Arctic sea ice concentration(SIC)prediction on a subseasonal scale plays an important role in polar navigation.To reduce the high uncertainty of daily forecasts,three time series prediction models are combined with em...Arctic sea ice concentration(SIC)prediction on a subseasonal scale plays an important role in polar navigation.To reduce the high uncertainty of daily forecasts,three time series prediction models are combined with empirical orthogonal function(EOF)decomposition to forecast Arctic pentad-mean SIC,where each month is divided into six pentad-means–the first five each span five days,and the last encompasses the remaining days,which may vary in length.The models were trained on SIC data from 1989 to2018 and tested from 2019 to 2023,with lead times ranging from 1 to 12 pentad-means.Model skill was evaluated based on SIC spatial patterns,sea ice area(SIA),and the sea ice edge in September from 2019 to 2023.The moving-averaged 2-m temperature helps reduce the long short-term memory model's error in the Beaufort and Chukchi Seas.Based on the models'scores for each EOF time series,weighted ensemble prediction results were obtained.These results outperform two benchmark models across all lead times.In addition,the ensemble prediction better reproduces the seasonal cycle of the SIA,with relative errors ranging from 1.04%to 3.85%.The predicted September ice edge closely matches observations,with binary accuracy consistently above 90%.Forecast models show the lowest errors in the central Arctic,while relatively higher errors appear in the Barents and Kara Seas.展开更多
The correlation between the Soil Moisture and Ocean Salinity(SMOS)L-band brightness temperature and thin sea ice thickness has been widely exploited using semi-empirical retrieval approaches based on a single-tie poin...The correlation between the Soil Moisture and Ocean Salinity(SMOS)L-band brightness temperature and thin sea ice thickness has been widely exploited using semi-empirical retrieval approaches based on a single-tie point(STP).However,due to pronounced spatial heterogeneity in seawater and sea ice properties across the Arctic,the use of an STP often leads to regionally biased.To address this limitation,this study proposes a multi-tie point(MTP)sea ice thickness retrieval method based on SMOS brightness temperature and sea ice concentration time series.Multiple seawater and sea ice tie-point values are identified through point-by-point time series analysis,quality control,and statistical hypothesis testing,allowing spatial variability in radiometric properties to be explicitly considered.The MTP-based retrieval is applied to Arctic freeze-up conditions.Validation against independent SMOS thin sea ice thickness products shows that the MTP approach yields significantly reduced bias and root mean square error compared with the conventional STP method,with statistically significant improvements confirmed by paired t-tests.While retrieval accuracy stabilizes beyond a certain number of tie points,the preprocessing cost associated with tie-point selection increases substantially.Considering both accuracy and efficiency,the MTP framework provides a practical and robust approach for large-scale Arctic thin sea ice thickness retrieval and enables improved characterization of regional freezing processes and maximum ice thickness.展开更多
Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiote...Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiotemporal distribution of Arctic SIC is more challenging than predicting its total extent.In this study,spatiotemporal prediction models for monthly Arctic SIC at 1-to 3-month leads are developed based on U-Net-an effective convolutional deep-learning approach.Based on explicit Arctic sea-ice-atmosphere interactions,11 variables associated with Arctic sea-ice variations are selected as predictors,including observed Arctic SIC,atmospheric,oceanic,and heat flux variables at 1-to 3-month leads.The prediction skills for the monthly Arctic SIC of the test set(from January 2018 to December 2022)are evaluated by examining the mean absolute error(MAE)and binary accuracy(BA).Results showed that the U-Net model had lower MAE and higher BA for Arctic SIC compared to two dynamic climate prediction systems(CFSv2 and NorCPM).By analyzing the relative importance of each predictor,the prediction accuracy relies more on the SIC at the 1-month lead,but on the surface net solar radiation flux at 2-to 3-month leads.However,dynamic models show limited prediction skills for surface net solar radiation flux and other physical processes,especially in autumn.Therefore,the U-Net model can be used to capture the connections among these key physical processes associated with Arctic sea ice and thus offers a significant advantage in predicting Arctic SIC.展开更多
Prydz Bay,East Antarctica,is a critical region for studying ocean–sea ice–ice shelf interactions and their role in the global climate system.This review synthesizes the advancements in numerical modeling of physical...Prydz Bay,East Antarctica,is a critical region for studying ocean–sea ice–ice shelf interactions and their role in the global climate system.This review synthesizes the advancements in numerical modeling of physical oceanographic processes in Prydz Bay,highlighting the evolution from early one-dimensional thermodynamic models to contemporary high-resolution,three-dimensional coupled ocean–sea ice–ice shelf frameworks.We discuss key milestones in understanding processes such as frazil ice dynamics and its impact on the basal mass balance of the Amery Ice Shelf,the pathways and mechanisms of Modified Circumpolar Deep Water intrusions,and the dynamic influences of large icebergs on regional circulation.Despite significant progress,challenges remain in integrating multi-component interactions and achieving long-term,high-resolution climate projections.Future efforts should focus on developing fully coupled models that incorporate atmosphere–ocean–sea ice–ice shelf–iceberg interactions,supported by enhanced observational networks and improved computational efficiency.This review underscores the importance of continued modeling advancement to better predict the responses of Antarctic ice shelves and polar climate to global change.展开更多
Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we...Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we developed a pure data-driven DL model for predicting the Antarctic austral summer monthly-to-seasonal sea ice concentration(SIC)by incorporating a novel hybrid sea ice edge constraint loss function(HybridLoss).The model is referred to as ASICNet.Independent testing based on the last five years(2019–23)demonstrates that ASICNet with HybridLoss achieves significantly higher skill metrics than without,with a reduced mean absolute error of 0.021 from 0.022,a reduced integrated ice edge error of 1.714×10^(6)from 1.794×10^(6)km^(2),but an increased pattern correlation coefficient of 0.40 from 0.38,although both ASICNet versions outperform dynamical and statistical models.Furthermore,enhanced heat maps were developed to interpret the predictability sources of sea ice within DL-based models,and the results suggest that the predictability of Antarctic sea ice is attributable to factors like the Antarctic Dipole(ADP),Amundsen Sea Low(ASL),and Southern Ocean sea surface temperature(SST),as revealed in previous studies.Thus,ASICNet is an efficient tool for austral summer Antarctic SIC prediction.展开更多
Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performan...Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performance of PINNs in solving the temperature diffusion equation of the seawater across six scenarios,including forward and inverse problems under three different boundary conditions.Results demonstrate that PINNs achieved consistently higher accuracy with the Dirichlet and Neumann boundary conditions compared to the Robin boundary condition for both forward and inverse problems.Inaccurate weighting of terms in the loss function can reduce model accuracy.Additionally,the sensitivity of model performance to the positioning of sampling points varied between different boundary conditions.In particular,the model under the Dirichlet boundary condition exhibited superior robustness to variations in point positions during the solutions of inverse problems.In contrast,for the Neumann and Robin boundary conditions,accuracy declines when points were sampled from identical positions or at the same time.Subsequently,the Argo observations were used to reconstruct the vertical diffusion of seawater temperature in the north-central Pacific for the applicability of PINNs in the real ocean.The PINNs successfully captured the vertical diffusion characteristics of seawater temperature,reflected the seasonal changes of vertical temperature under different topographic conditions,and revealed the influence of topography on the temperature diffusion coefficient.The PINNs were proved effective in solving the temperature diffusion equation of seawater with limited data,providing a promising technique for simulating or predicting ocean phenomena using sparse observations.展开更多
The rapid melting of Arctic sea ice poses significant risks to the safety of shipping routes.Accurate remote sensing data on sea ice concentration(SIC)is crucial for effective route planning of ships and ensuring navi...The rapid melting of Arctic sea ice poses significant risks to the safety of shipping routes.Accurate remote sensing data on sea ice concentration(SIC)is crucial for effective route planning of ships and ensuring navigational safety.Despite the availability of numerous SIC products in China,these datasets still lag behind mainstream international products in terms of data accuracy,spatiotemporal resolution,and time span.To enhance the accuracy of China's domestic SIC remote sensing data,this study used the SIC data derived from the passive microwave remote sensing dataset provided by the University of Bremen(BRM-SIC)as a reference to conduct a comprehensive evaluation and analysis of two additional SIC datasets:the dataset derived from the microwave radiation imager(MWRI)aboard the FY-3D satellite,provided by the National Satellite Meteorological Center(FY-SIC),and the dataset obtained through the DT-ASI algorithm from the microwave imager of the FY-3D satellite,provided by Ocean University of China(OUC-SIC).Based on the evaluation results,a TransUnet fusion correction model was developed.The performance of this model was then compared against Ordinary Least Squares(OLS),Random Forest(RF),and UNet correction models,through spatial and temporal analyses.Results indicate that,compared to FY-SIC data,the RMSE of the OUC-SIC data and the standard data is reduced by24.245%,while the R is increased by 12.516%.Overall,the accuracy of OUC-SIC data is superior to that of FY-SIC data.During the research period(2020–2022),the standard deviation(SD)and coefficient of variation(CV)of OUC-SIC were 3.877%and 10.582%,respectively,while those for FY-SIC were 7.836%and 7.982%,respectively.In the study area,compared with OUC-SIC data,FYSIC data exhibited a larger standard deviation of deviation and a smaller coefficient of variation of deviation across most sea areas.These results indicate that the OUC-SIC data exhibit better temporal and spatial stability,whereas the FY-SIC data show stronger relative dimensionless stability.Among the four correction models,all showed improvements over the original,unfused corrected data.The fusion corrections using the OLS,RF,UNet,and TransUnet models reduced RMSE by 5.563%,14.601%,42.927%,and48.316%,respectively.Correspondingly,R increased by 0.463%,1.176%,3.951%,and 4.342%,respectively.Among these models,TransUnet performed the best,effectively integrating the advantages of FY-SIC and OUC-SIC data and notably improving the overall accuracy and spatiotemporal stability of SIC data.展开更多
基金supported by the National Key Research and Development Program(No.2023YFC2809101)the Laoshan Laboratory Technology Innovation Project(No.LSKJ202202301)。
文摘Arctic sea ice concentration(SIC)prediction on a subseasonal scale plays an important role in polar navigation.To reduce the high uncertainty of daily forecasts,three time series prediction models are combined with empirical orthogonal function(EOF)decomposition to forecast Arctic pentad-mean SIC,where each month is divided into six pentad-means–the first five each span five days,and the last encompasses the remaining days,which may vary in length.The models were trained on SIC data from 1989 to2018 and tested from 2019 to 2023,with lead times ranging from 1 to 12 pentad-means.Model skill was evaluated based on SIC spatial patterns,sea ice area(SIA),and the sea ice edge in September from 2019 to 2023.The moving-averaged 2-m temperature helps reduce the long short-term memory model's error in the Beaufort and Chukchi Seas.Based on the models'scores for each EOF time series,weighted ensemble prediction results were obtained.These results outperform two benchmark models across all lead times.In addition,the ensemble prediction better reproduces the seasonal cycle of the SIA,with relative errors ranging from 1.04%to 3.85%.The predicted September ice edge closely matches observations,with binary accuracy consistently above 90%.Forecast models show the lowest errors in the central Arctic,while relatively higher errors appear in the Barents and Kara Seas.
基金supported by the National Key Research and Development Program of China(Grant nos.2023YFC2809103,2024YFC2813505)the Fundamental Research Funds for the Central Universities(Grant nos.2042025kf0083,2042025gf0014)the Antarctic Zhongshan Ice and Space Environment National Observation and Research Station(Grant no.ZSNORS-20252702).
文摘The correlation between the Soil Moisture and Ocean Salinity(SMOS)L-band brightness temperature and thin sea ice thickness has been widely exploited using semi-empirical retrieval approaches based on a single-tie point(STP).However,due to pronounced spatial heterogeneity in seawater and sea ice properties across the Arctic,the use of an STP often leads to regionally biased.To address this limitation,this study proposes a multi-tie point(MTP)sea ice thickness retrieval method based on SMOS brightness temperature and sea ice concentration time series.Multiple seawater and sea ice tie-point values are identified through point-by-point time series analysis,quality control,and statistical hypothesis testing,allowing spatial variability in radiometric properties to be explicitly considered.The MTP-based retrieval is applied to Arctic freeze-up conditions.Validation against independent SMOS thin sea ice thickness products shows that the MTP approach yields significantly reduced bias and root mean square error compared with the conventional STP method,with statistically significant improvements confirmed by paired t-tests.While retrieval accuracy stabilizes beyond a certain number of tie points,the preprocessing cost associated with tie-point selection increases substantially.Considering both accuracy and efficiency,the MTP framework provides a practical and robust approach for large-scale Arctic thin sea ice thickness retrieval and enables improved characterization of regional freezing processes and maximum ice thickness.
基金supported by the National Key Research and Development Program of China[grant number 2022YFE0106800]an Innovation Group Project of the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)[grant number 311024001]+3 种基金a project supported by the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)[grant number SML2023SP209]a Research Council of Norway funded project(MAPARC)[grant number 328943]a Nansen Center´s basic institutional funding[grant number 342624]the high-performance computing support from the School of Atmospheric Science at Sun Yat-sen University。
文摘Current shipping,tourism,and resource development requirements call for more accurate predictions of the Arctic sea-ice concentration(SIC).However,due to the complex physical processes involved,predicting the spatiotemporal distribution of Arctic SIC is more challenging than predicting its total extent.In this study,spatiotemporal prediction models for monthly Arctic SIC at 1-to 3-month leads are developed based on U-Net-an effective convolutional deep-learning approach.Based on explicit Arctic sea-ice-atmosphere interactions,11 variables associated with Arctic sea-ice variations are selected as predictors,including observed Arctic SIC,atmospheric,oceanic,and heat flux variables at 1-to 3-month leads.The prediction skills for the monthly Arctic SIC of the test set(from January 2018 to December 2022)are evaluated by examining the mean absolute error(MAE)and binary accuracy(BA).Results showed that the U-Net model had lower MAE and higher BA for Arctic SIC compared to two dynamic climate prediction systems(CFSv2 and NorCPM).By analyzing the relative importance of each predictor,the prediction accuracy relies more on the SIC at the 1-month lead,but on the surface net solar radiation flux at 2-to 3-month leads.However,dynamic models show limited prediction skills for surface net solar radiation flux and other physical processes,especially in autumn.Therefore,the U-Net model can be used to capture the connections among these key physical processes associated with Arctic sea ice and thus offers a significant advantage in predicting Arctic SIC.
基金supported by the Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(Grant nos.SML2021SP306,SML2023SP201)the National Key R&D Program of China(Grant no.2024YFF0506603)+1 种基金the National Natural Science Foundation of China(Grant no.42576020)Guangdong Basic and Applied Basic Research Foundation,China(Grant nos.2024A1515012717,2026A1515012241).
文摘Prydz Bay,East Antarctica,is a critical region for studying ocean–sea ice–ice shelf interactions and their role in the global climate system.This review synthesizes the advancements in numerical modeling of physical oceanographic processes in Prydz Bay,highlighting the evolution from early one-dimensional thermodynamic models to contemporary high-resolution,three-dimensional coupled ocean–sea ice–ice shelf frameworks.We discuss key milestones in understanding processes such as frazil ice dynamics and its impact on the basal mass balance of the Amery Ice Shelf,the pathways and mechanisms of Modified Circumpolar Deep Water intrusions,and the dynamic influences of large icebergs on regional circulation.Despite significant progress,challenges remain in integrating multi-component interactions and achieving long-term,high-resolution climate projections.Future efforts should focus on developing fully coupled models that incorporate atmosphere–ocean–sea ice–ice shelf–iceberg interactions,supported by enhanced observational networks and improved computational efficiency.This review underscores the importance of continued modeling advancement to better predict the responses of Antarctic ice shelves and polar climate to global change.
基金jointly supported by the National Natural Science Foundation of China(Grant No.42376250)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19070402).
文摘Predicting Antarctic sea ice is of substantial academic and practical significance.However,current prediction models,including deep learning(DL)-based models,show notable bias in the marginal ice zone.In this study,we developed a pure data-driven DL model for predicting the Antarctic austral summer monthly-to-seasonal sea ice concentration(SIC)by incorporating a novel hybrid sea ice edge constraint loss function(HybridLoss).The model is referred to as ASICNet.Independent testing based on the last five years(2019–23)demonstrates that ASICNet with HybridLoss achieves significantly higher skill metrics than without,with a reduced mean absolute error of 0.021 from 0.022,a reduced integrated ice edge error of 1.714×10^(6)from 1.794×10^(6)km^(2),but an increased pattern correlation coefficient of 0.40 from 0.38,although both ASICNet versions outperform dynamical and statistical models.Furthermore,enhanced heat maps were developed to interpret the predictability sources of sea ice within DL-based models,and the results suggest that the predictability of Antarctic sea ice is attributable to factors like the Antarctic Dipole(ADP),Amundsen Sea Low(ASL),and Southern Ocean sea surface temperature(SST),as revealed in previous studies.Thus,ASICNet is an efficient tool for austral summer Antarctic SIC prediction.
基金Supported by the National Key Research and Development Program of China(No.2023YFC3008200)the Independent Research Project of Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai)(No.SML2022SP505)。
文摘Physics-informed neural networks(PINNs),as a novel artificial intelligence method for solving partial differential equations,are applicable to solve both forward and inverse problems.This study evaluates the performance of PINNs in solving the temperature diffusion equation of the seawater across six scenarios,including forward and inverse problems under three different boundary conditions.Results demonstrate that PINNs achieved consistently higher accuracy with the Dirichlet and Neumann boundary conditions compared to the Robin boundary condition for both forward and inverse problems.Inaccurate weighting of terms in the loss function can reduce model accuracy.Additionally,the sensitivity of model performance to the positioning of sampling points varied between different boundary conditions.In particular,the model under the Dirichlet boundary condition exhibited superior robustness to variations in point positions during the solutions of inverse problems.In contrast,for the Neumann and Robin boundary conditions,accuracy declines when points were sampled from identical positions or at the same time.Subsequently,the Argo observations were used to reconstruct the vertical diffusion of seawater temperature in the north-central Pacific for the applicability of PINNs in the real ocean.The PINNs successfully captured the vertical diffusion characteristics of seawater temperature,reflected the seasonal changes of vertical temperature under different topographic conditions,and revealed the influence of topography on the temperature diffusion coefficient.The PINNs were proved effective in solving the temperature diffusion equation of seawater with limited data,providing a promising technique for simulating or predicting ocean phenomena using sparse observations.
基金supported by the National Natural Science Foundation of China(No.41971339)the SDUST Research Fund(No.2019TDJH103)。
文摘The rapid melting of Arctic sea ice poses significant risks to the safety of shipping routes.Accurate remote sensing data on sea ice concentration(SIC)is crucial for effective route planning of ships and ensuring navigational safety.Despite the availability of numerous SIC products in China,these datasets still lag behind mainstream international products in terms of data accuracy,spatiotemporal resolution,and time span.To enhance the accuracy of China's domestic SIC remote sensing data,this study used the SIC data derived from the passive microwave remote sensing dataset provided by the University of Bremen(BRM-SIC)as a reference to conduct a comprehensive evaluation and analysis of two additional SIC datasets:the dataset derived from the microwave radiation imager(MWRI)aboard the FY-3D satellite,provided by the National Satellite Meteorological Center(FY-SIC),and the dataset obtained through the DT-ASI algorithm from the microwave imager of the FY-3D satellite,provided by Ocean University of China(OUC-SIC).Based on the evaluation results,a TransUnet fusion correction model was developed.The performance of this model was then compared against Ordinary Least Squares(OLS),Random Forest(RF),and UNet correction models,through spatial and temporal analyses.Results indicate that,compared to FY-SIC data,the RMSE of the OUC-SIC data and the standard data is reduced by24.245%,while the R is increased by 12.516%.Overall,the accuracy of OUC-SIC data is superior to that of FY-SIC data.During the research period(2020–2022),the standard deviation(SD)and coefficient of variation(CV)of OUC-SIC were 3.877%and 10.582%,respectively,while those for FY-SIC were 7.836%and 7.982%,respectively.In the study area,compared with OUC-SIC data,FYSIC data exhibited a larger standard deviation of deviation and a smaller coefficient of variation of deviation across most sea areas.These results indicate that the OUC-SIC data exhibit better temporal and spatial stability,whereas the FY-SIC data show stronger relative dimensionless stability.Among the four correction models,all showed improvements over the original,unfused corrected data.The fusion corrections using the OLS,RF,UNet,and TransUnet models reduced RMSE by 5.563%,14.601%,42.927%,and48.316%,respectively.Correspondingly,R increased by 0.463%,1.176%,3.951%,and 4.342%,respectively.Among these models,TransUnet performed the best,effectively integrating the advantages of FY-SIC and OUC-SIC data and notably improving the overall accuracy and spatiotemporal stability of SIC data.
