Due to ecological environmental fragility and soil erosion in Guangxi, studies of landscape patterns and associated ecological risks are needed to guide sustainable land development and ecologically sensitive land management. This study assesses dynamic spatial and temporal change patterns in land use and ecological risks based on 30 m land-use data, analyzes spatial correlations with ecological risks, and explores natural and socio-economic factor impacts on ecological risks. The results reveal: (1) A rapid and sizeable construction land increase in Guangxi from 2000 to 2018 associated mainly with loss of woodland and grassland. (2) Guangxi had the highest number of arable land patches from 2000 to 2018, and the distribution tended to be fragmented; moreover, the construction land gradually expanded outward from concentrated areas to form larger aggregates with increasing internal stability each year. (3) Guangxi ecological risk levels were low, low–medium, and medium, with significantly different spatial distributions observed for areas possessing different ecological risk levels. Regional ecological risk gradually decreased from the middle Guangxi regions to the surrounding areas and was positively correlated with spatial distribution. (4) Socio-economic factor impacts on ecological risk exceeded natural factor impacts. These results provide guidance toward achieving ecologically sensitive regional land-use management and ecological risk reduction and control, it can also provide a reference for ecological risk research in other similar regions in the world.

Landsat 9 enhances the radiation resolution of the operational land imager from the 12 bits of Landsat 8 to 14 bits. The higher radiation resolution improves the sensitivity of the sensor to detect many subtler differences, especially in the case of dense forests or water. However, it remains unclear whether the difference in radiation resolution between Landsat 8 and Landsat 9 actually affects the classification results of water and tree species. Accordingly, the spectral reflectance and vegetation indices were extracted in this study, based on Landsat 8 and Landsat 9 images. Then, the classification models of land use and land cover (LULC) and tree species were developed by using a gradient tree boosting algorithm. Subsequently, the results were analyzed to further investigate how the differences in radiation resolution affect the classification results of LULC and tree species. It is shown that the LULC classification results of Landsat 8 and Landsat 9 are relatively favorable in most cases. However, the LULC classification results are relatively poor in test areas with a lower classification accuracy of water. Further analysis, in the case of test areas with poor classification results, indicates that there are significant differences in the water classification results between the two datasets. In other words, Landsat 9 produces better water classification results than Landsat 8 in most test areas. However, a temperature close to zero may lead to inverse water classification results. In addition, it indicates that the difference in forest classification results between the two datasets is small, but the results of forest tree species classification based on Landsat 9 are superior to those based on Landsat 8, with an improvement in overall accuracy of 6.01%. The results demonstrate that the difference in radiation resolution between Landsat 8 and Landsat 9 has little impact on the results of LULC classification in most cases. Nevertheless, in the case of some test areas, Landsat 9 is better suited for enhancing the classification accuracy of water and tree species.

Image segmentation is an important task in image processing and analysis but due to the same ground object having different spectra and different ground objects having similar spectra, segmentation, particularly on high-resolution remote sensing images, can be significantly challenging. Since the spectral distribution of high-resolution remote sensing images can have complex characteristics (e.g., asymmetric or heavy-tailed), an innovative image segmentation algorithm is proposed based on the hierarchical Student’s-t mixture model (HSMM) and spatial constraints with adaptive smoothing. Considering the complex distribution of spectral intensities, the proposed algorithm constructs the HSMM to accurately build the statistical model of the image, making more reasonable use of the spectral information and improving segmentation accuracy. The component weight is defined by the attribute probability of neighborhood pixels to overcome the influence of image noise and make a simple and easy-to-implement structure. To avoid the effects of artificially setting the smoothing coefficient, the gradient optimization method is used to solve the model parameters, and the smoothing coefficient is optimized through iterations. The experimental results suggest that the proposed HSMM can accurately model asymmetric, heavy-tailed, and bimodal distributions. Compared with traditional segmentation algorithms, the proposed algorithm can effectively overcome noise and generate more accurate segmentation results for high-resolution remote sensing images.

To extract more structural features, which can contribute to segment a synthetic aperture radar (SAR) image accurately, and explore their roles in the segmentation procedure, this paper presents an energy-based SAR image segmentation method with weighted features. To precisely segment a SAR image, multiple structural features are incorporated into a block- and energy-based segmentation model in weighted way. In this paper, the multiple features of a pixel, involving spectral feature obtained from original SAR image, texture and boundary features extracted by a curvelet transform, form a feature vector. All the pixels’ feature vectors form a feature set of a SAR image. To automatically determine the roles of the multiple features in the segmentation procedure, weight variables are assigned to them. All the weight variables form a weight set. Then the image domain is partitioned into a set of blocks by regular tessellation. Afterwards, an energy function and a non-constrained Gibbs probability distribution are used to combine the feature and weight sets to build a block-based energy segmentation model with feature weighted on the partitioned image domain. Further, a reversible jump Markov Chain Monte Carlo (RJMCMC) algorithm is designed to simulate from the segmentation model. In the RJMCMC algorithm, three move types were designed according to the segmentation model. Finally, the proposed method was tested on the SAR images, and the quantitative and qualitative results demonstrated its effectiveness.

To address the problems of low accuracy and the extracted coastlines with breakpoints in most existing coastline extraction methods, this paper proposes a regionalized coastline extraction method that combines Simple Linear Iteration Clustering (SLIC), Bayes’ theorem, and Metropolis-Hastings (M-H) algorithm for high-resolution images. First, the SLIC algorithm is utilized to segment the superpixels. Associated with each superpixel, there is a random label, and the label belongs to the land or the ocean. Then, the Bayes’ theorem and the M-H algorithm are combined to define the superpixel labeling optimization function. The optimal results of the function are obtained to achieve coastline extraction after numerous iterations. Finally, the proposed and four compared methods are tested. From the qualitative results, it can be seen that the proposed method only extracts the coastlines, and the extracted coastlines have no breakpoints; the Canny operator method not only extracts the coastlines with breakpoints, but also extracts the boundaries of many land targets; the other three compared methods can also extract the boundaries of some land targets except for extracting complete coastlines. For the proposed method, its average Recall, Overall Accuracy, and Kappa coefficient are 99.45%, 99.43%, and 0.9882, respectively; For the object-oriented method, these metrics are 71.24%, 84.29%, and 0.7157; The metrics of the BP neural network method are 91.29%, 93.04%, and 0.8707. For the CNN method, these metrics are 90.73%, 90.60%, and 0.9023, respectively. Further, it can be verified that the proposed method can not only extract complete coastlines but also has higher accuracy.