基于机器学习的西北太平洋海雾预报模型研究

打开文本图片集

中图分类号：P457.7;P47 文献标志码：A 文章编号：2096-3599（2025）03-0018-12

DOI：10.19513/j.cnki.hyqxxb.20250117002

AbstractThe Northwest Pacific is one of the areas with the highest sea fog frequency globall and serves as a major shipping route. Currently，there are no dedicated sea fog prediction products for this region. Therefore， studyingthecharacteristicsandpredictionof theseafogin thisarea iscrucial.Based on thedata from Intermational Comprehensive Ocean-Atmosphere Data Set（ICOADS）and ERA5 data from 2O13 to 2023，this study analyzes the distribution characteristics of the sea fog over Northwest Pacific and develops a sea fog prediction model using the machine learning method.By calculating mutual information （MI）values，we identify 12 key factors closely related to the occurrence of sea fog，including sea surface temperature （SST）， relative humidity，difference between SST and dew point temperature （ （tSST-td） and geographical coordinates. To address the class imbalance between fog and non-fog samples， we apply resampling techniques and assess the impacts of various sampling strategies on the model performance. The results indicate that adding geographical information as factors and applying oversampling significantly improve the model performance， and the eXtreme Gradient Boosting（XGBoost）model shows the highest threat score.The feature importance analysis indicates that the difference between SSTand dew point temperature and relative humidity serveas thecore factors in the sea fog prediction model.Among comparative models，the XGBoost model achieves the best overall performance，folowed by the convolutional neural network （CNN）and support vector machine （SVM），and both CNN and SVM achieve a threat score above O.3. Case studies further confirm that the XGBoost model shows the best results，demonstrating the highest agreement with the observed fog coverage. This study reveals thecomplexities of sea fog formation over Northwest Pacific and provides a scientific basis for sea fog prediction over open ocean areas.

KeywordsNorthwest Pacific；sea fog prediction;machine learning;resampling

0 引言

海雾指受海洋影响，海上大气水平能见度小于1km 的天气现象[1]，对海上安全和经济活动有重要影响。（剩余15381字）