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

2019 ◽  
Author(s):  
Young Jun Kim ◽  
Hyun-Cheol Kim ◽  
Daehyeon Han ◽  
Sanggyun Lee ◽  
Jungho Im
Keyword(s):  
Neural Networks ◽  
Sea Ice ◽  
Prediction Model ◽  
Convolutional Neural Networks ◽  
Arctic Sea Ice ◽  
Ocean Current ◽  
Sea Ice Concentration ◽  
Model Based ◽  
Arctic Sea ◽  
Ice Concentration

Abstract. Changes in Arctic sea ice affect atmospheric circulation, ocean current, and polar ecosystems. There have been unprecedented decreases in the amount of Arctic sea ice, due to the global warming and its various adjoint cases. In this study, a novel one-month sea ice concentration (SIC) prediction model is proposed, with eight predictors using a deep learning approach, Convolutional Neural Networks (CNN). This monthly SIC prediction model based CNN is shown to perform better predictions (mean absolute error (MAE) of 2.28 %, root mean square error (RMSE) of 5.76 %, normalized RMSE (nRMSE) of 16.15 %, and NSE of 0.97) than a random forest (RF)-based model (MAE of 2.45 %, RMSE of 6.61 %, nRMSE of 18.64 %, and NSE of 0.96) and a simple prediction model based on the yearly trend (MAE of 9.36 %, RMSE of 21.93 %, nRMSE of 61.94 %, and NSE of 0.83) through hindcast validations. Spatiotemporal analysis also confirmed the superiority of the CNN model. The CNN model showed good SIC prediction results in extreme cases that recorded unforeseen sea ice plummets in 2007 and 2012 with less than 5.0 % RMSEs. This study also examined the importance of the input variables through a sensitivity analysis. In both the CNN and RF models, the variables of past SICs were identified as the most sensitive factor in predicting SIC. For both models, the SIC-related variables generally contributed more to predict SICs over ice-covered areas, while other meteorological and oceanographic variables were more sensitive to the prediction of SICs in marginal ice zones. The proposed one-month SIC prediction model provides valuable information which can be used in various applications, such as Arctic shipping route planning, management of fishery industry, and long-term sea ice forecasting and dynamics.

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

2020 ◽  
Vol 14 (3) ◽  
pp. 1083-1104
Author(s):  
Young Jun Kim ◽  
Hyun-Cheol Kim ◽  
Daehyeon Han ◽  
Sanggyun Lee ◽  
Jungho Im
Keyword(s):  
Neural Networks ◽  
Sea Ice ◽  
Prediction Model ◽  
Convolutional Neural Networks ◽  
Route Planning ◽  
Arctic Sea Ice ◽  
Ocean Current ◽  
Sea Ice Concentration ◽  
Model Based ◽  
Arctic Sea

Abstract. Changes in Arctic sea ice affect atmospheric circulation, ocean current, and polar ecosystems. There have been unprecedented decreases in the amount of Arctic sea ice due to global warming. In this study, a novel 1-month sea ice concentration (SIC) prediction model is proposed, with eight predictors using a deep-learning approach, convolutional neural networks (CNNs). This monthly SIC prediction model based on CNNs is shown to perform better predictions (mean absolute error – MAE – of 2.28 %, anomaly correlation coefficient – ACC – of 0.98, root-mean-square error – RMSE – of 5.76 %, normalized RMSE – nRMSE – of 16.15 %, and NSE – Nash–Sutcliffe efficiency – of 0.97) than a random-forest-based (RF-based) model (MAE of 2.45 %, ACC of 0.98, RMSE of 6.61 %, nRMSE of 18.64 %, and NSE of 0.96) and the persistence model based on the monthly trend (MAE of 4.31 %, ACC of 0.95, RMSE of 10.54 %, nRMSE of 29.17 %, and NSE of 0.89) through hindcast validations. The spatio-temporal analysis also confirmed the superiority of the CNN model. The CNN model showed good SIC prediction results in extreme cases that recorded unforeseen sea ice plummets in 2007 and 2012 with RMSEs of less than 5.0 %. This study also examined the importance of the input variables through a sensitivity analysis. In both the CNN and RF models, the variables of past SICs were identified as the most sensitive factor in predicting SICs. For both models, the SIC-related variables generally contributed more to predict SICs over ice-covered areas, while other meteorological and oceanographic variables were more sensitive to the prediction of SICs in marginal ice zones. The proposed 1-month SIC prediction model provides valuable information which can be used in various applications, such as Arctic shipping-route planning, management of the fishing industry, and long-term sea ice forecasting and dynamics.

Arctic sea ice volume budget decomposition satellite product for the CryoSat-2 (2010-2020) period 

2021 ◽  
Author(s):  
Harry Heorton ◽  
Michel Tsamados ◽  
Paul Holland ◽  
Jack Landy
Keyword(s):  
Sea Ice ◽  
Climate Model ◽  
Volume Growth ◽  
Arctic Sea Ice ◽  
First Year ◽  
Sea Ice Concentration ◽  
Marginal Seas ◽  
Ice Volume ◽  
Arctic Sea ◽  
Ice Concentration

<p><span>We combine satellite-derived observations of sea ice concentration, drift, and thickness to provide the first observational decomposition of the dynamic (advection/divergence) and thermodynamic (melt/growth) drivers of wintertime Arctic sea ice volume change. Ten winter growth seasons are analyzed over the CryoSat-2 period between October 2010 and April 2020. Sensitivity to several observational products is performed to provide an estimated uncertainty of the budget calculations. The total thermodynamic ice volume growth and dynamic ice losses are calculated with marked seasonal, inter-annual and regional variations</span><span>. Ice growth is fastest during Autumn, in the Marginal Seas and over first year ice</span><span>. Our budget decomposition methodology can help diagnose the processes confounding climate model predictions of sea ice. We make our product and code available to the community in monthly pan-Arctic netcdft files for the entire October 2010 to April 2020 period.</span></p>

Gridded Arctic sea ice concentration reconstruction for the first half of the 20th century based on different proxy data

2021 ◽  
Author(s):  
Vladimir Semenov ◽  
Tatiana Matveeva
Keyword(s):  
Sea Ice ◽  
20Th Century ◽  
Climate Model ◽  
Surface Air Temperature ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
The North ◽  
Arctic Sea ◽  
Ice Concentration

<p>Global warming in the recent decades has been accompanied by a rapid recline of the Arctic sea ice area most pronounced in summer (10% per decade). To understand the relative contribution of external forcing and natural variability to the modern and future sea ice area changes, it is necessary to evaluate a range of long-term variations of the Arctic sea ice area in the period before a significant increase in anthropogenic emissions of greenhouse gases into the atmosphere. Available observational data on the spatiotemporal dynamics of Arctic sea ice until 1950s are characterized by significant gaps and uncertainties. In the recent years, there have appeared several reconstructions of the early 20<sup>th</sup> century Arctic sea ice area that filled the gaps by analogue methods or utilized combined empirical data and climate model’s output. All of them resulted in a stronger that earlier believed negative sea ice area anomaly in the 1940s concurrent with the early 20<sup>th</sup> century warming (ETCW) peak. In this study, we reconstruct the monthly average gridded sea ice concentration (SIC) in the first half of the 20th century using the relationship between the spatiotemporal features of SIC variability, surface air temperature over the Northern Hemisphere extratropical continents, sea surface temperature in the North Atlantic and North Pacific, and sea level pressure. In agreement with a few previous results, our reconstructed data also show a significant negative anomaly of the Arctic sea ice area in the middle of the 20th century, however with some 15% to 30% stronger amplitude, about 1.5 million km<sup>2</sup> in September and 0.7 million km<sup>2</sup> in March. The reconstruction demonstrates a good agreement with regional Arctic sea ice area data when available and suggests that ETWC in the Arctic has been accompanied by a concurrent sea ice area decline of a magnitude that have been exceeded only in the beginning of the 21<sup>st</sup> century.</p>

Sea-ice freeboard or thickness? Design choices in the context of data assimilation in the coupled numerical prediction system EC-Earth3 for seasonal Arctic sea ice prediction

2021 ◽  
Author(s):  
Francois Massonnet ◽  
Sara Fleury ◽  
Florent Garnier ◽  
Ed Blockley ◽  
Pablo Ortega Montilla ◽  
...  
Keyword(s):  
Data Assimilation ◽  
Sea Ice ◽  
General Circulation ◽  
Seasonal Prediction ◽  
Arctic Sea Ice ◽  
Ice Thickness ◽  
Sea Ice Concentration ◽  
Sea Ice Thickness ◽  
Arctic Sea ◽  
Ice Concentration

<p>It is well established that winter and spring Arctic sea-ice thickness anomalies are a key source of predictability for late summer sea-ice concentration. While numerical general circulation models (GCMs) are increasingly used to perform seasonal predictions, they are not systematically taking advantage of the wealth of polar observations available. Data assimilation, the study of how to constrain GCMs to produce a physically consistent state given observations and their uncertainties, remains, therefore, an active area of research in the field of seasonal prediction. With the recent advent of satellite laser and radar altimetry, large-scale estimates of sea-ice thickness have become available for data assimilation in GCMs. However, the sea-ice thickness is never directly observed by altimeters, but rather deduced from the measured sea-ice freeboard (the height of the emerged part of the sea ice floe) based on several assumptions like the depth of snow on sea ice and its density, which are both often poorly estimated. Thus, observed sea-ice thickness estimates are potentially less reliable than sea-ice freeboard estimates. Here, using the EC-Earth3 coupled forecasting system and an ensemble Kalman filter, we perform a set of sensitivity tests to answer the following questions: (1) Does the assimilation of late spring observed sea-ice freeboard or thickness information yield more skilful predictions than no assimilation at all? (2) Should the sea-ice freeboard assimilation be preferred over sea-ice thickness assimilation? (3) Does the assimilation of observed sea-ice concentration provide further constraints on the prediction? We address these questions in the context of a realistic test case, the prediction of 2012 summer conditions, which led to the all-time record low in Arctic sea-ice extent. We finally formulate a set of recommendations for practitioners and future users of sea ice observations in the context of seasonal prediction.</p>

Unexpectedly high dimethyl sulfide concentration in high-latitude Arctic sea ice melt ponds

2019 ◽  
Vol 21 (10) ◽  
pp. 1642-1649 ◽  
Author(s):  
Keyhong Park ◽  
Intae Kim ◽  
Jung-Ok Choi ◽  
Youngju Lee ◽  
Jinyoung Jung ◽  
...  
Keyword(s):  
Sea Ice ◽  
High Latitude ◽  
Dimethyl Sulfide ◽  
Arctic Sea Ice ◽  
Sulfide Concentration ◽  
Sea Ice Concentration ◽  
Ice Melt ◽  
Melt Ponds ◽  
Arctic Sea ◽  
Ice Concentration

Dimethyl sulfide (DMS) production in the northern Arctic Ocean has been considered to be minimal because of high sea ice concentration and extremely low productivity.

Sign in / Sign up

Export Citation Format

Share Document