Seabed sediment classification is of great significance in acoustic remote sensing. To accurately classify seabed sediments, big data are needed to train the classifier. However, acquiring seabed sediment information is expensive and time-consuming, which makes it crucial to design a well-performing classifier using small-sample seabed sediment data. To avoid data shortage, a self-attention generative adversarial network (SAGAN) was trained for data augmentation in this study. SAGAN consists of a generator, which generates data similar to the real image, and a discriminator, which distinguishes whether the image is real or generated. Furthermore, a new classifier for seabed sediment based on self-attention densely connected convolutional network (SADenseNet) is proposed to improve the classification accuracy of seabed sediment. The SADenseNet was trained using augmented images to improve the classification performance. The self-attention mechanism can scan the global image to obtain global features of the sediment image and is able to highlight key regions, improving the efficiency and accuracy of visual information processing. The proposed SADenseNet trained with the augmented dataset had the best performance, with classification accuracies of 92.31%, 95.72%, 97.85%, and 95.28% for rock, sand, mud, and overall, respectively, with a kappa coefficient of 0.934. The twelve classifiers trained with the augmented dataset improved the classification accuracy by 2.25%, 5.12%, 0.97%, and 2.64% for rock, sand, mud, and overall, respectively, and the kappa coefficient by 0.041 compared to the original dataset. In this study, SAGAN can enrich the features of the data, which makes the trained classification networks have better generalization. Compared with the state-of-the-art classifiers, the proposed SADenseNet has better classification performance.

Microwave radiometers are passive remote sensing devices that are widely used in marine atmospheric observations. The accuracy of its inversion of temperature and humidity profiles is an important indicator of its performance. Back Propagation (BP) neural networks are widely used in the study of microwave radiometer inversion problems. However, the BP network which is carried by the radiometer inversion suffers from profile data collapse. To address this, this study introduced a residual network to improve the accuracy of water vapor vertical profiles. Aiming at the problem of large inversion temperature error due to the effect of turbulence on the light-travel phase induced by stationary fronts along the seashore in the subtropical monsoon climate region, we used historical data to establish the seasonal a priori mean profile and design a dead-zone residual adjustment model. The accuracy of the residual network and the deadband-adjusted residual network was verified using the meteorological records of the Taizhou region from 2013–2018, with the experimental data and BP hierarchical network as the comparison term. We found no data collapse in the temperature and humidity profile inversion results of the residual network. Relative to the initial BP hierarchical algorithm, where the error of water vapor in the range 6–10 km was reduced by 80%, the dead zone residual adjustment model in the inverse-temperature phenomenon reduced the sum of squares error by 21%, compared with the ordinary residual network inversion results. Our findings provide new insights into the accuracy improvement of radiometer remote sensing.

With the potential shown by artificial intelligence in recent years, deep learning has been widely used in the field of marine environment monitoring such as underwater image classification. It will be disturbed by the marine environment in the acquisition process of underwater acoustic images, which will lead to the acquisition of images containing a lot of noise information. In addition, it is very difficult to collect a large amount of underwater acoustic image data because it is expensive and time-consuming to do so. Both of these factors will reduce the accuracy of underwater acoustic image classification. In order to overcome the influence of the above factors, we proposed an underwater acoustic image classification method based on image denoising and transfer learning. Firstly, we use curvature filtering for image denoising to eliminate the noise contained in the image, which can effectively remove noise while maintaining the edge information of the image. Then we utilize the transfer learning technique to improve the accuracy of underwater acoustic image classification. The experimental results show that the curvature-filtered images have better image evaluation indexes than other methods. Moreover, the classification methods based on transfer learning has better classification accuracy than the ones without transfer learning.

Microwave radiometer is a passive remote sensing instrument. The MP3000A microwave radiometer is used in this study. To address the problem of time-series augmentation of contour data, this paper uses a super-resolution network model based on convolutional neural network for time-series augm-entation of 34,568 temperature contour data measured by $M$ P3000A from April 22, 2023 to June 15, 2023 in Harbin. High- resolution branches are added to the original super-resolution network, and the results are compared and analyzed by normal-izing and non-normalizing the original data. The heatmap of the temperature data error shows that the time series amplified temperature data is weakly different from the true value, with a mean square error MSE of 2.4831 and a mean absolute error MAE of 1.3213, and the network model performs well. It is shown that the use of super-resolution network model works well in time series for atmospheric microwave remote sensing data under the influence of the Pacific monsoon climate.