With the improvements in the density and quality of satellite altimetry data,a high-precision and high-resolution mean sea surface model containing abundant information regarding a marine gravity field can be calculat...With the improvements in the density and quality of satellite altimetry data,a high-precision and high-resolution mean sea surface model containing abundant information regarding a marine gravity field can be calculated from long-time series multi-satellite altimeter data.Therefore,in this study,a method was proposed for determining marine gravity anomalies from a mean sea surface model.Taking the Gulf of Mexico(15°–32°N,80°–100°W)as the study area and using a removal-recovery method,the residual gridded deflections of the vertical(DOVs)are calculated by combining the mean sea surface,mean dynamic topography,and XGM2019e_2159 geoid,and then using the inverse Vening-Meinesz method to determine the residual marine gravity anomalies from the residual gridded DOVs.Finally,residual gravity anomalies are added to the XGM2019e_2159 gravity anomalies to derive marine gravity anomaly models.In this study,the marine gravity anomalies were estimated with mean sea surface models CNES_CLS15MSS,DTU21MSS,and SDUST2020MSS and the mean dynamic topography models CNES_CLS18MDT and DTU22MDT.The accuracy of the marine gravity anomalies derived by the mean sea surface model was assessed based on ship-borne gravity data.The results show that the difference between the gravity anomalies derived by DTU21MSS and CNES_CLS18MDT and those of the ship-borne gravity data is optimal.With an increase in the distance from the coast,the difference between the gravity anomalies derived by mean sea surface models and ship-borne gravity data gradually decreases.The accuracy of the difference between the gravity anomalies derived by mean sea surface models and those from ship-borne gravity data are optimal at a depth of 3–4 km.The accuracy of the gravity anomalies derived by the mean sea surface model is high.展开更多
Online advertising has gained much attention on various platforms as a hugely lucrative market.In promoting content and advertisements in real life,the acquisition of user target actions is usually a multi-step proces...Online advertising has gained much attention on various platforms as a hugely lucrative market.In promoting content and advertisements in real life,the acquisition of user target actions is usually a multi-step process,such as impres-sion→click→conversion,which means the process from the delivery of the recommended item to the user’s click to the final conversion.Due to data sparsity or sample selection bias,it is difficult for the trained model to achieve the business goal of the target campaign.Multi-task learning,a classical solution to this pro-blem,aims to generalize better on the original task given several related tasks by exploiting the knowledge between tasks to share the same feature and label space.Adaptively learned task relations bring better performance to make full use of the correlation between tasks.We train a general model capable of captur-ing the relationships between various tasks on all existing active tasks from a meta-learning perspective.In addition,this paper proposes a Multi-task Attention Network(MAN)to identify commonalities and differences between tasks in the feature space.The model performance is improved by explicitly learning the stacking of task relationships in the label space.To illustrate the effectiveness of our method,experiments are conducted on Alibaba Click and Conversion Pre-diction(Ali-CCP)dataset.Experimental results show that the method outperforms the state-of-the-art multi-task learning methods.展开更多
基金The National Natural Science Foundation of China under contract Nos 42274006,42174041,41774001the Research Fund of University of Science and Technology under contract No.2014TDJH101.
文摘With the improvements in the density and quality of satellite altimetry data,a high-precision and high-resolution mean sea surface model containing abundant information regarding a marine gravity field can be calculated from long-time series multi-satellite altimeter data.Therefore,in this study,a method was proposed for determining marine gravity anomalies from a mean sea surface model.Taking the Gulf of Mexico(15°–32°N,80°–100°W)as the study area and using a removal-recovery method,the residual gridded deflections of the vertical(DOVs)are calculated by combining the mean sea surface,mean dynamic topography,and XGM2019e_2159 geoid,and then using the inverse Vening-Meinesz method to determine the residual marine gravity anomalies from the residual gridded DOVs.Finally,residual gravity anomalies are added to the XGM2019e_2159 gravity anomalies to derive marine gravity anomaly models.In this study,the marine gravity anomalies were estimated with mean sea surface models CNES_CLS15MSS,DTU21MSS,and SDUST2020MSS and the mean dynamic topography models CNES_CLS18MDT and DTU22MDT.The accuracy of the marine gravity anomalies derived by the mean sea surface model was assessed based on ship-borne gravity data.The results show that the difference between the gravity anomalies derived by DTU21MSS and CNES_CLS18MDT and those of the ship-borne gravity data is optimal.With an increase in the distance from the coast,the difference between the gravity anomalies derived by mean sea surface models and ship-borne gravity data gradually decreases.The accuracy of the difference between the gravity anomalies derived by mean sea surface models and those from ship-borne gravity data are optimal at a depth of 3–4 km.The accuracy of the gravity anomalies derived by the mean sea surface model is high.
基金Our work was supported by the research project of Yunnan University(Grant No.2021Y274)Natural Science Foundation of China(Grant No.61862064).
文摘Online advertising has gained much attention on various platforms as a hugely lucrative market.In promoting content and advertisements in real life,the acquisition of user target actions is usually a multi-step process,such as impres-sion→click→conversion,which means the process from the delivery of the recommended item to the user’s click to the final conversion.Due to data sparsity or sample selection bias,it is difficult for the trained model to achieve the business goal of the target campaign.Multi-task learning,a classical solution to this pro-blem,aims to generalize better on the original task given several related tasks by exploiting the knowledge between tasks to share the same feature and label space.Adaptively learned task relations bring better performance to make full use of the correlation between tasks.We train a general model capable of captur-ing the relationships between various tasks on all existing active tasks from a meta-learning perspective.In addition,this paper proposes a Multi-task Attention Network(MAN)to identify commonalities and differences between tasks in the feature space.The model performance is improved by explicitly learning the stacking of task relationships in the label space.To illustrate the effectiveness of our method,experiments are conducted on Alibaba Click and Conversion Pre-diction(Ali-CCP)dataset.Experimental results show that the method outperforms the state-of-the-art multi-task learning methods.