Regional haze episodes have occurred frequently in eastern China over the past decades. As a critical indicator to evaluate air quality, the mass concentration of ambient fine particulate matters smaller than 2.5 μm in aerodynamic diameter (PM_2.5) is involved in many studies. To overcome the limitations of ground measurements on PM_2.5 concentration, which is featured in disperse representation and coarse coverage, many statistical models were developed to depict the relationship between ground-level PM_2.5 and satellite-derived aerosol optical depth (AOD). However, the current satellite-derived AOD products and statistical models on PM_2.5–AOD are insufficient to investigate PM_2.5 characteristics at the urban scale, in that spatial resolution is crucial to identify the relationship between PM_2.5 and anthropogenic activities. This paper presents a geographically and temporally weighted regression (GTWR) model to generate ground-level PM_2.5 concentrations from satellite-derived 500 m AOD. The GTWR model incorporates the SARA (simplified high resolution MODIS aerosol retrieval algorithm) AOD product with meteorological variables, including planetary boundary layer height (PBLH), relative humidity (RH), wind speed (WS), and temperature (TEMP) extracted from WRF (weather research and forecasting) assimilation to depict the spatio-temporal dynamics in the PM_2.5–AOD relationship. The estimated ground-level PM_2.5 concentration has 500 m resolution at the MODIS satellite’s overpass moments twice a day, which can be used for air quality monitoring and haze tracking at the urban and regional scale. To test the performance of the GTWR model, a case study was carried out in a region covering the adjacent parts of Jiangsu, Shandong, Henan, and Anhui provinces in central China. A cross validation was done to evaluate the performance of the GTWR model. Compared with OLS, GWR, and TWR models, the GTWR model obtained the highest value of coefficient of determination (R²) and the lowest values of mean absolute difference (MAD), root mean square error (RMSE), and mean absolute percentage error (MAPE).

No single sensor can acquire complete information by applying one or several multi-surveys to cultural object reconstruction. For instance, a terrestrial laser scanner (TLS) usually obtains information on building facades, whereas aerial photogrammetry is capable of providing the perspective for building roofs. In this study, a camera-equipped unmanned aerial vehicle system (UAV) and a TLS were used in an integrated design to capture 3D point clouds and thus facilitate the acquisition of whole information on an object of interest for cultural heritage. A camera network is proposed to modify the image-based 3D reconstruction or structure from motion (SfM) method by taking full advantage of the flight control data acquired by the UAV platform. The camera network improves SfM performances in terms of image matching efficiency and the reduction of mismatches. Thus, this camera network modified SfM is employed to process the overlapping UAV image sets and to recover the scene geometry. The SfM output covers most information on building roofs, but has sparse resolution. The dense multi-view 3D reconstruction algorithm is then applied to improve in-depth detail. The two groups of point clouds from image reconstruction and TLS scanning are registered from coarse to fine with the use of an iterative method. This methodology has been tested on one historical monument in Fujian Province, China. Results show a final point cloud with complete coverage and in-depth details. Moreover, findings demonstrate that these two platforms, which integrate the scanning principle and image reconstruction methods, can supplement each other in terms of coverage, sensing resolution, and model accuracy to create high-quality 3D recordings and presentations.

This study presents a spectral–spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel to be classified. Specifically, it has two subnetworks. The spatial subnetwork introduces the proposed spatial self-attention module to exploit rich patch-based contextual information related to the center pixel. The spectral subnetwork introduces the proposed spectral self-attention module to exploit the long-range spectral correlation over local spectral features. The extracted spectral and spatial features are then adaptively fused for HSI classification. Experiments conducted on four HSI datasets demonstrate that the proposed network outperforms several state-of-the-art methods.

Landslide inventory is significant for landslide disaster reduction. To construct the landslide inventory, deep learning has received growing attention to detect landslides from satellite images. Among various deep learning algorithms, you-only-look-once (YOLO) has a strong ability to detect objects efficiently and has been widely used in landslide extraction. Despite its efficiency, there is no general rule to select the backbone and attention mechanism for YOLO. The selection of these two modules depends on specific application needs. Meanwhile, YOLO output is a series of anchor boxes, not accurate landslide boundaries. A single bounding box may contain many landslides and cannot extract individual landslides, limiting the YOLO applications in constructing landslide inventory. To address these issues, this article presents a lightweight attention-guided YOLO with level set layer (LA-YOLO-LLL) for landslide detection from optical satellite images. First, we introduced the MobileNetv3 to replace the original backbone of YOLO to simultaneously reduce the parameter complexity and improve the model transferability. Then, we presented a light pyramid features reuse fusion attention mechanism to improve landslide detection performance. Finally, we integrated the level set layer into YOLO head to produce accurate landslide boundaries. This article validated the accuracy and transferability of the presented method in two study areas (Bijie and Taiwan) with similar geo-environmental conditions. Experimental results show that the presented LA-YOLO-LLL model outperformed traditional YOLO in landslide detection. Findings in this article are valuable for landslide inventory construction, land use planning and risk control.

Pressure is a critical factor affecting the dielectric properties of rock materials. Previous studies have shown that the microwave dielectric properties of mineral rocks undergo regular changes under uniaxial pressure. In this study, diorite was selected as the specimen, and an open coaxial resonant microwave dielectric testing system was employed to investigate the microwave dielectric (2–18.3 GHz) properties of rock specimen under uniaxial and biaxial loading modes, respectively. Experimental results indicate that under uniaxial pressure, the dielectric constant at all frequency bands decreased gradually with the increasing of compressive stress, with an average decrease amplitude of 4.5%. Nevertheless, under the biaxial loading process, the change in dielectric constant exhibited a more complex pattern, which was closely related to the relationship between the axial stress and the lateral stress. When the axial stress was lower than the lateral stress, the dielectric constant increases significantly with the rise of axial stress. However, when the axial stress increased and got greater than the lateral stress, the dielectric constant began to decrease. The theoretical analysis based on dielectric physics indicate that both the changes in the number of polarization units and the polarization abilities of these polarization units influenced the dielectric properties of rocks under different loading conditions. This study is greatly important for revealing the change patterns and mechanisms of microwave dielectric properties of rocks, which implies that stress induced disturbances is an important factor to be considered in applying radar investigation and microwave remote sensing for the geological exploration, and geo-hazard perception.