定性,一直以来,端面识别定位属于一个难点问题。对多个YOLO(You Only Look Once)版本模型的原理分析和试验验证,融合这些YOLO版本模型优点,在yolo3主干网络基础上,采用数据增强、特征融合和损失函数等优化手段,构建更加适用于原木检测的端到端深度学习模型YOLO-Raw Wood(YOLO-RW),用于原木木材材积图像的准确识别和定位。为检验YOLO-RW模型性能,设计多组数据试验。结果表明,同比基准模型,YOLO-RW模型具有更高的端面识别精度和鲁棒性,在准确率和召回率评价指标平均值上,分别高出基准模型6.95%和2.38%以上。研究表明,YOLO-RW模型在原木木材材积检测领域有着较好的应用价值,亦可为相关目标识别领域的研究提供借鉴。
基金funded by the Zhejiang Agricultural Cooperative and Extensive Project of Key Technology(2020XTTGCY04-02,2020XTTGCY01-05)the Major Special Project for 2025 Scientific and Technological Innovation(Major Scientific and Technological Task Project in Ningbo City)(2021Z048).
文摘Thosea sinensis Walker(TSW)rapidly spreads and severely damages the tea plants.Therefore,finding a reliable operational method for identifying the TSW-damaged areas via remote sensing has been a focus of a research community.Such methods also enable us to calculate the precise application of pesticides and prevent the subsequent spread of the pests.In this work,based on the unmanned aerial vehicle(UAV)platform,five band images of multispectral red-edge camera were obtained and used for monitoring the TSW in tea plantations.By combining the minimum redundancy maximum relevance(mRMR)with the selected spectral features,a comprehensive spectral selection strategy was proposed.Then,based on the selected spectral features,three classic machine learning algorithms,including random forest(RF),support vector machine(SVM),and k-nearest neighbors(KNN)were used to construct the pest monitoring model and were evaluated and compared.The results showed that the strategy proposed in this work obtained ideal monitoring accuracy by only using the combination of a few optimized features(2 or 4).In order to differentiate the healthy and TSW-damaged areas(2-class model),the monitoring accuracies of all the three models were computed,which were above 96%.The RF model used the least number of features,including only SAVI and Bandred.In order to further discriminate the pest incidence levels(3-class model),the monitoring accuracies of all the three models were computed,which were above 80%,among which the RF algorithm based on SAVI,Band_(red),VARI__(green),and Band_(red_edge) features achieve the highest accuracy(OAA of 87%,and Kappa of 0.79).Considering the computational cost and model accuracy,this work recommends the RF model based on a few optimal feature combinations to monitor and distinguish the severity of TSW in tea plantations.According to the UAV remote sensing mapping results,the TSW infestation exhibited an aggregated distribution pattern.The spatial information of occurrence and severity can offer effective guidance for precise control of the pest.In addition,the relevant methods provide a reference for monitoring other leaf-eating pests,effectively improving the management level of plant protection in tea plantations,and guaranting the yield and quality of tea plantations.
文摘针对输送带表面纹理复杂且缺乏边缘设备实时准确识别损伤的现状,提出一种基于RW-YOLOv3的输送带表面损伤实时检测算法。首先,采用结构重参数化RepVGG网络替换YOLOv3算法原主干网络DarkNet53,实现输送带表面损伤快速精准检测;然后将交并比(Intersection over Union,IoU)损失、分类置信度损失和SIFI相似度加权求和构建预测框与目标框,并进行匹配生成代价矩阵,再通过计算最小代价矩阵,找到最优Wasserstein传输距离实现最优标签分配,从而减少正负样本不平衡造成的误差;最后,基于多尺度检测和结果融合,完成输送带表面损伤实时准确检测。实验结果表明,提出的算法较YOLOv3算法,检测精度均值提升了8.36%,检测速度提高了51.36 FPS,与其他算法相比,所提算法精度高、速度快,满足高带速下输送带表面损伤实时检测需求。
基金Supported by China Agriculture Research System of MOF and MARA(CARS-170303)Yunling Industrial Technology Leading Talent Training Project(2018LJRC56)Special Fund for the Construction of Modern Agricultural Industry Technology System in Yunnan Province。
文摘[Objectives]This study was conducted to screen high-efficiency formula pesticides and precise and efficient application techniques for the prevention and control of Sesamia inferens Walker and Ceratovacuna lanigera Zehntner.[Methods]Field efficacy trials were conducted using different combinations of 70%directed enhanced thiamethoxam seed treatment dispersible powder and 46%monosultap·Bacillus thuringiensis wettable powder.[Results]70%directed enhanced thiamethoxam ZF 450 g/hm^(2)+46%monosultap·B.thuringiensis WP 2250 g/hm^(2)had good control effects on both S.inferens and C.lanigera,so it was an ideal high-efficiency formula pesticide for controlling sugarcane S.inferens and C.lanigera.From January to May,combining with new plant or perennial root cultivation management,70%directed enhanced thiamethoxam ZF 450 g/hm^(2)can be evenly spread on sugarcane ditches and sugarcane stumps after being well mixed with fertilizers applied per hectare,and covered with soil in a timely manner,and during the peak incubation period of the first and second generation of S.inferens eggs from March to May,46%monosultap·B.thuringiensis WP 2250 g/hm^(2)was sprayed to the leaf surface in the mixture with water 675 kg with an electric backpack or a motorized sprayer.In such a way,the control efficacy on dead heart seedlings could reach over 89.8%,and that on C.lanigera could reach 100%.Meanwhile,it could effectively and concurrently control thrips,and the increases in yield and sugar content could reach 29310 kg/hm^(2)and 5.9 percentage points,respectively.[Conclusions]The promotion and application of the formula pesticide could achieve precise application and control of sugarcane pests,and improvement of sugarcane quality and planting efficiency,and help promote green prevention and control of sugarcane diseases and pests and the sustained high-quality development of the sugar industry.
