Search

The outbreaks of green tide have caused severe harm to the marine environment and human society. Synthetic Aperture Radar (SAR) plays an important role in green tide monitoring by virtue of its high resolution and cloud-free nature. The existing green tide extraction methods still face challenges in identifying multi-scale green tide patches due to noise interference, uneven greyscale and blurred boundaries in SAR images. Meanwhile, the practical application of deep learning methods with high precision is limited due to the complexity of the model and the large amount of computation. Therefore, we propose a multi-scale context-aware and batch-independent lightweight green tide extraction network called MBL-Net. A novel lightweight heterogeneous backbone is designed to extract multi-scale discriminative features and improve segmentation efficiency by using multi-scale selection kernel (MSK) modules and lightweight stages. Meanwhile, Triplet attention module is introduced to improve the internal consistency of the green tide region and suppress the effect of speckle noise. Then, the mixed pooling-based channel prior module (MCPM) is used to expand the receptive field of the network and extract the fine green tide structure by fusing multi-scale features. In addition, Filter Response Normalisation (FRN) is innovatively applied for feature normalization in the decoding stage, eliminating batch dependency. In order to verify the effectiveness of the proposed method, a dataset is built using the Sentinel-1 images of the Yellow Sea, China, from 2019 to 2021. The experimental results show that the proposed method achieves an overall accuracy of 98.59% with 0.970 G FLOPs and 3.525 M parameters, which ensures high precision and improves green tide detection efficiency. Compared with several representative networks, this method can capture more details of green tide with fewer parameters and faster calculation speed. [ABSTRACT FROM AUTHOR]

Timely and accurate acquisition of winter wheat planting areas is crucial for food security. In this study, Sentinel-1 and Sentinel-2 time-series data are integrated at the feature level to enhance the accuracy of winter wheat extraction. However, existing feature-level fusion models suffer from insufficient feature extraction and lack of feature completeness, thereby overlooking the complementarity and correlation between these two modalities. A Multimodal Fusion Convolutional Neural Network (MMF-CNN) model is proposed to address the issues above. Firstly, the images of Sentinel-1 and Sentinel-2 are processed to obtain the NDVI and backscatter characteristics of the winter wheat time series life cycle. A single feature and a combination of two features are then imported into each end of the model. The model adds a feature fusion module, which can fully extract the feature information. At the same time, the original features are retained in the process of multiscale feature fusion, which avoids the loss of the original information. Finally, Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Visual Geometry Group (VGG) are selected as the comparison models for comparative experiments, and the classification results of remote sensing images are obtained. These results demonstrate that the joint utilization of SAR and optical data yields the highest classification accuracy, with an F1 score of 97.42% for winter wheat. The overall accuracy (OA) of the proposed MMF-CNN method in this study is 96.87%, representing a 1.86% improvement compared to the Conv1D-CNN model. This improvement signifies adaptive feature learning at different hierarchical levels. Comparing the accuracy with other mainstream methods, the OA improves by 1.75%–4.37%, reveals finer ground details, and demonstrates faster performance. This study can provide methodological references for crop extraction studies based on multi-source data and time series analysis. [ABSTRACT FROM AUTHOR]

In the hyperspectral image (HSI) classification tasks, various deep learning models have achieved remarkable success. However, most deep learning models are compute-intensive, requiring significant computing power, time, and other resources. It becomes a challenge to pursue better results while saving computational resources. Therefore, a novel dual-input ultralight multi-head self-attention learning network (DUMS-LN) is proposed for HSI classification. The proposed DUMS-LN consists of three main core modules, namely the high-dimensional reduced module (HDRM), lightweight multi-head self-attention (LMHSA) module, and linearized hierarchical conversion module (LHCM). HDRM is used as a pre-processing module with efficient data compression and combines spatial and spectral information extraction from the raw data to provide cleaner and more comprehensive feature data for subsequent processing. In addition, the core computational module of DUMS-LN is the LMHSA module, which is lightweight but possesses better data processing capability than the traditional multi-head self-attention module. Finally, the LHCM divides the model into two phases, reducing the dimensionality of the feature data phase by phase so that the LMHSA module can perform feature extraction at different levels. Experiments on four benchmark HSI datasets show that the proposed DUMS-LN outperforms the comparison HSI classification algorithms regarding speed and classification accuracy. [ABSTRACT FROM AUTHOR]

Oil spills on the sea surface have caused serious harm to the marine ecological environment and coastal environment. Oil film thickness (OFT) is an important parameter for estimating oil spills amount, and accurate quantification of OFT is of great significance for rapid response and risk assessment of oil spills. In recent years, thermal infrared remote sensing has been gradually applied to quantify the OFT. In this paper, the outdoor oil spill simulation experiments were designed, and the bright temperature (BT) data of different OFTs were obtained for 24 consecutive hours in summer and autumn. On the basis of the correlation analysis of OFT and bright temperature difference (BTD) between oil and water, the traditional regression fitting model, classical machine learning model, ensemble learning model, and deep learning model were applied to the inversion of OFT. At the same time, inversion results of the four models were compared and analyzed. In addition, the best OFT inversion time using thermal infrared was studied based on 24-h thermal infrared data. Additionally, the inversion results were compared with the measured results; the optimal OFT range detectable using thermal infrared was explored. The experimental results show that: (1) Compared with ensemble learning model, traditional regression fitting model, and classical machine learning model, Convolutional Neural Network (CNN) has the advantages of high stability while maintaining high-precision inversion, and can be used as the preferred model for oil film thickness inversion; (2) The optimal time for OFT detection is around 10:00 to 13:00 of the day, and is not affected by seasonal changes; (3) During the day, thermal infrared has good detection ability for OFT greater than 0.4 mm, and weak detection ability for thinner oil films; (4) At night, thermal infrared has certain detection ability for relatively thick oil film, but the accuracy is lower than that in the daytime. [ABSTRACT FROM AUTHOR]

Marine oil spills can cause serious damage to marine ecosystems and biological species, and the pollution is difficult to repair in the short term. Accurate oil type identification and oil thickness quantification are of great significance for marine oil spill emergency response and damage assessment. In recent years, hyperspectral remote sensing technology has become an effective means to monitor marine oil spills. The spectral and spatial features of oil spill images at different levels are different. To accurately identify oil spill types and quantify oil film thickness, and perform better extraction of spectral and spatial features, a multilevel spatial and spectral feature extraction network is proposed in this study. First, the graph convolutional neural network and graph attentional neural network models were used to extract spectral and spatial features in non-Euclidean space, respectively, and then the designed modules based on 2D expansion convolution, depth convolution, and point convolution were applied to extract feature information in Euclidean space; after that, a multilevel feature fusion method was developed to fuse the obtained spatial and spectral features in Euclidean space in a complementary way to obtain multilevel features. Finally, the multilevel features were fused at the feature level to obtain the oil spill information. The experimental results show that compared with CGCNN, SSRN, and A2S2KResNet algorithms, the accuracy of oil type identification and oil film thickness classification of the proposed method in this paper is improved by 12.82%, 0.06%, and 0.08% and 2.23%, 0.69%, and 0.47%, respectively, which proves that the method in this paper can effectively extract oil spill information and identify different oil spill types and different oil film thicknesses. [ABSTRACT FROM AUTHOR]

The Sargassum bloom has severely impacted the ecological environment of the East China Sea and the Yellow Sea, causing significant economic losses. In recent years, deep learning has seen extensive development due to its outstanding feature extraction capabilities. However, the deep learning process typically involves a large number of parameters and computations. To address this issue, this paper proposes a lightweight deep learning network based on the U-Net framework, called SLWE-NET, which uses lightweight modules to replace the feature extraction modules in U-Net. In this experiment, SLWE-Net performed the best in both extraction accuracy and model lightweight. Compared to the formal U-Net, the number of parameters decreased by 65.83 %, the model size reduced from 94.97 MB to 32.51 MB, and the mIoU increased to 93.81 %. Therefore, the method proposed in this paper is beneficial for Sargassum extraction and provides a basis for operational monitoring. • The SLWE-Net model is an effective model for Sargassum detection through satellite images. • Using VoVNet as the feature extraction module of the model can better extract the target and achieve higher accuracy. • In terms of Sargassum extraction accuracy, SLWE-Net outperforms traditional spectral vegetation indices. • SLWE-Net has achieved notable advancements in model lightweight by decreasing parameter count and computation complexity. [ABSTRACT FROM AUTHOR]

Oil spill pollution at sea causes significant damage to marine ecosystems. Quad-polarimetric Synthetic Aperture Radar (SAR) has become an essential technology since it can provide polarization features for marine oil spill detection. Using deep learning models based on polarimetric features, oil spill detection can be achieved. However, there is insufficient feature extraction due to model depth, small reception field lend due to loss of target information, and fixed hyperparameter for models. The effect of oil spill detection is still incomplete or misclassified. To solve the above problems, we propose an improved deep learning model named BO-DRNet. The model can obtain a more sufficiently and fuller feature by ResNet-18 as the backbone in encoder of DeepLabv3+, and Bayesian Optimization (BO) was used to optimize the model's hyperparameters. Experiments were conducted based on ten prominent polarimetric features were extracted from three quad-polarimetric SAR images obtained by RADARSAT-2. Experimental results show that compared with other deep learning models, BO-DRNet performs best with a mean accuracy of 74.69% and a mean dice of 0.8551. This paper provides a valuable tool to manage upcoming disasters effectively. [ABSTRACT FROM AUTHOR]

Sea fog is a precarious weather disaster affecting transportation on the sea. The accuracy of the threshold method for sea fog detection is limited by time and region. In comparison, the deep learning method learns features of objects through different network layers and can therefore accurately extract fog data and is less affected by temporal and spatial factors. This study proposes a scSE-LinkNet model for daytime sea fog detection that leverages residual blocks to encoder feature maps and attention module to learn the features of sea fog data by considering spectral and spatial information of nodes. With the help of satellite radar data from Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), a ground sample database was extracted from Moderate Resolution Imaging Spectroradiometer (MODIS) L1B data. The scSE-LinkNet was trained on the training set, and quantitative evaluation was performed on the test set. Results showed the probability of detection (POD), false alarm rate (FAR), critical success index (CSI), and Heidke skill scores (HSS) were 0.924, 0.143, 0.800, and 0.864, respectively. Compared with other neural networks (FCN, U-Net, and LinkNet), the CSI of scSE-LinkNet was improved, with a maximum increase of nearly 8%. Moreover, the sea fog detection results were consistent with the measured data and CALIOP products. [ABSTRACT FROM AUTHOR]