Accurate monitoring of bare soil land (BSL) is an urgent need for environmental governance and optimal utilization of land resources. High-resolution imagery contains rich semantic information, which is beneficial for the recognition of objects on the ground. Simultaneously, it is susceptible to the impact of its background. We propose a semantic segmentation model, Deeplabv3+-M-CBAM, for extracting BSL. First, we replaced the Xception of Deeplabv3+ with MobileNetV2 as the backbone network to reduce the number of parameters. Second, to distinguish BSL from the background, we employed the convolutional block attention module (CBAM) via a combination of channel attention and spatial attention. For model training, we built a BSL dataset based on BJ-2 satellite images. The test result for the F1 of the model was 88.42%. Compared with Deeplabv3+, the classification accuracy improved by 8.52%, and the segmentation speed was 2.34 times faster. In addition, compared with the visual interpretation, the extraction speed improved by 11.5 times. In order to verify the transferable performance of the model, Jilin-1GXA images were used for the transfer test, and the extraction accuracies for F1, IoU, recall and precision were 86.07%, 87.88%, 87.00% and 95.80%, respectively. All of these experiments show that Deeplabv3+-M-CBAM achieved efficient and accurate extraction results and a well transferable performance for BSL. The methodology proposed in this study exhibits its application value for the refinement of environmental governance and the surveillance of land use.

As dust source bare soil land (BSL) contributes to air pollution and affects the photosynthesis of green plants and carbon absorption, it is the objective of this study to develop an approach for monitoring the changes of BSL using remote sensing technology. Unlike other land use/cover types, the classification of BSL as well as its change detection is often ignored. For traditional convolutional neural networks, deep layers cause a long range between input and output, inevitably leading to the loss of information and computational costs. To alleviate this problem, transformer is available to model the global dependencies. Bitemporal association, which is described as subtraction or attention mechanism, is not fully considered by current methods. Therefore, we proposed a spatial-temporal association enhanced mobile-friendly vision transformer (STAE-MobileVIT) for change detection of high-resolution images with light weight and high efficiency. On the one hand, a temporal association enhanced MobileVIT block is employed to strengthen the association of bitemporal images during feature extraction. On the other hand, a multiscale feature difference aggregator enhanced by spatial association is designed to fuse semantic and detailed information. Since the lack of binary change detection dataset for BSL, we established a small dataset named BSL-CD, consisting of 1083 pairs of 0.8 m bitemporal images with the size of 256 × 256 pixels, along with the corresponding labels. The experiments on BSL-CD show that our light-weight model surpass seven common methods by 3.48, 5.05, and 1.44 percent on F1, IoU, and OA, which proves the efficiency and accuracy of STAE-MobileVIT.

Soil fugitive dust (SFD) is a significant contributor to environmental particulate matter (PM), which not only pollutes and affects air quality but also poses risks to human health. The emission inventory can provide a basis for the effective prevention and control of SFD pollution. However, current emission inventories with low resolution and frequency make it difficult to assess dust emissions accurately. Obtaining monthly high-resolution bare soil information is one of the solutions for compiling SFD emission inventories. Taking Daxing District, Beijing, as a case study, this study first extracted bare soil for each month of 2020, 2021, and 2022, respectively, using high-spatial-resolution remote sensing satellite data, and then constructed a 10 m-size emission grid and monthly SFD emission inventories based on the wind erosion equation by inputting vegetation cover factor, meteorological data, and soil erosion index. The total emissions of TSP, PM₁₀, and PM_2.5 in Daxing District from 2020 to 2022 were 3996.54 tons, 359.26 tons, and 25.25 tons, respectively. Temporally, the SFD emissions showed a decreasing trend over the years and were mainly concentrated in the winter and spring seasons. Spatially, the SFD emissions were predominantly concentrated in the southern and northern areas. And the emissions of PM₁₀ exhibit a significantly stronger correlation with wind speed and the extent of bare soil area.