Radar quantitative precipitation estimation(QPE)is a key and challenging task for many designs and applications with meteorological purposes.Since the Z-R relation between radar and rain has a number of parameters on ...Radar quantitative precipitation estimation(QPE)is a key and challenging task for many designs and applications with meteorological purposes.Since the Z-R relation between radar and rain has a number of parameters on different areas,and the rainfall varies with seasons,the traditional methods are incapable of achieving high spatial and temporal resolution and thus difficult to obtain a refined rainfall estimation.This paper proposes a radar quantitative precipitation estimation algorithm based on the spatiotemporal network model(ST-QPE),which designs a convolutional time-series network QPE-Net8 and a multi-scale feature fusion time-series network QPE-Net22 to address these limitations.We report on our investigation into contrast reversal experiments with radar echo and rainfall data collected by the Hunan Meteorological Observatory.Experimental results are verified and analyzed by using statistical and meteorological methods,and show that the ST-QPE model can inverse the rainfall information corresponding to the radar echo at a given moment,which provides practical guidance for accurate short-range precipitation nowcasting to prevent and mitigate disasters efficiently.展开更多
We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed d...We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed dehazing network,the dehazing model proposed in this paper make use of the FPN network structure in the field of target detection,and uses five feature maps of different sizes to better obtain features of different proportions and different sub-regions.A large amount of experimental data proves that the dehazing model proposed in this paper is superior to previous dehazing technologies in terms of PSNR,SSIM,and subjective visual quality.In addition,it achieved a good performance in speed by using EfficientNet B0 as a feature extractor.We find that only using high-level semantic features can not effectively obtain all the information in the image.The FPN structure used in this paper can effectively integrate the high-level semantics and the low-level semantics,and can better take into account the global and local features.The five feature maps with different sizes are not simply weighted and fused.In order to keep all their information,we put them all together and get the final features through decode layers.At the same time,we have done a comparative experiment between ResNet with FPN and EfficientNet with BiFPN.It is proved that EfficientNet with BiFPN can obtain image features more efficiently.Therefore,EfficientNet with BiFPN is chosen as our network feature extraction.展开更多
Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener...Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener region location method based on online learning strategy was proposed,which can locate fastener regions according to the prior knowledge of track image and template matching method.Online learning strategy is used to update the template library dynamically,so that the method not only can locate fastener regions in the track images of multi railways,but also can automatically collect and annotate fastener samples.Secondly,a fastener defect recognition method based on deep convolutional neural network was proposed.The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region.The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.Findings–Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways.Specifically,fastener location module has achieved an average detection rate of 99.36%,and fastener defect recognition module has achieved an average precision of 96.82%.Originality/value–The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways,which has high reliability and strong adaptability to multi railways.展开更多
In this paper,we propose an end-to-end cross-layer gated attention network(CLGA-Net)to directly restore fog-free images.Compared with the previous dehazing network,the dehazing model presented in this paper uses the s...In this paper,we propose an end-to-end cross-layer gated attention network(CLGA-Net)to directly restore fog-free images.Compared with the previous dehazing network,the dehazing model presented in this paper uses the smooth cavity convolution and local residual module as the feature extractor,combined with the channel attention mechanism,to better extract the restored features.A large amount of experimental data proves that the defogging model proposed in this paper is superior to previous defogging technologies in terms of structure similarity index(SSIM),peak signal to noise ratio(PSNR)and subjective visual quality.In order to improve the efficiency of decoding and encoding,we also describe a fusion residualmodule and conduct ablation experiments,which prove that the fusion residual is suitable for the dehazing problem.Therefore,we use fusion residual as a fixed module for encoding and decoding.In addition,we found that the traditional defogging model based on the U-net network may cause some information losses in space.We have achieved effective maintenance of low-level feature information through the cross-layer gating structure that better takes into account global and subtle features.We also present the application of our CLGA-Net in challenging scenarios where the best results in both quantity and quality can be obtained.Experimental results indicate that the present cross-layer gating module can be widely used in the same type of network.展开更多
Radical/radical cross-coupling represents a straightforward way for the construction of new chemical bonds in theory and has received more and more attention over the past several years. Until now, it is challenging t...Radical/radical cross-coupling represents a straightforward way for the construction of new chemical bonds in theory and has received more and more attention over the past several years. Until now, it is challenging to achieve the selective bond formation between two transient radicals since selective radical cross-coupling usually happens between persistent radical and transient radical. However, the number of persistent radicals is much less than that of transient radicals. These issues limit the application of radical/radical cross-coupling in the construction of new chemical bonds. To solve this, we proposed a novel strategy ‘‘tuning radical reactivity" that could tune transient radical into persistent radical. This paper will introduce the concept and recent developments of ‘‘tuning radical reactivity".展开更多
The arylation of C(sp^(3))-H bonds has been a priority research topic in organic synthesis.Minsici reactions have been the powerful methods for C(sp^(3))-C(sp^(2))bonds formation.Despite its mature development,the sco...The arylation of C(sp^(3))-H bonds has been a priority research topic in organic synthesis.Minsici reactions have been the powerful methods for C(sp^(3))-C(sp^(2))bonds formation.Despite its mature development,the scopes of arenes are usually suitable for elec-tron-deficient heterocyclic compounds,rather than electron-rich arenes.Herein,we report an electrooxidation-induced alkylation of electron-rich arenes with H_(2) evolution under exogenous oxidant-free conditions,avoiding the utilization of metal catalysts.This pro-tocol is well performed with various electron-rich aniline derivatives and nitrogen-containing heterocyclic compounds.We anticipate that this electro-oxidative C(sp^(3))-H arylation represents an important expansion for the classic arenes alkylation,thereby proving an attractive strategy for the developments of radical cross-coupling chemistry.展开更多
Reported here is a precise electro-reduction strategy for radical defluorinative alkylation towards the synthesis of gem-difluoroalkenes from α-trifluoromethylstyrenes. According to the redox-potential difference of ...Reported here is a precise electro-reduction strategy for radical defluorinative alkylation towards the synthesis of gem-difluoroalkenes from α-trifluoromethylstyrenes. According to the redox-potential difference of the radical precursors, direct or indirect electrolysis is respectively adopted to realize the precise reduction. An easy-to-handle, catalyst-and metal-free condition is developed for the reduction of alkyl radical precursors that are generally easier to be reduced than α-trifluoromethylstyrenes,while a novel electro-Ni-catalytic system is established for the electro-reduction of alkyl bromides or chlorides towards the electrochemical synthesis of gem-difluoroalkenes. The merit of this protocol is exhibited by its mild conditions, wide substrate scope, and scalable preparation. Mechanistic studies and DFT calculations proved that the coordination of α-trifluoromethylstyrenes to Ni-catalyst prevents the direct reduction of the alkene and, in turn, promotes the activation of alkyl bromide through halogen atom transfer mechanism.展开更多
Pd(OAc)_(2) is an extensively utilized palladium source in the palladium initiated transformations either directly or as a catalyst precursor. However, the comprehension of the real structure of Pd(OAc)_(2) in solutio...Pd(OAc)_(2) is an extensively utilized palladium source in the palladium initiated transformations either directly or as a catalyst precursor. However, the comprehension of the real structure of Pd(OAc)_(2) in solution is still vague. In this work, the structure of palladium acetate in solution was studied in detail by using X-ray absorption fine structure (XAFS) spectroscopy. The results demonstrate that monomer is the main form for Pd(OAc)_(2) in the solution of 1,4-dioxane, N,N-dimethylacetamide (DMA), N,N-dimethylformamide (DMF), 1,2-dimethoxyethane (DME), MeCN and dimethyl sulfoxide (DMSO). In addition, Pd(II) could be reduced to Pd(0) in ethanol solution. The structural information in this research will benefit the understanding of the mechanism of Pd(OAc)_(2) involved organic reactions.展开更多
A[4+2]annulation of two different styrenes to construct polysubstituted 1,2-dihydronaphthalenes was achieved.This transformation proceeded smoothly under electrochemical oxidative conditions without metal catalysts an...A[4+2]annulation of two different styrenes to construct polysubstituted 1,2-dihydronaphthalenes was achieved.This transformation proceeded smoothly under electrochemical oxidative conditions without metal catalysts and external oxidants.A series of polysubstituted 1,2-dihydronaphthalenes were obtained with high regioselectivity and diastereoselectivity.Moreover,polysubstituted 1,2-dihydronaphthalenes were further transformed to polysubstituted 1,2,3,4-tetrahydronaphthalenes and polysubstituted naphthalenes,which show great potential in synthetic applications.展开更多
基金This work is supported by the Key Research and Development Program of Hunan Province(No.2019SK2161)the Key Research and Development Program of Hunan Province(No.2016SK2017).
文摘Radar quantitative precipitation estimation(QPE)is a key and challenging task for many designs and applications with meteorological purposes.Since the Z-R relation between radar and rain has a number of parameters on different areas,and the rainfall varies with seasons,the traditional methods are incapable of achieving high spatial and temporal resolution and thus difficult to obtain a refined rainfall estimation.This paper proposes a radar quantitative precipitation estimation algorithm based on the spatiotemporal network model(ST-QPE),which designs a convolutional time-series network QPE-Net8 and a multi-scale feature fusion time-series network QPE-Net22 to address these limitations.We report on our investigation into contrast reversal experiments with radar echo and rainfall data collected by the Hunan Meteorological Observatory.Experimental results are verified and analyzed by using statistical and meteorological methods,and show that the ST-QPE model can inverse the rainfall information corresponding to the radar echo at a given moment,which provides practical guidance for accurate short-range precipitation nowcasting to prevent and mitigate disasters efficiently.
基金the Key Research and Development Program of Hunan Province(No.2019SK2161)the Key Research and Development Program of Hunan Province(No.2016SK2017).
文摘We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed dehazing network,the dehazing model proposed in this paper make use of the FPN network structure in the field of target detection,and uses five feature maps of different sizes to better obtain features of different proportions and different sub-regions.A large amount of experimental data proves that the dehazing model proposed in this paper is superior to previous dehazing technologies in terms of PSNR,SSIM,and subjective visual quality.In addition,it achieved a good performance in speed by using EfficientNet B0 as a feature extractor.We find that only using high-level semantic features can not effectively obtain all the information in the image.The FPN structure used in this paper can effectively integrate the high-level semantics and the low-level semantics,and can better take into account the global and local features.The five feature maps with different sizes are not simply weighted and fused.In order to keep all their information,we put them all together and get the final features through decode layers.At the same time,we have done a comparative experiment between ResNet with FPN and EfficientNet with BiFPN.It is proved that EfficientNet with BiFPN can obtain image features more efficiently.Therefore,EfficientNet with BiFPN is chosen as our network feature extraction.
基金funded by the Key Research and Development Project of China Academy of Railway Sciences Corporation Limited(2021YJ310).
文摘Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener region location method based on online learning strategy was proposed,which can locate fastener regions according to the prior knowledge of track image and template matching method.Online learning strategy is used to update the template library dynamically,so that the method not only can locate fastener regions in the track images of multi railways,but also can automatically collect and annotate fastener samples.Secondly,a fastener defect recognition method based on deep convolutional neural network was proposed.The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region.The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.Findings–Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways.Specifically,fastener location module has achieved an average detection rate of 99.36%,and fastener defect recognition module has achieved an average precision of 96.82%.Originality/value–The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways,which has high reliability and strong adaptability to multi railways.
基金This work is supported by theKey Research and Development Program of Hunan Province(No.2019SK2161)the Key Research and Development Program of Hunan Province(No.2016SK2017).
文摘In this paper,we propose an end-to-end cross-layer gated attention network(CLGA-Net)to directly restore fog-free images.Compared with the previous dehazing network,the dehazing model presented in this paper uses the smooth cavity convolution and local residual module as the feature extractor,combined with the channel attention mechanism,to better extract the restored features.A large amount of experimental data proves that the defogging model proposed in this paper is superior to previous defogging technologies in terms of structure similarity index(SSIM),peak signal to noise ratio(PSNR)and subjective visual quality.In order to improve the efficiency of decoding and encoding,we also describe a fusion residualmodule and conduct ablation experiments,which prove that the fusion residual is suitable for the dehazing problem.Therefore,we use fusion residual as a fixed module for encoding and decoding.In addition,we found that the traditional defogging model based on the U-net network may cause some information losses in space.We have achieved effective maintenance of low-level feature information through the cross-layer gating structure that better takes into account global and subtle features.We also present the application of our CLGA-Net in challenging scenarios where the best results in both quantity and quality can be obtained.Experimental results indicate that the present cross-layer gating module can be widely used in the same type of network.
基金supported by the National Natural Science Foundation of China(21390402,21520102003)the Hubei Provincial Natural Science Foundation(2017CFA010)The Program of Introducing Talents of Discipline to Universities of China(111 Program)
文摘Radical/radical cross-coupling represents a straightforward way for the construction of new chemical bonds in theory and has received more and more attention over the past several years. Until now, it is challenging to achieve the selective bond formation between two transient radicals since selective radical cross-coupling usually happens between persistent radical and transient radical. However, the number of persistent radicals is much less than that of transient radicals. These issues limit the application of radical/radical cross-coupling in the construction of new chemical bonds. To solve this, we proposed a novel strategy ‘‘tuning radical reactivity" that could tune transient radical into persistent radical. This paper will introduce the concept and recent developments of ‘‘tuning radical reactivity".
基金the National Key R&D Program of China(No.2021YFA1500104)the National Natural Science Foundation of China(No.22031008)the Science Foundation of Wuhan(No.2020010601012192)。
文摘The arylation of C(sp^(3))-H bonds has been a priority research topic in organic synthesis.Minsici reactions have been the powerful methods for C(sp^(3))-C(sp^(2))bonds formation.Despite its mature development,the scopes of arenes are usually suitable for elec-tron-deficient heterocyclic compounds,rather than electron-rich arenes.Herein,we report an electrooxidation-induced alkylation of electron-rich arenes with H_(2) evolution under exogenous oxidant-free conditions,avoiding the utilization of metal catalysts.This pro-tocol is well performed with various electron-rich aniline derivatives and nitrogen-containing heterocyclic compounds.We anticipate that this electro-oxidative C(sp^(3))-H arylation represents an important expansion for the classic arenes alkylation,thereby proving an attractive strategy for the developments of radical cross-coupling chemistry.
基金supported by the National Key Research and Development Program of China(2021YFA1500100)the National Natural Science Foundation of China(22031008)the Science Foundation of Wuhan(2020010601012192)。
文摘Reported here is a precise electro-reduction strategy for radical defluorinative alkylation towards the synthesis of gem-difluoroalkenes from α-trifluoromethylstyrenes. According to the redox-potential difference of the radical precursors, direct or indirect electrolysis is respectively adopted to realize the precise reduction. An easy-to-handle, catalyst-and metal-free condition is developed for the reduction of alkyl radical precursors that are generally easier to be reduced than α-trifluoromethylstyrenes,while a novel electro-Ni-catalytic system is established for the electro-reduction of alkyl bromides or chlorides towards the electrochemical synthesis of gem-difluoroalkenes. The merit of this protocol is exhibited by its mild conditions, wide substrate scope, and scalable preparation. Mechanistic studies and DFT calculations proved that the coordination of α-trifluoromethylstyrenes to Ni-catalyst prevents the direct reduction of the alkene and, in turn, promotes the activation of alkyl bromide through halogen atom transfer mechanism.
基金This work was supported by the National Natural Science Foundation of China(No.21520102003)the Hubei Province Natural Science Foundation of China(No.2017CFA010)The Program of Introducing Talents of Discipline to Universities of China(111 Program)is also appreciated.All the XAFS data were collect-ed at beam line 44A of the TPS.
文摘Pd(OAc)_(2) is an extensively utilized palladium source in the palladium initiated transformations either directly or as a catalyst precursor. However, the comprehension of the real structure of Pd(OAc)_(2) in solution is still vague. In this work, the structure of palladium acetate in solution was studied in detail by using X-ray absorption fine structure (XAFS) spectroscopy. The results demonstrate that monomer is the main form for Pd(OAc)_(2) in the solution of 1,4-dioxane, N,N-dimethylacetamide (DMA), N,N-dimethylformamide (DMF), 1,2-dimethoxyethane (DME), MeCN and dimethyl sulfoxide (DMSO). In addition, Pd(II) could be reduced to Pd(0) in ethanol solution. The structural information in this research will benefit the understanding of the mechanism of Pd(OAc)_(2) involved organic reactions.
基金supported by the National Natural Science Foundation of China(22031008)Science Foundation of Wuhan(2020010601012192)The Program of Introducing Talents of Discipline to Universities of China(111 Program)is also appreciated.
文摘A[4+2]annulation of two different styrenes to construct polysubstituted 1,2-dihydronaphthalenes was achieved.This transformation proceeded smoothly under electrochemical oxidative conditions without metal catalysts and external oxidants.A series of polysubstituted 1,2-dihydronaphthalenes were obtained with high regioselectivity and diastereoselectivity.Moreover,polysubstituted 1,2-dihydronaphthalenes were further transformed to polysubstituted 1,2,3,4-tetrahydronaphthalenes and polysubstituted naphthalenes,which show great potential in synthetic applications.
