Iterative Training Sample Augmentation for Enhancing Land Cover Change Detection Performance With Deep Learning Neural Network.

Labeled samples are important in achieving land cover change detection (LCCD) tasks via deep learning techniques with remote sensing images. However, labeling samples for change detection with bitemporal remote sensing images is labor-intensive and time-consuming. Moreover, manually labeling samples between bitemporal images requires professional knowledge for practitioners. To address this problem in this article, an iterative training sample augmentation (ITSA) strategy to couple with a deep learning neural network for improving LCCD performance is proposed here. In the proposed ITSA, we start by measuring the similarity between an initial sample and its four-quarter-overlapped neighboring blocks. If the similarity satisfies a predefined constraint, then a neighboring block will be selected as the potential sample. Next, a neural network is trained with renewed samples and used to predict an intermediate result. Finally, these operations are fused into an iterative algorithm to achieve the training and prediction of a neural network. The performance of the proposed ITSA strategy is verified with some widely used change detection deep learning networks using seven pairs of real remote sensing images. The excellent visual performance and quantitative comparisons from the experiments clearly indicate that detection accuracies of LCCD can be effectively improved when a deep learning network is coupled with the proposed ITSA. For example, compared with some state-of-the-art methods, the quantitative improvement is 0.38%-7.53% in terms of overall accuracy. Moreover, the improvement is robust, generic to both homogeneous and heterogeneous images, and universally adaptive to various neural networks of LCCD. The code will be available at https://github.com/ImgSciGroup/ITSA.

The Effect of Socioeconomic Factors on Spatiotemporal Patterns of PM2.5 Concentration in Beijing-Tianjin-Hebei Region and Surrounding Areas.

The study investigated the spatiotemporal evolution of PM2.5 concentration in the Beijing-Tianjin-Hebei region and surrounding areas during 2015-2017, and then analyzed its socioeconomic determinants. First, an estimation model considering spatiotemporal heterogeneous relationships was developed to accurately estimate the spatial distribution of PM2.5 concentration. Additionally, socioeconomic determinants of PM2.5 concentration were analyzed using a spatial panel Dubin model, which aimed to improve the robustness of the model estimation. The results demonstrated that: (1) The proposed model significantly increased the estimation accuracy of PM2.5 concentration. The mean absolute error and root-mean-square error were 9.21 µg/m3 and 13.10 µg/m3, respectively. (2) PM2.5 concentration in the study area exhibited significant spatiotemporal changes. Although the PM2.5 concentration has declined year by year, it still exceeded national environmental air quality standards. (3) The per capita GDP, urbanization rate and number of industrial enterprises above the designated size were the key factors affecting the spatiotemporal distribution of PM2.5 concentration. This study provided scientific references for comprehensive PM2.5 pollution control in the study area.