☆ 4.7 Article

Subseasonal Prediction of Regional Antarctic Sea Ice by a Deep Learning Model

GEOPHYSICAL RESEARCH LETTERS (2023)

Related references

Note: Only part of the references are listed.

Article Meteorology & Atmospheric Sciences

Understanding Arctic Sea Ice Thickness Predictability by a Markov Model

Yunhe Wang et al.

Summary: The study developed a linear Markov model for the seasonal prediction of sea ice thickness (SIT). The model performed better in the cold season and up to 12 months in advance in the Arctic basin. The model skill remained high even after removing trends and the upper-ocean heat content (OHC) was found to contribute more to SIT prediction skill than other variables.

JOURNAL OF CLIMATE (2023)

Add to Collection

Article Geosciences, Multidisciplinary

Subseasonal Prediction of Regional Antarctic Sea Ice by a Deep Learning Model

Yunhe Wang et al.

Summary: A deep learning model called SIPNet has been developed to predict Antarctic sea ice concentration (SIC) at subseasonal scale, filling the gap in prediction capability. Autumn SIC variability contributes the most to sea ice predictability, whereas spring contributes the least. SIPNet can also capture the signal of ENSO and SAM on sea ice.

GEOPHYSICAL RESEARCH LETTERS (2023)

Add to Collection

Article Geochemistry & Geophysics

Predicting the Daily Sea Ice Concentration on a Subseasonal Scale of the Pan-Arctic During the Melting Season by a Deep Learning Model

Yibin Ren et al.

Summary: Predicting the daily sea ice concentration (SIC) of the Pan-Arctic during the melting season is crucial but challenging. In this study, we propose a deep-learning-based data driven model, SICNet90, which utilizes historical SIC data to predict the SIC of the next 90 days. We also design a physically constrained loss function to optimize the model's prediction accuracy. Experimental results show that SICNet90 outperforms the Climatology benchmark, achieving a significant improvement in binary accuracy and mean absolute error. Additionally, the model exhibits a predictability barrier and challenge, which aligns with the autocorrelation of SIC. The use of historical SIC data and other environmental factors contribute to the prediction accuracy.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2023)

Add to Collection

Article Environmental Sciences

A regime shift in seasonal total Antarctic sea ice extent in the twentieth century

Ryan L. Fogt et al.

Summary: In contrast to the Arctic, there has been a significant increase in Antarctic sea ice extent since 1979. However, the short and highly variable nature of observed Antarctic sea ice extent limits our understanding of its historical context. Through reconstructions, it has been found that the period since 1979 is the only time when all four seasons show a significant increase in Antarctic sea ice, with significant decreases in the early and middle twentieth century. These reconstructions provide reliable estimates of seasonally resolved Antarctic sea ice extent and can improve our understanding of air-sea-ice interactions in the Antarctic climate system.

NATURE CLIMATE CHANGE (2022)

Add to Collection

Article Environmental Sciences

The relative role of the subsurface Southern Ocean in driving negative Antarctic Sea ice extent anomalies in 2016-2021

Liping Zhang et al.

Summary: This study investigates the causes of low Antarctic sea ice extent using a coupled climate model partially constrained by observations. It finds that the subsurface Southern Ocean plays a critical role in the persistence of negative sea ice anomalies over 2016-2021, with the warming and destabilization of the ocean reducing sea ice extent over several years. The simultaneous variations in the atmosphere and ocean after 2016 further amplify the decline in Antarctic sea ice extent.

COMMUNICATIONS EARTH & ENVIRONMENT (2022)

Add to Collection

Article Geochemistry & Geophysics

A Data-Driven Deep Learning Model for Weekly Sea Ice Concentration Prediction of the Pan-Arctic During the Melting Season

Yibin Ren et al.

Summary: This study proposes a purely data-driven model, SICNet, for the weekly prediction of daily sea ice concentration of the pan-Arctic during the melting season. The model achieves high accuracy and outperforms existing deep-learning-based models. The temporal-spatial attention module helps capture spatiotemporal dependencies, resulting in better performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Add to Collection

Article Geography, Physical

Reassessing seasonal sea ice predictability of the Pacific-Arctic sector using a Markov model

Yunhe Wang et al.

Summary: A regional linear Markov model is developed to evaluate seasonal sea ice predictability in the Pacific-Arctic sector. The model consists of four seasonal modules with different predictor variables, accommodating seasonally varying driving processes. The model shows improved predictive skill compared to the pan-Arctic model, and retains skill in detrended sea ice extent predictions for up to 7-month lead times.

CRYOSPHERE (2022)

Add to Collection

Article Meteorology & Atmospheric Sciences

Extended-Range Arctic Sea Ice Forecast with Convolutional Long Short-Term Memory Networks

Yang Liu et al.

Summary: This study introduces a deep learning approach (ConvLSTM) to forecast sea ice in the Barents Sea at weather to subseasonal time scales, demonstrating skillful predictions at weekly to monthly time frames. The method utilizes historical records and covariances between variables, maintaining physical consistency and outperforming traditional forecasting methods. Sensitivity tests show that surface energy budget components significantly impact sea ice predictability at weather time scales. This promising approach could enhance operational Arctic sea ice forecasting in the future.

MONTHLY WEATHER REVIEW (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

Seasonal Prediction and Predictability of Regional Antarctic Sea Ice

Mitchell Bushuk et al.

Summary: The study compares the seasonal prediction skill and predictability of Antarctic sea ice using three coupled dynamical prediction systems. Each system is capable of skillfully predicting regional Antarctic sea ice extent, with the recently developed SPEAR systems showing more skill than FLOR. Zonally advected upper-ocean heat content anomalies are found to provide a crucial source of prediction skill for the winter sea ice edge position.

JOURNAL OF CLIMATE (2021)

Add to Collection

Article Multidisciplinary Sciences

Summertime sea-ice prediction in the Weddell Sea improved by sea-ice thickness initialization

Yushi Morioka et al.

Summary: This study demonstrates skillful prediction of summertime sea-ice concentration in the Weddell Sea using a coupled general circulation model, with wintertime sea-ice thickness initialization showing benefits for skillful prediction.

SCIENTIFIC REPORTS (2021)

Add to Collection

Article Multidisciplinary Sciences

Seasonal Arctic sea ice forecasting with probabilistic deep learning

Tom R. Andersson et al.

Summary: Accurate seasonal forecasts of sea ice are crucial in the context of global warming-induced sea ice loss. IceNet, a new machine learning tool, significantly improves the accuracy of sea ice forecasting compared to physics-based dynamical models. The unprecedented year-round reduction in Arctic sea ice extent due to anthropogenic warming highlights the importance of accurate seasonal sea ice forecasts in mitigating risks associated with rapid sea ice loss.

NATURE COMMUNICATIONS (2021)

Add to Collection

Review Environmental Sciences

Tropical teleconnection impacts on Antarctic climate changes

Xichen Li et al.

Summary: A substantial climatic changes have been observed in the Antarctic over the modern satellite era, many of which are believed to be influenced by tropical-polar teleconnections through Rossby wave dynamics. These connections play a significant role in shaping Antarctic climate variability and changes in recent years.

NATURE REVIEWS EARTH & ENVIRONMENT (2021)

Add to Collection

Article Meteorology & Atmospheric Sciences

SPEAR: The Next Generation GFDL Modeling System for Seasonal to Multidecadal Prediction and Projection

Thomas L. Delworth et al.

JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS (2020)

Add to Collection

Article Geography, Physical

Modeling the annual cycle of daily Antarctic sea ice extent

Mark S. Handcock et al.

CRYOSPHERE (2020)

Add to Collection

Article Geography, Physical

Prediction of monthly Arctic sea ice concentrations using satellite and reanalysis data based on convolutional neural networks

Young Jun Kim et al.

CRYOSPHERE (2020)

Add to Collection

Article Meteorology & Atmospheric Sciences

Reemergence of Antarctic sea ice predictability and its link to deep ocean mixing in global climate models

Sylvain Marchi et al.

CLIMATE DYNAMICS (2019)

Add to Collection

Article Multidisciplinary Sciences

A 40-y record reveals gradual Antarctic sea ice increases followed by decreases at rates far exceeding the rates seen in the Arctic

Claire L. Parkinson

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2019)

Add to Collection

Article Geosciences, Multidisciplinary

Predictability of Antarctic Sea Ice Edge on Subseasonal Time Scales

Lorenzo Zampieri et al.

GEOPHYSICAL RESEARCH LETTERS (2019)

Add to Collection

Article Multidisciplinary Sciences

Sustained ocean changes contributed to sudden Antarctic sea ice retreat in late 2016

Gerald A. Meehl et al.

NATURE COMMUNICATIONS (2019)

Add to Collection

Review Meteorology & Atmospheric Sciences

The Interconnected Global Climate System-A Review of Tropical-Polar Teleconnections

Xiaojun Yuan et al.

JOURNAL OF CLIMATE (2018)

Add to Collection

Article Meteorology & Atmospheric Sciences

Positive Trend in the Antarctic Sea Ice Cover and Associated Changes in Surface Temperature

Josefino C. Comiso et al.

JOURNAL OF CLIMATE (2017)

Add to Collection

Article Environmental Sciences

Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network

Junhwa Chi et al.

REMOTE SENSING (2017)

Add to Collection

Article Meteorology & Atmospheric Sciences

THE AMUNDSEN SEA LOW Variability, Change, and Impact on Antarctic Climate

M. N. Raphael et al.

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY (2016)

Add to Collection

Article Meteorology & Atmospheric Sciences

Pacific Influences on Tropical Atlantic Teleconnections to the Southern Hemisphere High Latitudes

Graham R. Simpkins et al.

JOURNAL OF CLIMATE (2016)

Add to Collection

Article Geosciences, Multidisciplinary

Antarctic sea-ice expansion between 2000 and 2014 driven by tropical Pacific decadal climate variability

Gerald A. Meehl et al.

NATURE GEOSCIENCE (2016)

Add to Collection

Article Multidisciplinary Sciences

Impacts of the north and tropical Atlantic Ocean on the Antarctic Peninsula and sea ice

Xichen Li et al.

NATURE (2014)

Add to Collection

Article Geosciences, Multidisciplinary

Initial-value predictability of Antarctic sea ice in the Community Climate System Model 3

Marika M. Holland et al.

GEOPHYSICAL RESEARCH LETTERS (2013)

Add to Collection

Article Oceanography

Climate modes in southern high latitudes and their impacts on Antarctic sea ice

Xiaojun Yuan et al.

JOURNAL OF GEOPHYSICAL RESEARCH-OCEANS (2008)

Add to Collection

Article Environmental Sciences

ENSO-related impacts on Antarctic sea ice: a synthesis of phenomenon and mechanisms

XJ Yuan

ANTARCTIC SCIENCE (2004)

Add to Collection

Article Meteorology & Atmospheric Sciences

Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century

NA Rayner et al.

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES (2003)

Add to Collection

© Peeref 2019-2024. All rights reserved.