Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from ima...Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small co展开更多
The assessment of gas storage capacity is crucial to furthering shale gas exploration and development in the eastern Sichuan Basin,China.Eleven organic-rich shale samples were selected to carry out the high pressure m...The assessment of gas storage capacity is crucial to furthering shale gas exploration and development in the eastern Sichuan Basin,China.Eleven organic-rich shale samples were selected to carry out the high pressure methane sorption,low-pressure N_(2)/CO_(2) gas adsorption,and bulk and skeletal density measurements to investigate the methane storage capacity(MSC).Based on the relative content of clay,carbonates,quartz+feldspar,we grouped the 11 samples into three lithofacies:silica-rich argillaceous shale(CM-1),argillaceous/siliceous mixed shale(M-2),and clay-rich siliceous shale(S-3).The total porosity of the shale samples varies from 3.4% to 5.6%,and gas saturation ranges from 47% to 89%.The measured total gas amount ranges from 1.84 mg/g to 4.22 mg/g with the ratio of free gas to total gas amount ranging from 52.7% to 70.8%.Free gas with high content in the eastern Sichuan Basin may be the key factor controlling amount of shale gas production.The TOC content critically controls the MSC of shales,because micropore,mesopore volumes and the specific surface areas associated with organic matter provide the storage sites for the free and adsorbed gas.The methane sorption capacities of samples from different lithofacies are also affected by clay minerals and moisture content.Clay minerals can provide additional surface areas for methane sorption,and water can cause a 7.1%-42.8% loss of methane sorption capacity.The total porosity,gas-bearing porosity,water saturation,free gas and adsorbed gas number of samples from different lithofacies show subtle differences if the shale samples had similar TOC contents.Our results suggest that,in the eastern Sichuan Basin,clay-rich shale lithofacies is also prospecting targets for shale gas production.展开更多
基金supported in part by the General Program Hunan Provincial Natural Science Foundation of 2022,China(2022JJ31022)the Undergraduate Education Reform Project of Hunan Province,China(HNJG-20210532)the National Natural Science Foundation of China(62276276)。
文摘Accurate diagnosis of apple leaf diseases is crucial for improving the quality of apple production and promoting the development of the apple industry. However, apple leaf diseases do not differ significantly from image texture and structural information. The difficulties in disease feature extraction in complex backgrounds slow the related research progress. To address the problems, this paper proposes an improved multi-scale inverse bottleneck residual network model based on a triplet parallel attention mechanism, which is built upon ResNet-50, while improving and combining the inception module and ResNext inverse bottleneck blocks, to recognize seven types of apple leaf(including six diseases of alternaria leaf spot, brown spot, grey spot, mosaic, rust, scab, and one healthy). First, the 3×3 convolutions in some of the residual modules are replaced by multi-scale residual convolutions, the convolution kernels of different sizes contained in each branch of the multi-scale convolution are applied to extract feature maps of different sizes, and the outputs of these branches are multi-scale fused by summing to enrich the output features of the images. Second, the global layer-wise dynamic coordinated inverse bottleneck structure is used to reduce the network feature loss. The inverse bottleneck structure makes the image information less lossy when transforming from different dimensional feature spaces. The fusion of multi-scale and layer-wise dynamic coordinated inverse bottlenecks makes the model effectively balances computational efficiency and feature representation capability, and more robust with a combination of horizontal and vertical features in the fine identification of apple leaf diseases. Finally, after each improved module, a triplet parallel attention module is integrated with cross-dimensional interactions among channels through rotations and residual transformations, which improves the parallel search efficiency of important features and the recognition rate of the network with relatively small co
基金funding supports from the Major Programs of National Natural Science Foundation of China(Nos.41690134 and 41690131)the National Natural Science Foundation of China(No.41872139).
文摘The assessment of gas storage capacity is crucial to furthering shale gas exploration and development in the eastern Sichuan Basin,China.Eleven organic-rich shale samples were selected to carry out the high pressure methane sorption,low-pressure N_(2)/CO_(2) gas adsorption,and bulk and skeletal density measurements to investigate the methane storage capacity(MSC).Based on the relative content of clay,carbonates,quartz+feldspar,we grouped the 11 samples into three lithofacies:silica-rich argillaceous shale(CM-1),argillaceous/siliceous mixed shale(M-2),and clay-rich siliceous shale(S-3).The total porosity of the shale samples varies from 3.4% to 5.6%,and gas saturation ranges from 47% to 89%.The measured total gas amount ranges from 1.84 mg/g to 4.22 mg/g with the ratio of free gas to total gas amount ranging from 52.7% to 70.8%.Free gas with high content in the eastern Sichuan Basin may be the key factor controlling amount of shale gas production.The TOC content critically controls the MSC of shales,because micropore,mesopore volumes and the specific surface areas associated with organic matter provide the storage sites for the free and adsorbed gas.The methane sorption capacities of samples from different lithofacies are also affected by clay minerals and moisture content.Clay minerals can provide additional surface areas for methane sorption,and water can cause a 7.1%-42.8% loss of methane sorption capacity.The total porosity,gas-bearing porosity,water saturation,free gas and adsorbed gas number of samples from different lithofacies show subtle differences if the shale samples had similar TOC contents.Our results suggest that,in the eastern Sichuan Basin,clay-rich shale lithofacies is also prospecting targets for shale gas production.
