Xinrong Lyu

GNSS-R technology provides a novel solution for sea ice dynamic monitoring through its all-weather observation capability and low-cost advantages. However, existing methods still face significant challenges in simultaneously achieving high-accuracy detection of ice-water boundaries and precise identification of large-area sea ice distant from transition zones. To address this issue, this paper proposes a novel sea ice detection model incorporating the semi-correlated supervision algorithm of dual neural networks. First, a dual-modal dataset comprising DDM and Differential DDM data is employed to capture the global scattering characteristics of sea ice and local differential features of transition regions, respectively. Second, an innovative dual-branch detection architecture is designed: the Differential DDM detection branch based on YOLOv11 achieves high-sensitivity identification of ice-water boundaries through local feature extraction, while the Efficient Vision Mamba detection branch enhances detection robustness for open water and continuous ice cover via global feature analysis. To further optimize model performance, a semi-correlated supervision correction algorithm is proposed, which dynamically integrates dual-branch detection results through temporal context analysis and bidirectional validation mechanisms, effectively resolving the performance imbalance between transition zones and stable regions in traditional single-model approaches. Experiments using J1-01B and TDS-1 satellites GNSS-R data demonstrate that the model achieves 94.1% accuracy for ice-water boundary detection, 97.3% accuracy for sea ice detection distant from transition zones, with an overall accuracy of 95.7%. This research establishes a high-accuracy, full-coverage technical framework for real-time polar sea ice monitoring, offering significant application value for global climate change studies and polar navigation safety.

Oil remains the most important energy source in the world today, and tankers are its main modes of transportation. However, there is a high risk of oil spills, which can cause serious damage to the ecological environment. Remote sensing monitoring is one of the most common processes of emergency management for oil spills. Short interval and uninterrupted remote sensing sequence data is crucial for monitoring and tracing oil spill events. However, the long revisit period of satellites poses a challenge of data scarcity for oil spill monitoring. To address the issue of insufficient remote sensing image data in oil spill monitoring and prediction, we propose a joint modeling approach that combines deep learning and numerical models to enhance the monitoring efficiency. Firstly, a DiffusionLSTM network is proposed based on the diffusion model’s ability to generate images and the capability of Long Short-Term Memory (LSTM) network to extract temporal information. The proposed network can learn the evolution pattern of images from historical remote sensing data and predict future scenarios. Comparative experiments on the MODSD dataset show that our proposed model achieved a significant improvement compared to traditional time-series image prediction models (ConvLSTM, GAN-LSTM). Secondly, a trajectory model based on numerical simulation methods is established using OpenOil. Taking into account the differences in different marine areas, we accurately reconstruct oil spill trajectories by calibrating the wind drift coefficients. For Sanchi oil spill incident, the error is reduced approximately to 2500 m. Finally, through fusing the images generated by DiffusionLSTM and the oil spill trajectories predicted by OpenOil, short time interval oil spill scene images have been generated efficiently to improve the monitoring efficiency.

We investigate the problem of oil spill timely backtracking. Most existing methods for backtracking oil spills rely heavily on historical wind fields. However, during the crucial early stages of an oil spill accident, only inaccurate forecasted or observed wind fields are available as historical data, which do not guarantee reliable accuracy for backtracking the oil spills. On the other hand, reanalysis wind fields are more accurate data for the historical wind fields. However, they normally have a latency of many days and can hardly be used for backtracking the oil spills in a timely manner. To obtain a timely and accurate estimate of the historical wind fields, we develop a self-attention temporal convolutional network (SaTCN). The SaTCN consists of a self-attention network and a temporal convolutional network. The self-attention network captures spatial correlations from a historical wind field sequence in a global manner. The temporal convolutional network captures spatial correlations and temporal characteristics from an attention-weighted wind field sequence in a local manner. The SaTCN is trained subject to the differences between the timely but inaccurate data of both forecasted and observed wind fields and the accurate but delayed data of reanalysis wind fields. The well-trained SaTCN can correct the timely historical wind fields into more accurate ones by approximating the reanalysis wind fields. The corrected historical wind fields thus obtained enable timely, accurate oil spill backtracking. Extensive experiments validate the effectiveness of the proposed backtracking method in addressing the Sanchi and Symphony oil spill accidents.

Machine learning-based methods provide attractive solutions to algal bloom detection. However, the effective utilization of training sets remains a crucial challenge. Taking the extraction of Ulva prolifera (U.Prolifera) as an example, to improve the detection accuracy, this manuscript presents a model based on self-sampling and semi-correlated co-training. The self-sampling module comprises balanced sampling and gradient descent to enhance the efficiency of extracting useful information from U.prolifera training sets. Balanced sampling optimizes the distribution of sampling points, while gradient descent determines the optimal number of sampling points. During the iteration process, useful information will be continuously extracted driven by the self-sampling module as the input of training for the subsequent machine learning algorithm. The classical semi-supervised machine learning approach named co-training is a very effective semi-supervised approach, but it requires two views to be sufficient and independent, a condition that is difficult to meet in practical applications. To address this issue, we developed a semi-correlated co-training module to achieve the two-view condition. To mitigate the problem of limited labeled samples, both labeled and unlabeled samples are used as inputs for the semi-correlated co-training module. Benefiting from the self-sampling module and the semi-correlated co-training module, the experimental results based on different U.prolifera datasets from MODIS and Sentinel-1 Synthetic Aperture Radar (SAR) show that the proposed model in the manuscript has made a contribution to the improvement of the detection accuracy of U.prolifera.

In this paper, sea ice classification on a remote sensing image given just a small number of labeled pixels is investigated. Effective sea ice classification is rendered from two aspects. First, a feature extraction method is developed. It extracts the context feature from a classification map. Second, an iterative learning paradigm is established. The labeled pixels are divided into two training subsets. At each iteration, the context feature for one subset is extracted from the classification map which is obtained subject to the other subset. Therefore, the two subsets mutually guide each other for updating the context feature in an iterative manner, which finally renders effective sea ice classification. The above paradigm is referred to as mutually guided contexts. The advantages of the new paradigm are two-fold. First, the context feature enriches the sea ice image representation in a general manner regardless of the types of raw image data. Second, the two training subsets keep providing different refined classification maps for each other such that the comprehensiveness of the context feature is recursively enhanced. Therefore, the paradigm of mutually guided contexts comprehensively characterizes the sea ice image representation for training and classification even when only small training data are available. Experiments validate the effectiveness of the mutually guided contexts for sea ice classification.

We present a new learning paradigm, that is, cross-supervised learning, and explore its use for cloud detection. The cross-supervised learning paradigm is characterized by both supervised training and mutually supervised training, and is performed by two base networks. In addition to the individual supervised training for labeled data, the two base networks perform the mutually supervised training using prediction results provided by each other for unlabeled data. Specifically, we develop In-extensive Nets for implementing the base networks. The In-extensive Nets consist of two Intensive Nets and are trained using the cross-supervised learning paradigm. The Intensive Net leverages information from the labeled cloudy images using a focal attention guidance module (FAGM) and a regression block. The cross-supervised learning paradigm empowers the In-extensive Nets to learn from both labeled and unlabeled cloudy images, substantially reducing the number of labeled cloudy images (that tend to cost expensive manual effort) required for training. Experimental results verify that In-extensive Nets perform well and have an obvious advantage in the situations where there are only a few labeled cloudy images available for training. The implementation code for the proposed paradigm is available at https://gitee.com/kang_wu/in-extensive-nets.