Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are ...Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are mainly obtained through in-situ ocean observations and simulation by ocean circulation models,which are usually challenging and costly.Recently,dynamical,statistical,or machine learning models have been proposed to invert the OST/OSS from sea surface information;however,these models mainly focused on the inversion of monthly OST and OSS.To address this issue,we apply clustering algorithms and employ a stacking strategy to ensemble three models(XGBoost,Random Forest,and LightGBM)to invert the real-time OST/OSS based on satellite-derived data and the Argo dataset.Subsequently,a fusion of temperature and salinity is employed to reconstruct OST and OSS.In the validation dataset,the depth-averaged Correlation(Corr)of the estimated OST(OSS)is 0.919(0.83),and the average Root-Mean-Square Error(RMSE)is0.639°C(0.087 psu),with a depth-averaged coefficient of determination(R~2)of 0.84(0.68).Notably,at the thermocline where the base models exhibit their maximum error,the stacking-based fusion model exhibited significant performance enhancement,with a maximum enhancement in OST and OSS inversion exceeding 10%.We further found that the estimated OST and OSS exhibit good agreement with the HYbrid Coordinate Ocean Model(HYCOM)data and BOA_Argo dataset during the passage of a mesoscale eddy.This study shows that the proposed model can effectively invert the real-time OST and OSS,potentially enhancing the understanding of multi-scale oceanic processes in the SCS.展开更多
为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合...为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合。通过5折交叉验证,根据各基模型在验证集上的AUC(area under curve)值对预测结果进行加权平均,使得表现较好的基模型在最终预测中贡献更大,从而提升模型的整体预测性能。在中老年结构化数据上的实验结果表明,ABS-Stacking模型在泛化能力和抑郁症预测效果上均优于单一模型和传统集成方法。该方法不仅有效解决了基分类器组合选择和性能加权的问题,还显著提高了模型的自适应性和泛化能力,为抑郁症预测提供了新的方法参考。展开更多
Improving the strength-ductility is crucial to the development of high-performance nickel-based super-alloys fabricated via additive manufacturing(AM).In this study,Sc and Y microalloying is used to regu-late the micr...Improving the strength-ductility is crucial to the development of high-performance nickel-based super-alloys fabricated via additive manufacturing(AM).In this study,Sc and Y microalloying is used to regu-late the microstructure and improve the strength-ductility of René104 supealloy(René104ScY).The re-sults suggest the formation of high-density stacking faults(SFs),Lomer-Cottrell locks,and nano-Al_(3)(Sc,Y)phases in the René104ScY matrix.The cellular/columnar structures are refined,the number of equiax-ial grains increases,and the number of columnar grains and their aspect ratio decrease in René104ScY.The synergistic effect of multiple strengthening mechanisms,including that formed by SFs,improves the strength and ductility of René104ScY fabricated via laser powder bed fusion.The yield strength,tensile strength,and elongation of René104ScY are 1059±15 MPa,1405±10 MPa,and 28.8%±0.6%,respec-tively.This study provides a novel approach for developing high-performance nickel-based superalloys using AM.展开更多
基金jointly supported by the National Key Research and Development Program of China(2022YFC3104304)the National Natural Science Foundation of China(Grant No.41876011)+1 种基金the 2022 Research Program of Sanya Yazhou Bay Science and Technology City(SKJC-2022-01-001)the Hainan Province Science and Technology Special Fund(ZDYF2021SHFZ265)。
文摘Three-dimensional ocean subsurface temperature and salinity structures(OST/OSS)in the South China Sea(SCS)play crucial roles in oceanic climate research and disaster mitigation.Traditionally,real-time OST and OSS are mainly obtained through in-situ ocean observations and simulation by ocean circulation models,which are usually challenging and costly.Recently,dynamical,statistical,or machine learning models have been proposed to invert the OST/OSS from sea surface information;however,these models mainly focused on the inversion of monthly OST and OSS.To address this issue,we apply clustering algorithms and employ a stacking strategy to ensemble three models(XGBoost,Random Forest,and LightGBM)to invert the real-time OST/OSS based on satellite-derived data and the Argo dataset.Subsequently,a fusion of temperature and salinity is employed to reconstruct OST and OSS.In the validation dataset,the depth-averaged Correlation(Corr)of the estimated OST(OSS)is 0.919(0.83),and the average Root-Mean-Square Error(RMSE)is0.639°C(0.087 psu),with a depth-averaged coefficient of determination(R~2)of 0.84(0.68).Notably,at the thermocline where the base models exhibit their maximum error,the stacking-based fusion model exhibited significant performance enhancement,with a maximum enhancement in OST and OSS inversion exceeding 10%.We further found that the estimated OST and OSS exhibit good agreement with the HYbrid Coordinate Ocean Model(HYCOM)data and BOA_Argo dataset during the passage of a mesoscale eddy.This study shows that the proposed model can effectively invert the real-time OST and OSS,potentially enhancing the understanding of multi-scale oceanic processes in the SCS.
文摘为了解决传统抑郁症预测模型因过于依赖单一模型而难以有效应对数据复杂性的问题,提出了一种基于ABS-Stacking算法的抑郁症预测模型。在传统Stacking模型基础上采用最佳优先搜索算法构建基分类器筛选层,以自适应选择最优的基分类器组合。通过5折交叉验证,根据各基模型在验证集上的AUC(area under curve)值对预测结果进行加权平均,使得表现较好的基模型在最终预测中贡献更大,从而提升模型的整体预测性能。在中老年结构化数据上的实验结果表明,ABS-Stacking模型在泛化能力和抑郁症预测效果上均优于单一模型和传统集成方法。该方法不仅有效解决了基分类器组合选择和性能加权的问题,还显著提高了模型的自适应性和泛化能力,为抑郁症预测提供了新的方法参考。
基金financially supported by the Project of Chinese Academy of Engineering(Nos.2019-XZ-11 and 2023-XY-18)the Open Fund of National Joint Engineering Research Center for Abrasion Control and Molding of Metal Materials of China(No.HKDNM201907).
文摘Improving the strength-ductility is crucial to the development of high-performance nickel-based super-alloys fabricated via additive manufacturing(AM).In this study,Sc and Y microalloying is used to regu-late the microstructure and improve the strength-ductility of René104 supealloy(René104ScY).The re-sults suggest the formation of high-density stacking faults(SFs),Lomer-Cottrell locks,and nano-Al_(3)(Sc,Y)phases in the René104ScY matrix.The cellular/columnar structures are refined,the number of equiax-ial grains increases,and the number of columnar grains and their aspect ratio decrease in René104ScY.The synergistic effect of multiple strengthening mechanisms,including that formed by SFs,improves the strength and ductility of René104ScY fabricated via laser powder bed fusion.The yield strength,tensile strength,and elongation of René104ScY are 1059±15 MPa,1405±10 MPa,and 28.8%±0.6%,respec-tively.This study provides a novel approach for developing high-performance nickel-based superalloys using AM.
