Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model
Oceanic internal wave amplitude retrieval from satellite images based on a data-driven transfer learning model
复制标题
基于数据驱动迁移学习模型的卫星图像海洋内波振幅反演
DOI：
10.1016/j.rse.2022.112940
复制
发表时间：
2022-04
影响因子：
13.5
通讯作者：
Li Xiaofeng
中科院分区：
文献类型：
--
作者：
Zhang Xudong;Wang Haoyu;Wang Shuo;Liu Yanliang;Yu Weidong;Wang Jing;Xu Qing;Li Xiaofeng
内波具有振幅大、波峰长、传播距离长的特点。它们广泛分布于全球海洋。振幅是一个重要的IW参数，是很难从卫星图像中的IW表面特征。通过室内实验和卫星/现场联合测量，建立了两个内波数据集（888对实验室数据和121对同步现场数据和卫星图像）。为了有效地利用实验室数据，我们实现了一个迁移学习模型来从卫星图像中检索IW振幅。该模型是一个纯数据驱动的模型，使用实验室数据进行预训练，并使用卫星/现场数据进行重新训练。在迁移学习框架中加入了一个短连接，以减少信息丢失。采用偏差校正方法提高模型的精度。修正后的IW振幅估计值的均方根误差（RMSE）由修正前的12.09 m（17.84米）至9.59米（11.59 m），平均相对误差由21%（27%）下降到18%（16%），在测试（训练）数据集上，相关系数从0.81（0.72）提高到0.89（0.90）。对于振幅超过100 m的IWS，该模型可以预期得到10 m的绝对误差。平均相对误差随IW幅值的增大而减小。与其他算法的比较表明，该模型是有效的IW研究。应用该模型对安达曼海156幅包含IW特征的卫星图像进行了分析，发现大振幅IW主要分布在大陆坡200 ~ 1000 m水深处。当考虑峰-峰（PP）距离的一个像素输入误差时，模型显示出对误差的大容忍度。与基于KdV方程的方法相比，该模型具有更高的精度。
Internal waves (IW) are characterized by a large-amplitude, long-wave crest, and long-propagation distance. They are widespread in the global ocean. Amplitude is an essential IW parameter and is difficult to derive from the IW surface signatures in satellite images. A laboratory experiment and combined satellite/in-situ measurements were carried out to build two internal wave datasets (888 pairs of lab data and 121 pairs of synchronous in-situ data and satellite images). To efficiently use the lab data, we implemented a transfer learning model to retrieve IW amplitude from satellite images. The model is a purely data-driven model pre-trained with lab data and re-trained with satellite/in-situ data. A short connection was incorporated into the transfer learning framework to reduce information loss. Bias correction was adopted to improve the model performance. After the correction, the root mean square error (RMSE) of the estimated IW amplitude decreased from 12.09 m (17.84 m) to 9.59 m (11.59 m), the mean relative error decreased from 21% (27%) to 18% (16%), and the correlation coefficients improved from 0.81 (0.72) to 0.89 (0.90) on the test (training) dataset. For IWs with amplitude exceeding 100 m, the model can be expected to get an absolute error of 10 m. The mean relative error decreased with the increase in IW amplitudes. Comparisons with other algorithms demonstrate that the proposed model is efficient for IW studies. We applied the model to 156 satellite images containing IW signatures in the Andaman Sea, finding that large-amplitude IWs were mainly located at the water depth between 200 m and 1000 m on the continental slope. When considering one-pixel input errors for the peak-to-peak (PP) distance, the model shows large tolerance with the errors. Compared with the KdV equation-based method, the developed model was more accurate.
登录
查看更多内容
南海文昌海域内波振幅反演研究
影响因子：
1.4
作者：
Zhang Xudong;Wang Jing;Sun Lina;Meng Junmin
通讯作者：
Meng Junmin
影响因子：
13.5
作者：
I. Kozlov;D. Romanenkov;A. Zimin;B. Chapron
通讯作者：
I. Kozlov;D. Romanenkov;A. Zimin;B. Chapron
DOI：
10.1109/igarss.1999.773434
发表时间：
1999-06
期刊：
IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293)
影响因子：
--
作者：
M. Marghany
通讯作者：
M. Marghany
影响因子：
5.2
作者：
Xiaofeng Li;Christopher R. Jackson;W. Pichel
通讯作者：
Xiaofeng Li;Christopher R. Jackson;W. Pichel
DOI：
10.21046/2070-7401-2020-17-4-221-230
发表时间：
2020
期刊：
--
影响因子：
--
作者：
E. Zubkova;I. Kozlov
通讯作者：
E. Zubkova;I. Kozlov