Chengzu Bai

High-resolution synthetic aperture radars (SARs) are becoming an indispensable environmental monitoring system to capture the important geophysical phenomena on the earth and sea surface. However, there is a lack of comprehensive models that can orchestrate such large-scale datasets from numerous satellite missions such as GaoFen-3 and Sentinel-1. In addition, these SAR images of different ocean scenes need to convey a variety of high-level classification features in oceanic and atmospheric phenomena. In this study, we propose a multichannel neural network (MCNN) that supports oceanic SAR scene classification for limited oceanic data samples according to multi-feature fusion, data augmentation, and multichannel feature extraction. To exploit the multichannel semantics of SAR scenes, the multi-feature fusion module effectively combines and reshapes the spatiotemporal SAR images to preserve their structural properties. This fine-grained feature augmentation policy is extended to improve the data quality so that the classification model is less vulnerable to both small- and large-scale data. The multichannel feature extraction also aggregates different oceanic features convolutionally extracted from ocean SAR scenes to improve the classification accuracy of oceanic phenomena with different scales. Through extensive experimental analysis, our MCNN framework has demonstrated a commendable classification performance, achieving an average precision rate of 96%, an average recall rate of 95%, and an average F-score of 95% across ten distinct oceanic phenomena. Notably, it surpasses two state-of-the-art classification techniques, namely, AlexNet and CMwv, by margins of 23.7% and 18.3%, respectively.

Sea surface temperature (SST) fronts are important for fisheries and marine ecology, as well as upper-ocean dynamics, weather forecasting, and climate monitoring. In this paper, we propose a new approach to detect SST fronts from RADARSAT-2 ScanSAR images, based on the correlation of SAR-derived wind speeds using the gray level cooccurrence matrix (GLCM) approach. Due to the large differences between the correlation of wind speeds for SST fronts compared to other areas, SST fronts can be detected by the threshold method. To eliminate small-scale features (or noise), the 30 km scale is used as the length threshold for the detection of the SST fronts. The proposed method is effective when wind speeds are between 3 and 13 m s⁻¹. The overall accuracy of our method is about 93.6%, which is sufficient for operational applications.

Previously the interannual variability of tropical cyclone genesis (TCG) in the Australian region has mainly been attributed to the climate variability in the Pacific and Indian Oceans. In this study, we found that the influence from climate variability in the Atlantic is of equal importance. Application of a state-of-the-art causality analysis reveals that the Atlantic meridional mode (AMM), Atlantic multidecadal oscillation (AMO) and north tropical Atlantic (NTA) sea surface temperature (SST) anomalies are all causal to the Australian region TCG frequency. The associated physical mechanisms are investigated as well. Based on this causal analysis and inference, a statistical model is constructed to forecast TCG, using the Poisson regression and the step-by-step predictor selection method. The Atlantic causal factors, after being taken in as new predictors, help increase the forecast skill for the seasonal Australian region TCG by as much as 10% in terms of correlation increase and 40% in terms of root-mean-square error reduction.

Previously the interannual variability of tropical cyclone genesis (TCG) in the Australian region has mainly been attributed to the climate variability in the Pacific and Indian Oceans. In this study, we found that the influence from climate variability in the Atlantic is of equal importance. Application of a state-of-the-art causality analysis reveals that the Atlantic meridional mode (AMM), Atlantic multidecadal oscillation (AMO) and north tropical Atlantic (NTA) sea surface temperature (SST) anomalies are all causal to the Australian region TCG frequency. The associated physical mechanisms are investigated as well. Based on this causal analysis and inference, a statistical model is constructed to forecast TCG, using the Poisson regression and the step-by-step predictor selection method. The Atlantic causal factors, after being taken in as new predictors, help increase the forecast skill for the seasonal Australian region TCG by as much as 10% in terms of correlation increase and 40% in terms of root-mean-square error reduction.

The algorithms based on Surface Quasi-Geostrophic (SQG) dynamics have been developed and validated by many researchers through model products, however it is still doubtful whether these SQG-based algorithms are worth using in terms of observed data. This paper analyzes the factors impeding the practical application of SQG and makes amends by a simple “first-guess (FG) framework”. The proposed framework includes the correction of satellite salinity and the estimation of the FG background, making the SQG-based algorithms applicable in realistic circumstances. The dynamical-statistical method SQG-mEOF-R is thereafter applied to satellite data for the first time. The results are compared with two dynamical algorithms, SQG and isQG, and three empirical algorithms, multivariate linear regression (MLR), random forest (RF), and mEOF-R. The validation against Argo profiles showed that the SQG-mEOF-R presents a robust performance in mesoscale reconstruction and outperforms the other five algorithms in the upper layers. It is promising that the SQG-mEOF-R and the FG framework are applicable to operational reconstruction.

Principal component analysis (PCA) and its variations are still the primary tool for feature extraction (FE) in remote sensing community. This is unfortunate, as there has been strong argument against using PCA for this purpose due to its inherent linear properties and uninformative principal components. Therefore, several critical issues still should be considered in hyperspectral image classification when using PCA, among which: 1) the large number of spectral channels and small number of training samples; 2) the nonlinearities of hyperspectral data; 3) the small-sample issue. In order to alleviate these problems, this paper employs a new information-theoretic FE method so-called kernel entropic component analysis (KECA), which can not only extract more nonlinear information, but also be adapt to limited-sample environment. A theorem of the pivoted Cholesky decomposition is also introduced to improve the efficiency of the KECA. The optimized version can more rapidly implement spectral-spatial features extraction, particularly for large-scale HSIs, while effectively maintaining the clustering performances of KECA. Experiments implemented on several real HSIs verify the effectiveness of the new method armed with a support vector machine (SVM) classifier, in comparison with other PCA-based and state-of-the-art HSI classification algorithms. The code will be also made publicly available.