With the increasing number of remote sensing satellites, the diversification of observation modals, and the continuous advancement of artificial intelligence algorithms, historically opportunities have been brought to the applications of earth observation and information retrieval, including climate change monitoring, natural resource investigation, ecological environment protection, and territorial space planning. Over the past decade, artificial intelligence technology represented by deep learning has made significant contributions to the field of Earth observation. Therefore, this review will focus on the bottlenecks and development process of using deep learning methods for land use/land cover mapping of the Earth's surface. Firstly, it introduces the basic framework of semantic segmentation network models for land use/land cover mapping. Then, we summarize the development of semantic segmentation models in geographical field, focusing on spatial and semantic feature extraction, context relationship perception, multi-scale effects modelling, and the transferability of models under geographical differences. Then, the application of semantic segmentation models in agricultural management, building boundary extraction, single tree segmentation and inter-species classification are reviewed. Finally, we discuss the future development prospects of deep learning technology in the context of remote sensing big data.

Effectively managing extensive, multi-source, and multi-level real-scene 3D models for responsive retrieval scheduling and rapid visualization in the Web environment is a significant challenge in the current development of real-scene 3D applications in China. In this paper, we address this challenge by reorganizing spatial and temporal information into a 3D geospatial grid. It introduces the Global 3D Geocoding System (G3DGS), leveraging neighborhood similarity and uniqueness for efficient storage, retrieval, updating, and scheduling of these models. A combination of G3DGS and non-relational databases is implemented, enhancing data storage scalability and flexibility. Additionally, a model detail management scheduling strategy (TLOD) based on G3DGS and an importance factor $T$ is designed. Compared with mainstream commercial and open-source platforms, this method significantly enhances the loadable capacity of massive multi-source real-scene 3D models in the Web environment by 33 %, improves browsing efficiency by 48%, and accelerates invocation speed by 40%.

Affected by the insufficient information of single baseline observation data, the three-stage method assumes the Ground-to-Volume Ratio (GVR) to be zero so as to invert the vegetation height. However, this assumption introduces much biases into the parameter estimates which greatly limits the accuracy of the vegetation height inversion. Multi-baseline observation can provide redundant information and is helpful for the inversion of GVR. Nevertheless, the similar model parameter values in a multi-baseline model often lead to ill-posed problems and reduce the inversion accuracy of conventional algorithm. To this end, we propose a new step-by-step inversion method applied to the multi-baseline observations. Firstly, an adjustment inversion model is constructed by using multi-baseline volume scattering dominant polarization data, and the regularized estimates of model parameters are obtained by regularization method. Then, the reliable estimates of GVR are determined by the MSE (mean square error) analysis of each regularized parameter estimation. Secondly, the estimated GVR is used to extracts the pure volume coherence, and then the vegetation height parameter is inverted from the pure volume coherence by least squares estimation. The experimental results show that the new method can improve the vegetation height inversion result effectively. The inversion accuracy is improved by 26% with respect to the three-stage method and the conventional solution of multi-baseline. All of these have demonstrated the feasibility and effectiveness of the new method.

The relentless progress in the research of geographic spatial data models and their application scenarios is propelling an unprecedented rich Level of Detail (LoD) in realistic 3D representation and smart cities. This pursuit of rich details not only adds complexity to entity models but also poses significant computational challenges for model visualization and 3D GIS. This paper introduces a novel method for deriving multi-LOD models, which can enhance the efficiency of spatial computing in complex 3D building models. Firstly, we extract multiple facades from a 3D building model (LoD3) and convert them into individual semantic facade models. Through the utilization of the developed facade layout graph, each semantic facade model is then transformed into a parametric model. Furthermore, we explore the specification of geometric and semantic details in building facades and define three different LODs for facades, offering a unique expression. Finally, an innovative heuristic method is introduced to simplify the parameterized facade. Through rigorous experimentation and evaluation, the effectiveness of the proposed parameterization methodology in capturing complex geometric details, semantic richness, and topological relationships of 3D building models is demonstrated.

We-map is an interactive mobile map that can be easily communicated and applied on personal electronic devices, such as personal computers and mobile phones. Therefore, the study of direction systems and coordinate systems is critical, and exploring reference frames is essential in direction and coordinate systems. Despite its significance, existing research on We-map lacks specific solutions for the exploration of reference frames is indispensable for the establishment of accurate direction and coordinate systems. In this paper, we endeavor to address this gap by elucidating the significance of We-map reference frames, defining them with mathematical constraints, summarizing their nature and characteristics, deriving their transformation relationships and representing them through mathematical formulars and equations. Our work contributes to the fundamental theory of We-map and provides valuable systems and support for the mathematical foundation of We-map, map production, and platform development. Ultimately, this research serves to advance the development of We-map.

Accurate prediction of the movement trajectory of sea surface targets holds significant importance in achieving an advantageous position in the sea battle field. This prediction plays a crucial role in ensuring security defense and confrontation, and is essential for effective deployment of military strategy. Accurately predicting the trajectory of sea surface targets using AIS (Automatic Identification System) information is crucial for security defense and confrontation, and holds significant importance for military strategy deployment. In response to the problem of insufficient accuracy in ship trajectory prediction, this study proposes a hybrid genetic algorithm to optimize the Long Short-Term Memory (LSTM) algorithm. The HGA-LSTM algorithm is proposed for ship trajectory prediction. It can converge faster and obtain better parameter solutions, thereby improving the effectiveness of ship trajectory prediction. Compared to traditional LSTM and GA-LSTM algorithms, experimental results demonstrate that this algorithm outperforms them in both single-step and multi-step prediction.