Detection of marine oil spills from radar satellite images for the coastal ecological risk assessment.

Coastal ecosystems offer substantial support and space for the sustainable development of human society, and hence the ecological risk evaluation of coastal ecosystems is of great significance. In this article, we propose an innovative framework for evaluating coastal ecological risk by considering oil spill risk information and environmental vulnerability information. Specifically, a deep learning based marine oil spill monitoring method is presented to obtain the oil spill risk information from Sentinel-1 polarimetric synthetic aperture radar (PolSAR) images. The environmental vulnerability information is then obtained from biological sample data and habitat information. Finally, a weighted probability model is introduced to utilize the oil spill risk and environmental vulnerability information, to evaluate the coastal ecological risk. In the experimental part, the proposed oil spill monitoring method shows its reliability in global ocean areas, and the proposed model is adopted to evaluate the ecological risk in Jiaozhou Bay, China. The results show that the ecological situation of more than half of the areas in Jiaozhou Bay is unstable, and the areas with high risk are mainly concentrated in the ports, shipping channels, and those areas with high biodiversity. This study provides some new perspectives on ecological risk assessment for coastal ecosystems, facilitating the planning process and the actions to be taken in response to the accidents that occur in the ocean, especially oil spill accidents.

Multiple Classifiers Based Semi-Supervised Polarimetric SAR Image Classification Method.

Polarimetric synthetic aperture radar (PolSAR) image classification has played an important role in PolSAR data application. Deep learning has achieved great success in PolSAR image classification over the past years. However, when the labeled training dataset is insufficient, the classification results are usually unsatisfactory. Furthermore, the deep learning approach is based on hierarchical features, which is an approach that cannot take full advantage of the scattering characteristics in PolSAR data. Hence, it is worthwhile to make full use of scattering characteristics to obtain a high classification accuracy based on limited labeled samples. In this paper, we propose a novel semi-supervised classification method for PolSAR images, which combines the deep learning technique with the traditional scattering trait-based classifiers. Firstly, based on only a small number of training samples, the classification results of the Wishart classifier, support vector machine (SVM) classifier, and a complex-valued convolutional neural network (CV-CNN) are used to conduct majority voting, thus generating a strong dataset and a weak dataset. The strong training set are then used as pseudo-labels to reclassify the weak dataset by CV-CNN. The final classification results are obtained by combining the strong training set and the reclassification results. Experiments on two real PolSAR images on agricultural and forest areas indicate that, in most cases, significant improvements can be achieved with the proposed method, compared to the base classifiers, and the improvement is approximately 3-5%. When the number of labeled samples was small, the superiority of the proposed method is even more apparent. The improvement for built-up areas or infrastructure objects is not as significant as forests.

Multitemporal SAR Image Despeckling Based on a Scattering Covariance Matrix of Image Patch.

This paper presents a despeckling method for multitemporal images acquired by synthetic aperture radar (SAR) sensors. The proposed method uses a scattering covariance matrix of each image patch as the basic processing unit, which can exploit both the amplitude information of each pixel and the phase difference between any two pixels in a patch. The proposed filtering framework consists of four main steps: (1) a prefiltering result of each image is obtained by a nonlocal weighted average using only the information of the corresponding time phase; (2) an adaptively temporal linear filter is employed to further suppress the speckle; (3) the final output of each patch is obtained by a guided filter using both the original speckled data and the filtering result of step 3; and (4) an aggregation step is used to tackle the multiple estimations problem for each pixel. The despeckling experiments conducted on both simulated and real multitemporal SAR datasets reveal the pleasing performance of the proposed method in both suppressing speckle and retaining details, when compared with both advanced single-temporal and multitemporal SAR despeckling techniques.

Land Use Classification of the Deep Convolutional Neural Network Method Reducing the Loss of Spatial Features.

Land use classification is a fundamental task of information extraction from remote sensing imagery. Semantic segmentation based on deep convolutional neural networks (DCNNs) has shown outstanding performance in this task. However, these methods are still affected by the loss of spatial features. In this study, we proposed a new network, called the dense-coordconv network (DCCN), to reduce the loss of spatial features and strengthen object boundaries. In this network, the coordconv module is introduced into the improved DenseNet architecture to improve spatial information by putting coordinate information into feature maps. The proposed DCCN achieved an obvious performance in terms of the public ISPRS (International Society for Photogrammetry and Remote Sensing) 2D semantic labeling benchmark dataset. Compared with the results of other deep convolutional neural networks (U-net, SegNet, Deeplab-V3), the results of the DCCN method improved a lot and the OA (overall accuracy) and mean F1 score reached 89.48% and 86.89%, respectively. This indicates that the DCCN method can effectively reduce the loss of spatial features and improve the accuracy of semantic segmentation in high resolution remote sensing imagery.

Detection and prediction of land use/land cover change using spatiotemporal data fusion and the Cellular Automata-Markov model.

The detection and prediction of land use/land cover (LULC) change is crucial for guiding land resource management, planning, and sustainable development. In the view of seasonal rhythm and phenological effect, detection and prediction would benefit greatly from LULC maps of the same seasons for different years. However, due to frequent cloudiness contamination, it is difficult to obtain same-season LULC maps when using existing remote sensing images. This study utilized the spatiotemporal data fusion (STF) method to obtain summer Landsat-scale images in Hefei over the past 30 years. The Cellular Automata-Markov model was applied to simulate and predict future LULC maps. The results demonstrate the following: (1) the STF method can generate the same inter-annual interval summer Landsat-scale data for analyzing LULC change; (2) the fused data can improve the LULC detection and prediction accuracy by shortening the inter-annual interval, and also obtain LULC prediction results for a specific year; (3) the areas of cultivated land, water, and vegetation decreased by 33.14%, 2.03%, and 16.36%, respectively, and the area of construction land increased by 200.46% from 1987 to 2032. The urban expansion rate will reach its peak until 2020, and then slow down. The findings provide valuable information for urban planners to achieve sustainable development goals.