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

Abstract

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.

Expert Knowledge-Driven Bayesian Network Modeling for Marine Disaster Assessment Under the Small Sample Condition

“…The BN-based assessment model is an intelligent model and we focus on comparing it with other intelligent assessment models. At present, BPNN and SVM have achieved successful applications in the field of risk assessment (Feng and Liu, 2017;Li et al, 2021a Figure 6 displays the disaster assessment results of the three models. The assessment accuracy of BPNN and SVM are 61.34 and 70.67%, respectively, which are significantly lower than the accuracy of BN (91.03%).…”

“…Through systematic analysis of risk-causing factors and riskbearing bodies of marine disasters, Li et al (2018b) adopted the BN and gray relational analysis to build a risk assessment model. Then, Li et al (2020;2021a) also proposed the improved weighted BN to mine the causal relationship of disaster factors and realized probabilistic reasoning of marine disaster risk.…”

Modeling of Precipitation Prediction Based on Causal Analysis and Machine Learning

“…McGraw et al [25] examined the causal relationship between Arctic sea ice and atmospheric circulation using Granger causal analysis. Li et al [26] developed a new data-driven prediction technique for sea ice density by screening the key environmental factors affecting the sea ice density through causal analysis based on the Granger causality test. Liang et al [27] demonstrated that the South China Sea significantly influences the Pacific-North America remote sensing model, using the causal inference of information flow.…”