Social networks, combined with location-based services, offer valuable opportunities to examine social media sentiment and interactions across regions. Information flow within social networks is often highly directional and intense, transcending geographic distances. As a result, Geographically Weighted Regression (GWR), a traditional model that uses geographic distance to measure spatial proximity, falls short in explaining the factors influencing social media sentiment. To address this limitation, this study proposed a bi-directional flow weighted regression (BDFWR) model, supported by large language models, to interpret influencing factors of social media sentiment. The results demonstrated that the BDFWR model outperformed the GWR model by effectively capturing the relationship between social media sentiment and socioeconomic factors. This approach revealed deeper insights into the spatial heterogeneity of social media sentiment across diverse regions, enhancing the accuracy of modelling social media sentiment distribution. Incorporating bi-directional flow distance significantly improved the model’s performance, particularly in cases involving ‘closely low interflow’ and ‘remotely high interflow’ phenomena—critical aspects often neglected in conventional geographic models. Moreover, large language models excelled in detecting implicit positive and negative trends within textual data, offering a promising avenue for advancing sentiment analysis research.

The emergence of crowdsourced geographic information (CGI) has markedly accelerated the evolution of land-use and land-cover (LULC) mapping. This approach taps into the collective power of the public to share spatial information, providing a relevant data source for producing LULC maps. Through the analysis of 262 papers published from 2012 to 2023, this work provides a comprehensive overview of the field, including prominent researchers, key areas of study, major CGI data sources, mapping methods, and the scope of LULC research. Additionally, it evaluates the pros and cons of various data sources and mapping methods. The findings reveal that while applying CGI with LULC labels is a common way by using spatial analysis, it is limited by incomplete CGI coverage and other data quality issues. In contrast, extracting semantic features from CGI for LULC interpretation often requires integrating multiple CGI datasets and remote sensing imagery, alongside advanced methods such as ensemble and deep learning. The paper also delves into the challenges posed by the quality of CGI data in LULC mapping and explores the promising potential of introducing large language models to overcome these hurdles.

Land cover mapping is crucial for natural resource assessment, urban planning, and sustainable development. Land cover nomenclature often includes two or three hierarchic levels with tree-like hierarchical structures. This study aims to explore these hierarchical relationships and the potential of hierarchical semantic segmentation for land cover mapping. We propose a hierarchical semantic segmentation architecture by taking advantage of dual U-shape network, named as HierU-Net. The coarse-level result is ingested to the fine-level segmentation functioned as soft constraints. The propagation of error will not be certain. Moreover, we employ a multi-task loss function weighted by homoscedastic uncertainty to optimize the training. To evaluate the performance of the proposed method, we create a hierarchical semantic segmentation dataset (HierToulouse), which contains 11,528 samples, including images and land cover labels at two hierarchical levels. The experiments demonstrate that the proposed approach is capable of achieving accurate land cover segmentation at both coarse and fine levels, with segmentation results surpassing those obtained using the flat method.

Due to the limitations of hardware technology and budget constraints, there always exists a tradeoff between spatial and spectral resolutions in a hyperspectral image (HSI). Because of the limited spatial resolution, mixed pixels are a common issue in HSIs, and consequently, some targets appear as subpixels. The effectiveness of hyperspectral target detection is affected greatly by the subpixel targets, especially when the size of the targets is small. In this article, we proposed a double dictionary-based nonlinear representation model for hyperspectral subpixel target detection (DDNRTD). DDNRTD represents HSIs with a nonlinear model based on background and target dictionaries, which fully considers the spatial property of background and targets and can separate background and targets reliably, especially for small-sized subpixel targets. In addition, we designed an over-completed background dictionary construction strategy to represent the background part more effectively, which integrates spectral angle distance (SAD) with sparse representation. Experiments on two simulated and five real HSI datasets showed that the proposed DDNRTD method produced more accurate detection results than six state-of-the-art methods.

The majority of spatial data provided as Volunteered Geographic Information (VGI) are roads and other linear map features. Such data have been widely used in routing and navigation, road network update, emergency response, urban planning and more. Due to the lack of cartographic standards and issues with volunteer credibility, the quality of VGI linear features remains a concern and could seriously hinder the broad application of VGI data. This research proposes a comprehensive quality assessment framework for VGI linear features which adopts factor analysis to integrate two novel quality metrics with six other commonly used metrics, and further examines the spatial autocorrelation and semantic correlation of VGI linear feature quality. The OpenStreetMap road network of Allegheny County, Pennsylvania (USA) was selected as an example to test the proposed framework. Our results suggest that the proposed metrics, Box-counting dimension difference and Link accuracy are feasible for detecting quality issues and are important supplements to the common quality metrics. The findings also show that significant spatial autocorrelation exists in spatial completeness, positional accuracy, and logical consistency. Road type such as Tertiary, Residential, Service and Link has been proven to be a typical indicator of the different quality elements for VGI linear features.

Understanding the spatial scale sensitivity of cellular automata is crucial for improving the accuracy of land use change simulation. We propose a framework based on a response surface method to comprehensively explore spatial scale sensitivity of the cellular automata Markov chain (CA-Markov) model, and present a hybrid evaluation model for expressing simulation accuracy that merges the strengths of the Kappa coefficient and of Contagion index. Three Landsat-Thematic Mapper remote sensing images of Wuhan in 1987, 1996, and 2005 were used to extract land use information. The results demonstrate that the spatial scale sensitivity of the CA-Markov model resulting from individual components and their combinations are both worthy of attention. The utility of our proposed hybrid evaluation model and response surface method to investigate the sensitivity has proven to be more accurate than the single Kappa coefficient method and more efficient than traditional methods. The findings also show that the CA-Markov model is more sensitive to neighborhood size than to cell size or neighborhood type considering individual component effects. Particularly, the bilateral and trilateral interactions between neighborhood and cell size result in a more remarkable scale effect than that of a single cell size.

Terrestrial laser scanning (TLS) is a widely used remote sensing technique which can produce very dense point cloud data very promptly and is particularly suited for surface deformation monitoring. Deformation magnitude is typically estimated by comparing TLS scans over the same area but at different time epochs of interest. However, there is an issue related to such a method, which is not clear that whether the difference between two successive surveys results from the surface deformation. Hence, it is vital to determine the minimum detectable deformation (MDD) by a TLS device with a given registration and point cloud error level. In this paper, the MDD is determined based on the computation of the point cloud error entropy. The performance of the proposed method is extensively evaluated numerically using simulated plane board deformation point clouds under a range of distances and incidence angles. This proposed method was also successfully applied to deformation monitoring of one landslide test site located in the Wuhan University of Technology. The experimental results demonstrate that the theoretical MDD has a good match with the actual deformation, and the deformation greater than MDD can be accurately detected by the TLS device.

With pixel un-mixing, the omission of pixel caused by mixed pixel can be resolved so as to improve the classification accuracy. But the trouble is only the proportion of each end member object in one pixel which can be got through pixel un-mixing, while the spatial distribution of is uncertain. The objective of this study is to introduce the sub-pixel mapping based on spatial attraction model and explore some issues of it, such as neighboring pixels selection and spatial attraction normalization. As the experiments proven, the sub-pixel mapping could get better result by the eight neighboring pixels selecting mode and normalizing by sub-pixel mode in most cases.

Geomatics is a new developed science represented by "3S" technology including communication and computer technology. It is ideally suited for engineering management, especially in the construction management of large construction projects which include a large of spatial information. In this paper, spatial information technology will be introduced to engineering management filed to construct of EGIS (Engineering Geographic Information System). It not only have the past engineering information management system functions, but also have a powerful and unique ability with spatial information technology, such as graphics performance, spatial analysis, 3D visualization, etc. In addition, we could use GPS technology to achieve real-time monitoring and quality controlling of construction process. A prototype system of RCC-EGIS had been developed. The main functions, technology Route and the key technology of this system will be introduced.

The remote sensing classification is usually difficult to get a satisfied result because of the complicated relationships between surface objects and their spectral characteristics. Considering the spatial dependences of different objects, the spatial object information was introduced and an object- orientation classification method was proposed by different authors. That method could improve the classification results because the spatial dependences and spectral characteristics of objects were simultaneously considered. The results from that method are usually not good enough, as most of parameters and criteria need to be decided by experience, which is easy to bring some biases. In this paper, an object-neighborhood searching was proposed, in which the dependant locations of spatial objects and other ancillary geographical data were used to correct the regular errors in the supervised classification results. In this study, the original supervised resultant image was mainly found three kinds of regular errors: 1) some rice paddies were classified into wetlands; 2) some grasslands were classified into farmlands; 3) some urban areas were confused with the bare land especially in the river flat. In order to solve those problems, water body was selected as a reference to implement an object-neighborhood searching, combining with the GIS-based road information and analysis of slope and elevation. The object-neighborhood searching algorithm was implemented by ERDAS IMAGINE spatial model language, and ERDAS IMAGINE Knowledge Classifier was used to create the criteria and correct the regular errors in the supervised classification. The results showed that the classification accuracy could be greatly improved using the proposed method of this paper.

The research purpose is to discuss the development trend and theory of the semantic integration and interoperability of geography information systems on the network ages and to point out that the geography ontology is the foregone conclusion of the development of the semantic-based integration and interoperability of geography information systems. After analyzing the effect by using the various new technologies, the paper proposes new idea for the family of the ontology class based on the GIS knowledge built here. They are the basic ontology, the domain ontology and the application ontology and are very useful for the sharing and transferring of the semantic information between the complicated distributed systems and object abstracting. The main contributions of the paper are as follows: (1) For the first time taking the ontology and LDAP (lightweight directory access protocol) in creating and optimizing the architecture of spatial information gird and accelerating the fusion of Geography Information System and other domain's information systems. (2) For the first time, introducing a hybrid method to build geography ontology. This hybrid method mixes the excellence of the independent domain expert and data mining. It improves the efficiency of the method of the domain expert and builds ontology semi-automatically. (3) For the first time, implementing the many-to-many relationship of integration ontology system by LDAP's reference and creating ontology-based virtual organization that could provide transparent service to guests.

With the development of digital information technology in mining industry, the concept of DM (digital mining) and MGIS (mining geographical information system) are becoming the research focus but not perfect. How to effectively manage the dataset of geological, surveying and mineral products grade is the key point that concerned the sustainable development and standardized management in mining industry. Based on the existing combined GIS and remote sensing technology, we propose a model named DMMIS (digital mining management information system), which is composed of the database layer, the ActiveX layer and the user interface layer. The system is used in Laozhaiwan gold mine, Yunnan Province of China, which is shown to demonstrate the feasibility of the research and development achievement stated in this paper. Finally, some conclusions and constructive advices for future research work are given.