The arid zone of central Asia secluded inland and has the typical features of the atmosphere. Human activities have had a significant impact on the air quality in this region. Urumqi is a key city in the core area of the Silk Road and an important economic center in Northwestern China. The urban environment is playing an increasingly important role in regional development. To study the characteristics and influencing factors of the main atmospheric pollutants in Urumqi, this study selected Urumqi’s daily air quality index (AQI) data and observation data of six major pollutants including fine particulate matter (PM_2.5), breathable particulate matter (PM₁₀), sulfur dioxide (SO₂), nitrogen dioxide (NO₂), carbon monoxide (CO), and ozone (O_{3_8h}) from 2014 to 2018 in conjunction with meteorological data to use a backward trajectory analysis method to study the main characteristics of atmospheric pollutants and their sources in Urumqi from 2014 to 2018. The results showed that: (1) From 2014 to 2018, the annual average of PM_2.5, PM₁₀, SO₂, NO₂ and CO concentrations showed a downward trend, and O_{3_8h} concentrations first increased, then decreased, and then increased, reaching the highest value in 2018 (82.15 μg·m^-3); The seasonal changes of PM_2.5, PM₁₀, SO₂, NO₂ and CO concentrations were characterized by low values in summer and fall seasons and high values in winter and spring seasons. The concentration of O_{3_8h}, however, was in the opposite trend, showing the high values in summer and fall seasons, and low values in winter and spring seasons. From 2014 to 2018, with the exception of O_{3_8h}, the concentration changes of the other five major air pollutants were high in December, January, and February, and low in May, June, and July; the daily changes showed a “U-shaped” change during the year. The high-value areas of the "U-shaped" mode formed around the 50th day and the 350th day. (2) The high-value area of AQI was from the end of fall (November) to the beginning of the following spring (March), and the low-value area was from April to October. It showed a U-shaped change trend during the year and the value was mainly distributed between 50 and 100. (3) The concentrations of major air pollutants in Urumqi were significantly negatively correlated with precipitation, temperature, and humidity (P<0.01), and had the highest correlation coefficients with temperature. (4) Based on the above analysis results, this study analyzed two severe pollution events from late November to early December. Analysis showed that the PM_2.5/PM₁₀ ratio in two events remained at about 0.1 when the pollution occurred, but was higher before and after the pollution (up to 1.46). It was shown that the pollution was a simple sandstorm process. Backward trajectory analysis clustered the airflow trajectories reaching Urumqi into 4 categories, and the trajectories from central Asia contributed the maximum values of average PM_2.5 and PM₁₀ concentrations.

Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. Using 2D and 3D information fusion for the advantages of compensation and accuracy improvement has become a hot research topic. However, there are no critical reviews focusing on the fusion strategies of 2D and 3D information integration based on various data for segmentation and detection, which are the basic tasks of computer vision. To boost the development of this research domain, the existing representative fusion strategies are collected, introduced, categorized, and summarized in this paper. In addition, the general structures of different kinds of fusion strategies were firstly abstracted and categorized, which may inspire researchers. Moreover, according to the methods included in this paper, the 2D information and 3D information of different methods come from various kinds of data. Furthermore, suitable datasets are introduced and comparatively summarized to support the relative research. Last but not least, we put forward some open challenges and promising directions for future research.

The change in land use leads to territorial spatial conflict. Territorial spatial conflicts mainly show that the boundaries of agricultural space, urban space, and ecological space overlap each other and interfere with each other’s functions, which will have a negative impact on regional high-quality development. The Aksu River, the most principal source of the Tarim River, the largest instream river in China, is a key area for maintaining ecological security in Northwestern China. It is highly significant to identify the spatial conflict characteristics of land use in this region to promote the sustainable use of regional land resources, optimization of spatial patterns, and the balance between economic construction and ecological environmental protection in mountainous areas. This paper takes the Aksu River Basin as the research area. Using Arcgis 10.8 software, Yaahp software, and SPSSAU software, it builds a land use spatial conflict measurement model based on a quantitative analysis of land use changes from 1990 to 2020 and explores the spatial and temporal evolution characteristics of land use conflicts in the Aksu River Basin. The results show that: (1) From 1990 to 2020, the spatial conflict pattern of the study area was dominated by ecological spatial conflicts. The spatial conflict area shows dynamic changes, but the overall trend is decreasing. (2) The spatial conflict pattern of territorial space in the Aksu River Basin has basically formed, and the three types of spatial conflicts are closely related to the level of local economic development. (3) Ecological spatial conflicts are mainly distributed in high-altitude mountains, river valleys, and oasis-to-desert transition areas. Urban spatial conflicts are mainly distributed in the middle and lower reaches of the Aksu River plain oasis. Agricultural spatial conflicts are scattered but large in scale, with small differences in the proportion of conflict distribution among the counties.

Identifying the driving factors of urban land surface temperatures (U-LSTs) is critical in improving urban thermal environments and in supporting the sustainable development of cities. Previous studies have demonstrated that two- and three-dimensional (2D and 3D) urban structure parameters (USPs) largely influence seasonal U-LSTs. However, the effects of 2D and 3D USPs on seasonal U-LSTs at different spatial scales still await a general explanation. In this study, we used very-high-resolution remotely sensed data to investigate how 2D and 3D USPs impact seasonal U-LSTs at different spatial scales (including pixel and city block scales). In addition, the influences of various functional zones on U-LSTs were analyzed. The results show that, (1) generally, the links between USPs and U-LSTs at the city block scale were more obvious than those at the pixel scale, e.g., the Pearson correlation coefficient (r) between U-LST and the mean building height at the city block scale (summer: r = −0.156) was higher than that at the pixel scale (summer: r = −0.081). Tree percentage yielded a considerable cooling effect on summer U-LSTs on both the pixel (r = −0.199) and city block (r = −0.369) scales, and the effect was more obvious in regions with tall trees. (2) The independently total explained variances (R²) of 3D USPs on seasonal U-LSTs were considerably higher than those of 2D USPs in most urban functional zones (UFZs), suggesting the distinctive roles of 3D USPs in U-LST regulation at the local scale. Three-dimensional USPs (R² value = 0.66) yielded more decisive influences on summer U-LSTs than 2D USPs did (R² value = 0.48). (3) Manufacturing zones yielded the highest U-LST, followed by residential and commercial zones. Notably, it is found that the explained variances of the total study area for seasonal U-LSTs were significantly lower than those of each UFZ, suggesting the different roles of 2D and 3D USPs played in various UFZs and that it is critical to explain U-LST variations by using UFZs.

Ecological corridors can improve the connectivity between different habitat regions, ultimately halting the loss of biodiversity and habitat fragmentation. Building ecological corridors is a crucial step in protecting biodiversity. Ecological corridors had previously been built primarily on nature reserves, ignoring ecosystem services. In this study, a novel approach to building ecological corridors is put forth that takes into account a variety of ecosystem services, morphological spatial pattern analysis (MSPA), and connectivity methodologies to identify significant ecological sources. Ecological corridors and significant strategic nodes are created based on the minimum cumulative resistance model (MCR) and circuit theory in order to construct the Yangtze River Delta’s ecological security pattern. The research found that: (1) the identified ecological sources are 90,821.84 km², and the total length of ecological corridors is 4704.03 km. (2) In total, 141 ecological restoration areas are identified, with a total area of 2302.77 km²; 151 ecological protection areas are identified, with a total area of 5303.43 km². This study can provide valuable insights into the establishment of ecological patterns and the construction of priority restoration and protection areas in the ecological restoration of the Yangtze River Delta.

Ecosystem degradation and conversion are leading to a widespread reduction in the provision of ecosystem services. It is crucial for the governance of regional land spaces to rapidly identify key areas for ecosystem restoration. Herein, we combined the InVEST Habitat Quality Model with the granularity inverse method to identify ecological sources in Jiashi county, China, based on the “source-corridor” ecological security pattern paradigm. The minimum cumulative resistance model and circuit theory were adopted to diagnose the ecological “pinch points”, barrier points, break points, and key restoration areas for land space. Our results show that: (1) the area of the ecological source and the total length of the ecological corridor were identified as 1331.13 km² and 316.30 km, respectively; (2) there were 164 key ecological “pinch points” and 69 key ecological barrier points in Jiashi county, with areas of 15.13 km² and 14.57 km², respectively. Based on the above ecological security pattern, recovery strategies are put forward to improve regional ecosystem health. This study describes the best practices which can be used to guide the planning and implementation of ecosystem restoration at the local landscape scale.