Machine Learning Incorporated With Causal Analysis for Short-Term Prediction of Sea Ice

Accurate and fast prediction of sea ice conditions is the foundation of safety guarantee for Arctic navigation. Aiming at the imperious demand of short-term prediction for sea ice, we develop a new data-driven prediction technique for the sea ice concentration (SIC) combined with causal analysis. Through the causal analysis based on kernel Granger causality (KGC) test, key environmental factors affecting SIC are selected. Then multiple popular machine learning (ML) algorithms, namely self-adaptive differential extreme learning machine (SaD-ELM), classification and regression tree (CART), random forest (RF) and support vector regression (SVR), are employed to predict daily SIC, respectively. The experimental results in the Barents-Kara (B-K) sea show: (1) compared with correlation analysis, the input variables of ML models screened out by causal analysis achieve better prediction; (2) when lead time is short (<3 d), the four ML algorithms are all suitable for short-term prediction of daily SIC, while RF and SaD-ELM have better prediction performance with long lead time (>3 d); (3) RF has the best prediction accuracy and generalization ability but hugely time consuming, while SaD-ELM achieves more favorable performance when taking computational complexity into consideration. In summary, ML is applicable to short-term prediction of daily SIC, which develops a new way of sea ice prediction and provides technical support for Arctic navigation.

[1]  Zhiping Lin,et al.  Self-Adaptive Evolutionary Extreme Learning Machine , 2012, Neural Processing Letters.

[2]  Elizabeth C. Kent,et al.  Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century , 2003 .

[3]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

[4]  M. Paluš,et al.  Comparison of six methods for the detection of causality in a bivariate time series. , 2018, Physical review. E.

[5]  Steffen Tietsche,et al.  A review on Arctic sea‐ice predictability and prediction on seasonal to decadal time‐scales , 2016 .

[6]  J. Wallace,et al.  Arctic Sea Ice Variability on a Timescale of Weeks and Its Relation to Atmospheric Forcing , 1994 .

[7]  E. Barnes,et al.  New Insights on Subseasonal Arctic–Midlatitude Causal Connections from a Regularized Regression Model , 2019, Journal of Climate.

[8]  G. Vecchi,et al.  Skillful regional prediction of Arctic sea ice on seasonal timescales , 2017 .

[9]  I. Simmonds,et al.  The central role of diminishing sea ice in recent Arctic temperature amplification , 2010, Nature.

[10]  Lindi J. Quackenbush,et al.  The MODIS ice surface temperature product as an indicator of sea ice minimum over the Arctic Ocean , 2014 .

[11]  Yanlin Wang,et al.  Sea Ice Management for Oil and Gas Platforms in the Bohai Sea , 2017 .

[12]  Kwangjin Kim,et al.  Satellite-Based Prediction of Arctic Sea Ice Concentration Using a Deep Neural Network with Multi-Model Ensemble , 2018, Remote. Sens..

[13]  George Sugihara,et al.  Detecting Causality in Complex Ecosystems , 2012, Science.

[14]  Bernhard Schölkopf,et al.  Inferring causation from time series in Earth system sciences , 2019, Nature Communications.

[15]  M. Déqué,et al.  Seasonal Forecasts of the Pan-Arctic Sea Ice Extent Using a GCM-Based Seasonal Prediction System , 2013 .

[16]  Lawrence C. Hamilton,et al.  Predicting September sea ice: Ensemble skill of the SEARCH Sea Ice Outlook 2008–2013 , 2014 .

[17]  Ming Li,et al.  Application of Intelligent Dynamic Bayesian Network with Wavelet Analysis for Probabilistic Prediction of Storm Track Intensity Index , 2018, Atmosphere.

[18]  Jonathan F. Donges,et al.  Using Causal Effect Networks to Analyze Different Arctic Drivers of Midlatitude Winter Circulation , 2016 .

[19]  James A. Maslanik,et al.  A practical method for long‐range forecasting of ice severity in the Beaufort Sea , 2002 .

[20]  Ming Li,et al.  Probabilistic Prediction of Significant Wave Height Using Dynamic Bayesian Network and Information Flow , 2020, Water.

[21]  J. Ringsberg,et al.  A voyage planning tool for ships sailing between Europe and Asia via the Arctic , 2020 .

[22]  Ian Simmonds,et al.  The Atmospheric Response to Three Decades of Observed Arctic Sea Ice Loss , 2013 .

[23]  D. Luo,et al.  Ural Blocking as an Amplifier of the Arctic Sea Ice Decline in Winter , 2017 .

[24]  C. Sims.  Money, Income, and Causality , 1972 .

[25]  Charles Fowler,et al.  A long‐range forecast of Arctic summer sea‐ice minimum extent , 2006 .

[26]  Daniele Marinazzo,et al.  Kernel method for nonlinear granger causality. , 2007, Physical review letters.

[27]  Jinlun Zhang,et al.  Accuracy of short‐term sea ice drift forecasts using a coupled ice‐ocean model , 2015, Journal of geophysical research. Oceans.

[28]  Michael Steele,et al.  Seasonal predictions of ice extent in the Arctic Ocean , 2008 .

[29]  X. Liang,et al.  Unraveling the cause-effect relation between time series. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[30]  Julienne C. Stroeve,et al.  Arctic Sea Ice Extent Plummets in 2007 , 2008 .

[31]  David A. Clausi,et al.  Sea Ice Concentration Estimation during Freeze-Up from SAR Imagery Using a Convolutional Neural Network , 2017, Remote. Sens..

[32]  C. Deser,et al.  Evolution of Arctic sea ice concentration trends and the role of atmospheric circulation forcing, 1979–2007 , 2008 .

[33]  Chengzu Bai,et al.  Forecasting the Tropical Cyclone Genesis over the Northwest Pacific through Identifying the Causal Factors in Cyclone–Climate Interactions , 2017 .

[34]  Dake Chen,et al.  A Markov Model for Seasonal Forecast of Antarctic Sea Ice , 2004 .

[35]  Junhwa Chi,et al.  Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network , 2017, Remote. Sens..

[36]  Ken Caldeira,et al.  Atmospheric impacts of sea ice decline in CO2 induced global warming , 2015, Climate Dynamics.

[37]  Arctic Sea Ice Seasonal Prediction by a Linear Markov Model , 2016 .

[38]  E. Carmack,et al.  Pacific Ocean inflow: Influence on catastrophic reduction of sea ice cover in the Arctic Ocean , 2006 .

[39]  Michael Karcher,et al.  Future sea ice conditions and weather forecasts in the Arctic: Implications for Arctic shipping , 2017, Ambio.

[40]  Ming Li,et al.  Causality-Based Attribute Weighting via Information Flow and Genetic Algorithm for Naive Bayes Classifier , 2019, IEEE Access.

[41]  Lei Wang,et al.  Predicting Summer Arctic Sea Ice Concentration Intraseasonal Variability Using a Vector Autoregressive Model , 2016 .

[42]  Sayan Mukherjee,et al.  Feature Selection for SVMs , 2000, NIPS.

[43]  Salil Mahajan,et al.  Impact of the Atlantic Meridional Overturning Circulation (AMOC) on Arctic Surface Air Temperature and Sea Ice Variability , 2011 .