Submicron scale temperature sensors are crucial for a range of applications,particularly in micro and na-noscale environments.One promising solution involves the use of active whispering gallery mode(WGM)microresonato...Submicron scale temperature sensors are crucial for a range of applications,particularly in micro and na-noscale environments.One promising solution involves the use of active whispering gallery mode(WGM)microresonators.These resonators can be remotely excited and read out using free-space structures,simplifying the process of sensing.In this study,we present a submicron-scale temperature sensor with a remarkable sensitivity up to 185 pm/℃based on a trian-gular MAPbI3 nanoplatelet(NPL)laser.Notably,as temperature changes,the peak wavelength of the laser line shifts lin-early.This unique characteristic allows for precise temperature sensing by tracking the peak wavelength of the NPL laser.The optical modes are confined within the perovskite NPL,which measures just 85 nm in height,due to total internal reflec-tion.Our NPL laser boasts several key features,including a high Q of~2610 and a low laser threshold of about 19.8μJ·cm^(−2).The combination of exceptional sensitivity and ultra-small size makes our WGM device an ideal candidate for integration into systems that demand compact temperature sensors.This advancement paves the way for significant prog-ress in the development of ultrasmall temperature sensors,opening new possibilities across various fields.展开更多
针对目前深度学习模型通常只能提取单一尺度岩相特征,无法获得多尺度信息且没有充分适应测井曲线自身形态特点影响岩相识别的问题,基于深度学习以Resnet50为基础网络,设计开发多尺度特征提取模块SMGC(strip-pooling and multi-scale gro...针对目前深度学习模型通常只能提取单一尺度岩相特征,无法获得多尺度信息且没有充分适应测井曲线自身形态特点影响岩相识别的问题,基于深度学习以Resnet50为基础网络,设计开发多尺度特征提取模块SMGC(strip-pooling and multi-scale group convolution),并加入改进的ECAs(efficient channel attention strengthen)注意力模块增强对测井曲线条形纹理信息关注度,提出一种SMGC-ECAs-Resnet致密砂岩测井曲线岩相识别方法。以松辽盆地三肇凹陷扶余油层为例,对测井曲线数据预处理构建图像数据集,利用SMGC-ECAs-Resnet网络模型对其进行识别得到分类结果,设置对比试验和鲁棒性实验证明模型有效性。结果表明:所提出的SMGC-ECAs-Resnet网络岩相识别准确率达到91.9%,为复杂致密砂岩岩相的测井识别提供了新的方法。展开更多
Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset...Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset blocks are built.In order to obtain a better performance, AdaBoost is used in each model building.In the boosting iteration step, the component learners which have higher diversity and accuracy are collected via the kernel parameters adjusting.Then the local models via voting method are integrated.The experimental study shows that LDAB-SVM can deal with large scale dataset efficiently without reducing the performance of the classifier.展开更多
文摘Submicron scale temperature sensors are crucial for a range of applications,particularly in micro and na-noscale environments.One promising solution involves the use of active whispering gallery mode(WGM)microresonators.These resonators can be remotely excited and read out using free-space structures,simplifying the process of sensing.In this study,we present a submicron-scale temperature sensor with a remarkable sensitivity up to 185 pm/℃based on a trian-gular MAPbI3 nanoplatelet(NPL)laser.Notably,as temperature changes,the peak wavelength of the laser line shifts lin-early.This unique characteristic allows for precise temperature sensing by tracking the peak wavelength of the NPL laser.The optical modes are confined within the perovskite NPL,which measures just 85 nm in height,due to total internal reflec-tion.Our NPL laser boasts several key features,including a high Q of~2610 and a low laser threshold of about 19.8μJ·cm^(−2).The combination of exceptional sensitivity and ultra-small size makes our WGM device an ideal candidate for integration into systems that demand compact temperature sensors.This advancement paves the way for significant prog-ress in the development of ultrasmall temperature sensors,opening new possibilities across various fields.
文摘针对目前深度学习模型通常只能提取单一尺度岩相特征,无法获得多尺度信息且没有充分适应测井曲线自身形态特点影响岩相识别的问题,基于深度学习以Resnet50为基础网络,设计开发多尺度特征提取模块SMGC(strip-pooling and multi-scale group convolution),并加入改进的ECAs(efficient channel attention strengthen)注意力模块增强对测井曲线条形纹理信息关注度,提出一种SMGC-ECAs-Resnet致密砂岩测井曲线岩相识别方法。以松辽盆地三肇凹陷扶余油层为例,对测井曲线数据预处理构建图像数据集,利用SMGC-ECAs-Resnet网络模型对其进行识别得到分类结果,设置对比试验和鲁棒性实验证明模型有效性。结果表明:所提出的SMGC-ECAs-Resnet网络岩相识别准确率达到91.9%,为复杂致密砂岩岩相的测井识别提供了新的方法。
基金supported by the National Natural Science Foundation of China (60603098)
文摘Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset blocks are built.In order to obtain a better performance, AdaBoost is used in each model building.In the boosting iteration step, the component learners which have higher diversity and accuracy are collected via the kernel parameters adjusting.Then the local models via voting method are integrated.The experimental study shows that LDAB-SVM can deal with large scale dataset efficiently without reducing the performance of the classifier.
