English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. Changes in Arctic sea ice affect atmospheric circulation,ocean current, and polar ecosystems. There have been unprecedented decreasesin 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-learningapproach, convolutional neural networks (CNNs). This monthly SIC predictionmodel based on CNNs is shown to perform better predictions (mean absoluteerror – 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 %, ACCof 0.98, RMSE of 6.61 %, nRMSE of 18.64 %, and NSE of 0.96) and thepersistence 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 hindcastvalidations. The spatio-temporal analysis also confirmed the superiority ofthe CNN model. The CNN model showed good SIC prediction results in extremecases that recorded unforeseen sea ice plummets in 2007 and 2012 with RMSEs of lessthan 5.0 %. This study also examined the importance of the inputvariables through a sensitivity analysis. In both the CNN and RF models, thevariables of past SICs were identified as the most sensitive factor inpredicting SICs. For both models, the SIC-related variables generallycontributed more to predict SICs over ice-covered areas, while othermeteorological and oceanographic variables were more sensitive to theprediction of SICs in marginal ice zones. The proposed 1-month SICprediction model provides valuable information which can be used in variousapplications, such as Arctic shipping-route planning, management of the fishingindustry, and long-term sea ice forecasting and dynamics.

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