Search

This paper investigates how ancillary geographic data – in particular, information on land or assessor parcels – might be used to improve estimates for small area populations and population characteristics. It seeks to determine whether parcel land use codes can be used to reliably replicate population and housing distributions within small (subcounty) areas and whether other parcel attributes – in addition to land use – exhibit any explanatory power in replicating population and housing characteristics within these same places. The basis for this paper was Professor Barbara Buttenfield's service on the Census Scientific Advisory Committee, in which her working group explored the utility of administrative source data as an alternative or complement to federal survey data. This analysis highlights some of the benefits and complications of the incorporation of parcel data into geodemographic estimation, and the findings demonstrate that such a use is problematic but encouraging. [ABSTRACT FROM AUTHOR]

Dr. Buttenfield led the user evaluation and user interface design/improvement tasks in the Alexandra Digital Library (ADL) Project from 1994 to 1998 funded by the National Science Foundation in the U.S. Her research efforts in the ADL extended the role of cartographers from traditional map designers to web-based user interface and user experiences (UI/UX) designers. This paper will highlight key concepts and design principles (including user center design (UCD), usability testing, and user interface evaluation) in the ADL project and re-investigate these pioneering research topics in cartography with recent development of the Metaverse and human-computer interaction (HCI) using Extended Reality (XR), including Virtual Reality, (VR), Augmented Reality (AR), and Mixed Reality (MR). The new role of cartographers today includes user interface designers and usability evaluators using XR-enabled mapping tools and technologies. This paper will discuss cartographic research challenges and opportunities in the era of the Metaverse and highlight some software issues for cartographers to develop 3D or 4D web GIS applications. [ABSTRACT FROM AUTHOR]

We describe a Python-based software tool called RADIAN (RAnDom spatIal dAta geNerator) developed with the purpose of generating simple synthetic spatial datasets. These datasets can be used in many contexts such as teaching and learning of GIS, testing of spatial algorithms, testing and visualization approaches. This paper provides a motivation for the need for a tool such as RADIAN along with a survey of other similar approaches. The methodological component of how RADIAN generates synthetic spatial datasets is described. We describe experimental results from the comparison of RADIAN with QGIS, which is the most closely comparable tool available at the time of writing. Finally, we provide some conclusions on the impact and potential of RADIAN with some interesting avenues for future work and development. RADIAN is available as open-source software. [ABSTRACT FROM AUTHOR]

This document is an editorial from the journal "Cartography & Geographic Information Science" that recognizes the contributions of Professor Emerita Barbara P. Buttenfield to the field of Cartography and Geographic Information Science (GIScience). It highlights her research areas, academic honors, and awards. The editorial also discusses a scientometric analysis of papers citing Buttenfield's work, revealing four main areas of impact: visualization, mapping and GIS, population dynamics and urban issues, and environmental focus. The document introduces the five contributions to the special issue, which align with Buttenfield's main areas of impact. The guest editors express their gratitude to the authors and reviewers involved in the special issue and wish Buttenfield a happy retirement. [Extracted from the article]

Buttenfield (1988) pioneered research on multiple representations in the dawn of GIScience. Her efforts evoked inquiries into fundamental issues arising from the selective abstractions of infinite geographic complexity in spatial databases, cartography, and application needs for varied geographic details. These fundamental issues posed ontological challenges (e.g. entity classification) and implementational complications (e.g. duplication and inconsistency) in geographic information systems (GIS). Expanding upon Buttenfield's line of research over the last three decades, this study reviewed multiple representations in spatial databases, spatial cognition, and deep learning. Initially perceived as a hindrance to GIS, multiple representations were found to offer new perspectives to encode and decipher geographic complexity. This paper commenced by acknowledging Buttenfield's pivotal contributions to multiple representations in GIScience. Subsequent discussions synthesized the literature to outline cognitive representations of space in the brain's hippocampal formation and feature representations in deep learning. By cross-referencing related concepts of multiple representations in GIScience, the brain's spatial cells, and machine learning algorithms, this review concluded that multiple representations facilitate learning geography for both humans and machines. [ABSTRACT FROM AUTHOR]

Creating a map style from scratch is challenging. Cartographers may find inspirations from artistic paintings and transfer their style to maps. However, the reference painting and the extracted style elements may not fit well with the content and function of maps, resulting in undesirable or even frustrating map stylization. The question of how to choose appropriate paintings as inspirations and utilize their essential visual elements to stylize maps remains unanswered. As neuroscience has developed, an increasing number of neural mechanisms underlying visual perception have been discovered, deepening our understanding of artistic styles and their adaptation to maps. In this paper, we draw connections between visual neurons and style elements of both artistic paintings and maps by examining seven neural mechanisms (i.e. central-peripheral vision, color-to-contour adhesion, double-opponent effects, visual filling-in, orientation selectivity, latency variation, and what-where separation) that are typical of artistic paintings. We also demonstrate that these mechanisms are transferable to maps. We then create a cartographic style syntactics to generally indicate how and to what degree these mechanisms can be reflected in four cartographic stylistic criteria (i.e. identification, expressiveness, aesthetic appeal and emotional impact). Our work contributes to the integration of principles from neuroscience with cartographic design to deepen our understanding of map perception and to facilitate map style transfer. [ABSTRACT FROM AUTHOR]

Information Theory of Cartography plays an important role in guiding map design, generalization, and evaluation, and measurement of map information is the most basic topic of this theory. However, there are many problems in current measurement methods, and there is a long way to go to form a theoretically rigorous algorithm that can effectively depict spatial information and comprehensively consider the feeling of map readers. Luckily, we can now propose an evaluation metric that exhibits a certain correlation with map information based on deep learning to benefit actual cartography, and we term it as generalized map information evaluation to demonstrate differentiation. Specifically, this paper first constructs a subjective data set to support the supervised learning paradigm. Also, considering the difficulty of large-scale subjective data set collection, this paper proposes a Transfer-learning method for generalized Map Information evaluation (TransMI). Technically, a Siamese Network is pre-trained to explicitly acquire prior knowledge about the reasons for changes to mapped information. On this basis, one branch of the network is extracted and fine-tuned on the subjective data set to achieve the goal of predicting the quality of generalized map information. The results and the analysis of ablation studies prove the feasibility of our method. [ABSTRACT FROM AUTHOR]

The information contained in a map is always represented by text, symbols, and map-type. Among them, map-type is a critical element that denotes the category and theme of map content, which can support map content extraction, map retrieval, and other map data mining tasks. However, the representations of map-type are always so complex and diverse that relies on multiple descriptive labels. Traditional deep learning methods regarding map-type classification are developed by single label, which only supports single-task classification. This means these approaches might overlook the common features among multiple map-type. In this paper, we propose a framework of multi-task deep learning strategy for employing the state-of-the-art deep convolutional neural network models, including ResNet50, MobileNetV2, and Inception-v3, to conduct efficient multi-label map-type classification. Specifically, we develop the dedicated classification module and label selection layer, and integrate them into the backbone of the deep convolutional network model. The experiments revealed that our proposed multi-task classification strategy can achieve greater accuracy in map-type classification, with less processing time required compared to state-of-the-art deep learning regarding map-type classification. This proves that multi-task classification strategy could be competitive to recognize and discover the complex map-type information. [ABSTRACT FROM AUTHOR]

The AutoCarto 2022 symposium centered around the theme of "Ethics in Mapping: Integrity, Inclusion, and Empathy." The conference brought together experts in cartography and geographic information science (GIScience) to explore the ethical responsibilities in these fields. The conference featured sessions on topics such as the power of maps for equity and social justice, uncertainty in geospatial data, and diversity, ethics, and equality. A special issue of the conference included papers on societal impacts and ethical issues, cartographic design and map production, and technical advancements in cartography. The document also discusses the future of the conference series and potential research directions in the field. [Extracted from the article]

The past decade has witnessed the rapid development of geospatial artificial intelligence (GeoAI) primarily due to the ground-breaking achievements in deep learning and machine learning. A growing number of scholars from cartography have demonstrated successfully that GeoAI can accelerate previously complex cartographic design tasks and even enable cartographic creativity in new ways. Despite the promise of GeoAI, researchers and practitioners have growing concerns about the ethical issues of GeoAI for cartography. In this paper, we conducted a systematic content analysis and narrative synthesis of research studies integrating GeoAI and cartography to summarize current research and development trends regarding the usage of GeoAI for cartographic design. Based on this review and synthesis, we first identify dimensions of GeoAI methods for cartography such as data sources, data formats, map evaluations, and six contemporary GeoAI models, each of which serves a variety of cartographic tasks. These models include decision trees, knowledge graph and semantic web technologies, deep convolutional neural networks, generative adversarial networks, graph neural networks, and reinforcement learning. Further, we summarize seven cartographic design applications where GeoAI have been effectively employed: generalization, symbolization, typography, map reading, map interpretation, map analysis, and map production. We also raise five potential ethical challenges that need to be addressed in the integration of GeoAI for cartography: commodification, responsibility, privacy, bias, and (together) transparency, explainability, and provenance. We conclude by identifying four potential research directions for future cartographic research with GeoAI: GeoAI-enabled active cartographic symbolism, human-in-the-loop GeoAI for cartography, GeoAI-based mapping-as-a-service, and generative GeoAI for cartography. [ABSTRACT FROM AUTHOR]

The rapid development of information and communications technology has turned individuals into sensors, fostering the growth of human-generated geospatial big data. In disaster management, geospatial big data, mainly social media data, have opened new avenues for observing human responses to disasters in near real-time. Previous research relies on geographical information in geotags, content, and user profiles to locate social media messages. However, less than 1% of users geotag their messages, leaving geolocating users through user profiles or message content addresses increasingly crucial. This paper evaluates and visualizes the margin of error incurred when using user profiles or message-mentioned addresses to geolocate social media data for disaster research. Using Twitter data during the 2017 Hurricane Harvey as an example, this research assessed the inconsistencies in predicting users' locations in various administrative units during each disaster phase using three geolocating strategies. The results reveal that the similarities between geotags, and user profile locations decrease from 94.07% to 64.56%, 43.9%, 31.82%, 27.05%, and 26.7% as the geographical scale changes from country to state, county, block group, 1-kilometer, and 30-meter levels. These similarities are overall higher than the agreements between locations derived from geotags and tweet content. The geolocation consistencies among the three methods remain stable across disaster phases. The impacts of uncertainties in geolocating Twitter data for disaster management applications were further unraveled. The findings offer valuable insights into the trade-off between spatial scale and geolocation accuracy and inform the selection of appropriate scales when applying different geolocating strategies in future social media-based investigations. [ABSTRACT FROM AUTHOR]

This paper explores scholarly literature published since the 1960s that examines peoples' cognitive and perceptual understanding of map projections. Map projections present challenges to virtually everyone who uses them. Some of the challenges include selecting a projection, specifying projection parameters, and understanding distortion patterns. Broadly speaking, cartographic inquiry has addressed many topics in cognition and perception; yet, research focused on projections remains scarce. We surveyed the body of research studies incorporating projections or a projection-related topic (e.g. distortion) as a variable in the experimental design. Topics included asking participants to estimate areas, conceptualize travel paths, or identify preferred graticule aesthetics. Despite the conclusions reported by these studies, we noted three general concerns that may diminish the accuracy of results from research in this area. First, projection-specific terminology or properties critical to the studies and analysis that may be misunderstood by researchers and/or participants. Second, study participants were largely homogenous. Third, most of the studies were not designed for replication or reproducibility. Given our critique, we offer six suggestions for those who are interested in new cognitive and perceptual projection research. [ABSTRACT FROM AUTHOR]

Continuous-scale representation of urban blocks is critical for enriching the web-based mapping experience in the modern era. Traditionally, continuous-scale merging methods for surface elements have been employed to deal with landscape features, such as patches and land-cover data. In comparison, the artificially constructed urban blocks offer complex semantics and unique shapes. Traditional methods face challenges in maintaining their fundamental characteristics, which can result in improper merging outcomes. Therefore, this paper proposes a progressive merging method that takes into account the functional semantics and grid features of blocks. Initially, the POI data is used to obtain the functional semantic vectors of the blocks for creating basic information about the starting map. The blocks are then abstracted into a graphical structure whereby a breadth-first algorithm is employed to generate their groups; thereby, forming the target map. The map-based geometric and semantic merging cost formula has been devised to calculate the optimal merging sequence by the A* algorithm. Experiments have been performed by defining the main urban area of Beijing city as the study area. The comparative analysis indicates that the proposed method can obtain more reasonable progressive merging results. [ABSTRACT FROM AUTHOR]

Similarity of point patterns is critical to geographic information retrieval. Many methods depend on measuring the similarity between point patterns within the spatial database. However, previous researches mainly focus on point density which is only one aspect of point patterns. A point distribution can be complex by its numerous alignments of point groups, which usually imply different geographical meanings in reality. In this paper, we propose a new method that uses image analysis techniques to comprehensively consider the characteristics of a point pattern. Specifically, given a set of point datasets falling in the same region, our method first generates the point intensity surfaces to transform the original vector space to raster space; then, the method constructs a matrix to describe all the pattern-related information. Finally, the point pattern similarity is calculated by decomposing this matrix into the lower-order representation and the factorized basis features. Due to the use of matrix decomposition, the proposed method has the merits that it can eliminate noises from the original data and assess the similarity of two patterns with emphasis on their major features. As a case study, our method is effective in discovering regularity from the taxi pick-up/drop-off point datasets. [ABSTRACT FROM AUTHOR]

3-D classroom seating information is of great significance in a host of planning contexts including indoor navigation and facility management. Mapping classroom 3-D seats based on a single-view LiDAR scan is challenging because of occlusions and viewpoint limitations. In essence, one is left with incomplete point clouds, making object recognition difficult. The aim of this paper is to acquire complete point clouds for objects in a room based on a single-view LiDAR scan, focusing in particular on chairs in indoor spaces such as classrooms, lecture halls, theaters, concert venues, and sports arenas. A spatial optimization enabled framework is proposed for 3-D classroom seat mapping from a single-view LiDAR scan. A two-step clustering method is proposed to segment each individual chair object in the LiDAR scan. A chair model is extracted and used to complete other chair point clouds via registration. Notably, a parameter estimation method is devised based on spatial priors and integrated in an iterative closest point optimization approach to refine registration. Applications to multiple classroom scans demonstrate the effectiveness and accuracy of the proposed methodology. The developed segmentation-registration framework harnesses spatial knowledge to complete a single-view LiDAR scan with many identical objects. The resultant object point cloud is critical for navigation, route guidance, facility management, pandemic response and planning, indoor mapping and venue utilization, among others, which require precise and complete spatial information. Identified 3-D chairs extracted from LiDAR scans provide essential information for stakeholders seating configuration, property management, and indoor navigation. A new and challenging problem of completing partial objects from a single-view LiDAR scan is formulated. The developed framework provides a fast and high-precision solution to process single-view LiDAR scans for extracting and restoring incomplete objects by combining spatial knowledge, machine learning, and spatial optimization. Empirical results demonstrate the capability to acquire complete chair point clouds from multiple classroom scans to support planning and policy efforts in mitigating disease spread. [ABSTRACT FROM AUTHOR]

Close-range interpersonal interactions serve as a major channel for virus transmission, with higher infection risks indoors than outdoors. Thus, evaluating indoor infectious disease transmission risks is vital for effective epidemic prevention and control. However, collecting complete individual-level behavioral data faces challenges due to privacy concerns and data acquisition costs, impeding accurate indoor risk mapping. To address this, we propose an individual-centered, scenario-based simulation framework in this paper. This framework incorporates stepwise movement of agents to model crowd interactions in indoor spaces, enabling infection risk mapping through geographic scenario simulation. The simulation model's core components encompass the generation of indoor environments, formulation of individual behavior rules, establishment of human-environment interaction logic, and simulation of virus transmission processes. Additionally, we outline the implementation algorithm for this simulation model. Lastly, we employ a high-risk university canteen as a case study to demonstrate the model's capabilities in creating risk maps at different levels: spatial, spatiotemporal, and individual. The proposed framework achieves the construction and process simulation of multi-dimensional geographic scenarios at a microscale, introduces a behavior path model based on spatiotemporal cubes, and enhances the comprehensive analysis and mapping capabilities for indoor infectious disease risk, laying the foundation for precise prevention and control. [ABSTRACT FROM AUTHOR]

People create route descriptions based on their mental maps to provide route guidance, which represents their knowledge of the environment. Recent studies have attempted to model navigation knowledge from human route descriptions to facilitate route communication. However, they mainly focus on outdoor environments and do not address the representation of human descriptions of indoors in the form of schematic maps through the automatic extraction of spatial knowledge. Schematic maps have been commonly applied for public transportation by utilizing abstract representations to reduce cognitive load. Compared to route descriptions, schematic maps can provide easy-to-understand navigation guidance. In this paper, we present a novel NLP-based pipeline to automatically generate schematic maps from human route descriptions for indoor navigation. The experimental data consists of a set of crowdsourced route descriptions that follow a common template for a test building of the Soleway indoor navigation web service. The route descriptions and the generated schematic maps were presented to human participants in an online survey, and it was found that 92% of the generated schematic maps matched well with the corresponding human route descriptions. Thus, the proposed method is an effective and reliable approach for modeling route descriptions through schematic maps in indoor route communication. [ABSTRACT FROM AUTHOR]

Machine learning is increasingly used as a computing paradigm in cartographic research. In this extended editorial, we provide some background of the papers in the CaGIS special issue Machine Learning in Cartography with a special focus on pattern recognition in maps, cartographic generalization, style transfer, and map labeling. In addition, the paper includes a discussion about map encodings for machine learning applications and the possible need for explicit cartographic knowledge and procedural modeling in cartographic machine learning models. [ABSTRACT FROM AUTHOR]

The onset of the COVID-19 pandemic in late 2019 triggered an unprecedented global health crisis. Originating in Wuhan, China, the spread of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a worldwide upheaval, affecting every aspect of human life. As countries grappled with rising case counts, hospitalizations, and fatalities, the role of geospatial information and visualization in managing and understanding the pandemic became increasingly vital. This special issue of the Cartography and Geographic Information Science (CaGIS) Journal sought to explore the innovative and impactful ways in which geovisualization techniques have been employed to confront and elucidate the complexities of COVID-19. We describe significance and contribution of each paper that is part of the special issue, and avenues for new, exciting research around infectious diseases, keeping in mind that the research needs to be reproducible. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has had a profound impact worldwide and continues to spread due to various mutations of the virus. Many governmental and nonprofit agencies at different levels have quickly developed COVID-19 dashboards to disseminate information on the pandemic to the public. However, most of these systems have mainly distributed "plain" information (e.g. cases, death counts, vaccination), and rarely provided insights that can be gained from spatiotemporal analyses, such as the detection of emerging clusters. The results from these analyses hold tremendous potential for health policymakers as they try to identify ways to slow down transmission. We present a web-based geographic framework to detect and visualize space-time clusters of COVID-19. Our tightly coupled framework integrates the prospective space-time scan statistics and local indicators of spatial association (LISA) with novel 2D and 3D interactive visuals in a cyber environment (). We illustrate the applicability of our approach using COVID-19 data for the continental US. Our framework is portable to other regions that may experience infectious diseases but is also flexible to handle data of different spatial and temporal granularities. This paper fits within an effort to integrate space-time analytics for the monitoring of infectious diseases in web environment, ultimately improving health surveillance systems. [ABSTRACT FROM AUTHOR]

The spatial analysis of health data usually raises geoprivacy issues. Due to the virulence of COVID-19, scientists and crisis managers do need to analyze the distribution and spread of the disease with spatially precise data. In particular, it is useful to locate each case on a map to identify clusters of cases. To allow such analyses without breach of geoprivacy, geomasking techniques are necessary. This paper experiments with the geomasking techniques from the literature to solve this problem: masking the real address of positive cases while preserving the local spatial cluster patterns. In particular, two different approaches based on aggregation and perturbation are adapted to the geomasking of addresses in areas with different densities of population. A new simulated cluster crowding method is also proposed to preserve clusters as much as possible. The results show that geomasking techniques can spatially anonymize addresses while preserving clusters, and the best geomasking method depends on the use of the anonymized data. [ABSTRACT FROM AUTHOR]

A flow map is a type of thematic visualization that depicts the movement of objects across a geographical space using a tree layout resembling a natural river system. In this paper, we introduce an innovative and automated approach called REA-FM, which leverages the power of the maze-solving algorithm to extract rivers from digital elevation models (DEMs). This enables the creation of flow maps that originate from a single source and extend to multiple destinations. Initially, REA-FM represents the mapping space of a flow map using a DEM. Subsequently, a maze-solving algorithm is adapted to extract flow paths from the destinations to the origin within the DEM data, with constraints on search directions, direction weights, and search ranges based on quality criteria specific to flow maps. To obtain comprehensive flow maps, the maze-solving algorithm is employed iteratively, considering the importance of each flow path, as determined by their respective lengths. These obtained paths are finally rendered smoothly with varying widths using Bézier curves, thereby enhancing the visual aesthetics of the flow map. A comparative evaluation with existing approaches demonstrates that REA-FM can generate natural-looking flow maps with reduced total length and improved node distribution, eliminating node overlaps and edge crossings. Furthermore, the effectiveness of REA-FM is validated through three extension experiments involving heterogeneous mapping spaces and areas with obstacles. Parameter analysis confirms that REA-FM offers intuitive control over the layout of flow maps. Project website: https://github.com/TrentonWei/FlowMap [ABSTRACT FROM AUTHOR]

Street intersections are challenging for people with visual impairments. While tactile maps are an important support in both mobility training and independent journeys, the caseload of manual map production has made them less accessible. This paper explores the possibility of (semi-) automatically producing tactile maps for street intersections at large scales, with an initial evaluation focused on the graphic aspect of the produced maps. The automation attempts to identify acceptable default parameters and values and proposes an exploration of possible choices for potentially open decisions. It adapts the classic map production process with parameters to present the information tactilely at the intersection scale, and produces representation meaningful for PVIs and realistic for an automatic procedure, resulting in ready-to-print maps in two scales of three sizes, with different levels of details and styles. The resulting maps are evaluated by professionals involved in tactile graphics through a questionnaire to evaluate the defaults and discuss the possibility of open choices. The professionals validated the maps, and their evaluation emphasized the need to have an acceptable default while keeping some options open to cater to the diversity in the visually impaired audience. [ABSTRACT FROM AUTHOR]

With backcountry winter travel increasing in popularity, the importance of accessible avalanche safety information is crucial. Widely accessible avalanche backcountry maps use slope shading to show where avalanches are likely to start. This paper presents a new methodology called Human-Centered Avalanche Susceptibility Mapping (H-CASM), which shifts the cartographic emphasis of backcountry avalanche maps from the hazard of an avalanche starting in a specific location to risk to a human traveling in the terrain. Utilizing ArcGIS, RAMMS avalanche runout model, and Python, we developed H-CASM as an open-source code to incorporate possible avalanche runouts, terrain traps, and connected slopes while trying to reduce instances of false certainty in visualizations. To provide a more comprehensive representation of susceptible terrain, we integrated aspect, distance to ridges, and vector ruggedness in addition to slope for start zone susceptibility using high-resolution one-meter Digital Elevation Models (DEMs). Avoiding the use of discrete susceptibility categories, we applied continuous gradient shading reducing false certainty in the final visualization. This proof of concept sets a new precedent for the future of backcountry avalanche susceptibility maps. [ABSTRACT FROM AUTHOR]

The automation of map labeling is an ongoing research challenge. Currently, the map labeling algorithms are based on rules defined by experts for optimizing the placement of the text labels on maps. In this paper, we investigate the feasibility of using well-labeled map samples as a source of knowledge for automating the labeling process. The basic idea is to train deep learning models, specifically the generative models CycleGAN and Pix2Pix, on a large number of map examples. Then, the trained models are used to predict good locations of the labels given unlabeled raster maps. We compare the results obtained by the deep learning models to manual map labeling and a state-of-the-art optimization-based labeling method. A quantitative evaluation is performed in terms of legibility, association and map readability as well as a visual evaluation performed by three professional cartographers. The evaluation indicates that the deep learning models are capable of finding appropriate positions for the labels, but that they, in this implementation, are not well suited for selecting the labels to show and to determine the size of the labels. The result provides valuable insights into the current capabilities of generative models for such task, while also identifying the key challenges that will shape future research directions. [ABSTRACT FROM AUTHOR]

Pattern recognition of linear feature sets, such as river networks, road networks, and contour clusters, is essential in cartography and geographic information science. Previous studies have investigated many methods to identify the patterns of linear feature sets; the key to each of these studies is to generate a reasonable and computable representation for each set. However, most existing methods are only designed for a specific task or data type and cannot provide a general solution for formalizing linear feature sets owing to their complex geometric characteristics, spatial relations and distributions. In addition, some methods require human involvement to specify characteristics, choose parameters, and determine the weights of different measures. To reduce human intervention and improve adaptability to various feature types, this paper proposes a novel deep learning architecture for learning the representations of linear feature sets. The presented model accepts vector data directly without extra data conversion and feature extraction. After generating local, neighborhood, and global representations of inputs, the representations are aggregated accordingly to perform pattern recognition tasks, including classification and segmentation. In the experiments, building groups classification and road interchanges segmentation achieved accuracies of 98% and 89%, respectively, indicating the model's effectiveness and adaptability. [ABSTRACT FROM AUTHOR]