节点文献
基于机器学习的海洋环境预报订正方法研究
Research on correction method of marine environment prediction based on machine learning
【摘要】 结合中尺度数值模式WRF预报数据和ERA5再分析资料,利用机器学习方法对WRF预报场的风场、温度、气压进行预报订正。采用ERA5作为真值,与原始WRF预报相比,利用随机森林模型可以将预报结果整体均方根误差降低44%以上,利用深度神经网络模型可以将预报结果整体均方根误差降低34%以上。通过随机森林模型实验得到不同输入特征对预报要素的影响程度,分析了关键的预报订正因子。
【Abstract】 Combining the mesoscale numerical model WRF and the ERA5 reanalysis data, machine learning method is used to improve the forecast accuracy of wind, temperature and pressure. ERA5 is assumed as the true value. Comparing with the bare forecast of WRF, the random forest model reduces the overall RMSE more than 44%, while the deep neural network reduces the overall RMSE more than 34%. The random forest model experiment shows that the influence of different input features on the forecast elements, based on which the key forecast correction factors are analyzed.
【Key words】 WRF model; random forest; deep neural network; forecast correction;
- 【文献出处】 海洋通报 ,Marine Science Bulletin , 编辑部邮箱 ,2020年06期
- 【分类号】TP181;P73
- 【被引频次】5
- 【下载频次】362