Jia Li's research while affiliated with Yunnan Normal University and other places

... The principal problem in the creation of such maps is the possibility to have upgraded and accurate systems based on near-real-time data. Besides the mapping traditionally conducted with geographic information systems technologies [1,2], artificial intelligence techniques are used to help better create these kinds of maps, and several authors in the literature have addressed this. For example, in various contributions [3][4][5], Nwazelibe et al. have demonstrated advanced mapping technologies for testing the performance of different algorithms in the landslide susceptibility mapping of Nigeria's Udi Province, which is a region known for incessant soil erosion and landslide events. ...

... Recent technological advances allowed researchers to obtain data from hard-to-reach areas, resulting in utilizing UAV in mountainous regions and regions with mass movements in a safe manner and with enhanced detail (Clapuyt et al. 2017;Macciotta et al. 2020;Rodriguez et al. 2020). Importantly, topographical changes in landslides can detect complex displacement patterns using subsequent DSMs (Digital Surface Model) (Conforti et al. 2021;Zhang et al. 2023). Other researchers have used the technique to calculate surface displacements caused by mining activities and earthquakes, which can be effectively monitored using UAVs (Deffontaines et al. 2017;Cwiakała et al. 2020). ...

... The use of both UAV photogrammetry and LiDAR is well documented in landslide literature due to their ability to reduce fieldwork efforts and enhance safety conditions in landslide data collection and analysis. These technologies allow to obtain significant results in terms of characterization, mapping, and modelling [34][35][36][37][38], enabling the monitoring of temporal and spatial dynamics in landslide processes ( [39] and references therein). Turning specifically to rock landslides, UAV photogrammetry and LiDAR are particularly useful for detecting source areas, extracting discontinuity and joint families, computing the volumes of involved rock masses, and modeling block trajectories [40][41][42][43][44]. ...

... It offers wide area coverage, continuous monitoring over time, and simultaneous assessment over large geographical areas. It helps identify trends and potential factors by acquiring data at different time intervals, reducing the need for extensive ground surveys (Zhang et al., 2023), but has limitations such as topographic errors and noise. This article addresses the land subsidence in East Baton Rouge Parish (EBRP) in Louisiana using InSAR Sentinel-1 images collected between 2017 and 2021. ...

... These issues significantly hinder the achievement of large-scale and high-precision numerical calculations for open-pit mines. With the development of unmanned aerial vehicle (UAV) technology, the use of oblique photogrammetry methods has emerged as a means to rapidly construct high-precision three-dimensional realistic models of open-pit mines, thereby compensating for the limitations of traditional methods [9][10]. ...

... The coastal zone's resources and environmental protection rely greatly on the extraction and analysis of the shoreline, which acts as the boundary between the land and the water [7]. The study will employ data from shoreline islands as it provides uncertainty information brought on by processes such as erosion, accretion, sedimentation, wind and wave patterns, and sea level rise. ...

... Moreover, the completeness of 3D models is also vital for the development of digital cities and real-scene 3D representations of China (Lu et al. 2014). Among them, full-automatic extraction and restoration of water-area, optimization of 3D point clouds and 3D model can be an important part of making 3D models reach a high level of completeness and improving the aesthetics and usability of urban scene 3D models (Mishra et al. 2023;Duan et al. 2021). ...

... For traffic land, although we lack direct traffic flow data on each road, the 130-m night-light data is used. This resolution is much better than commonly used data, such as the DMSP and the VIIRS, which have resolutions of 1 km and 500 m, respectively (Andries et al. 2023;Zhang et al. 2021). Because most vehicles turn their lights on during night travel, this method is feasible, as confirmed by other studies (Andreano et al. 2021;Kabanda 2020). ...

... However, many graduates lack practical skills in frontline positions [2][3][4]. These de ciencies include a disconnect between theory and practice, insu cient practical skills like data analysis and epidemic investigation, inadequate communication and collaboration abilities, and a lack of problem-solving capabilities for public health emergencies and complex health issues. ...

... In addition, other CNN-based models such as PSPNet [34], AlexNet [35], ResNet [36], U-Net [37], and DenseNet [38] have also been utilized for the semantic segmentation of landslides. Furthermore, target detection models represented by faster R-CNN [39] and the YOLO series [40][41][42] have also been applied to landslide recognition tasks. ...