Geographic Information Science Research Articles

ML Approaches for the Study of Significant Heritage Contexts: An Application on Coastal Landscapes in Sardinia

Remote Sensing (RS) and Geographic Information Science (GIS) techniques are powerful tools for spatial data collection, analysis, management, and digitization within cultural heritage frameworks. Despite their capabilities, challenges remain in automating data semantic classification for conservation purposes. To address this, leveraging airborne Light Detection And Ranging (LiDAR) point clouds, complex spatial analyses, and automated data structuring is crucial for supporting heritage preservation and knowledge processes. In this context, the present contribution investigates the latest Artificial Intelligence (AI) technologies for automating existing LiDAR data structuring, focusing on the case study of Sardinia coastlines. Moreover, the study preliminary addresses automation challenges in the perspective of historical defensive landscapes mapping. Since historical defensive architectures and landscapes are characterized by several challenging complexities—including their association with dark periods in recent history and chronological stratification—their digitization and preservation are highly multidisciplinary issues. This research aims to improve data structuring automation in these large heritage contexts with a multiscale approach by applying Machine Learning (ML) techniques to low-scale 3D Airborne Laser Scanning (ALS) point clouds. The study thus develops a predictive Deep Learning Model (DLM) for the semantic segmentation of sparse point clouds (<10 pts/m2), adaptable to large landscape heritage contexts and heterogeneous data scales. Additionally, a preliminary investigation into object-detection methods has been conducted to map specific fortification artifacts efficiently.

Improving horizon computation algorithm with quasirandom sequences

The topographic horizon can be used to estimate shading for applications requiring an accurate solar resource estimate, including the effects of the local terrain. With high-resolution topography data, horizon estimation significantly contributes to the computation time needed for irradiance simulations. Approximate horizon algorithms have been proposed previously, sampling topography in a finite number of directions. This paper extends this idea by presenting a sampling approach based on the quasirandom sequences. The sampling strategy is optimized with 300,000 km2 of topography data from Europe and the USA. We demonstrate that our algorithm is several orders of magnitude faster than the precise horizon calculation and significantly improves the previous approximate algorithms. In particular, at the ground level with a topography resolution of 1 m/pixel, the proposed method achieved the same accuracy as the old approximate method four times faster. The horizon is one of the key methods in geographical information science and a part of many modeling tools in the built environment. Improvements in computation time benefit all applications that require irradiance modeling, e.g., the yield of vehicle- and building-integrated photovoltaic or temperature modeling of buildings.

Preface

With the rapid development of science and technology, computer, remote sensing technology and aerospace science have increasingly become the focus of attention of academia and industry. Since the first International Conference on Computer, Remote Sensing and Aerospace (CRSA) was held, the conference has become an important platform for scholars in related fields to exchange ideas and share results. The 2024 4th International Conference on Computer, Remote Sensing and Aerospace (CRSA 2024) continues the high-level academic tradition of the previous three conferences, and was held virtually in Osaka, Japan from July 5th to 7th, 2024. The conference aimed to promote the cross-fertilization between computer science, remote sensing technology and aerospace science, to promote technological innovation and industrial upgrading, and to contribute wisdom and strength to the global scientific and technological development. It called for papers on such topics as High-Performance Computing, Computer Aided Design, Robotics and Automation, Geographic Information Science, Satellite Navigation and Positioning, Optical Remote Sensing, Aeroelasticity and Structural Dynamics, Manned / Unmanned Aviation, etc. The conference attracted the active participation of experts, scholars, engineers and industrial elites from all over the world, and the latest research results and technological advances in relevant field were demonstrated through thematic reports, oral and poster presentations. The thematic speeches covered the problems, challenges, solutions, and future research directions of computer science, remote sensing technology and aerospace science, and provided participants with comprehensive and in-depth understanding and insight, stimulating thinking and innovation. Scholars who participated in oral and poster presentations had in-depth exchanges with other participants, sharing experiences and insights, and jointly exploring cutting-edge issues in relevant disciplines and domains. In addition, we have carefully selected and prepared a collection of Proceedings based on this conference, which represents a bunch of excellent papers, covering the latest research achievements and innovative ideas in related fields. We hope that this Proceedings will be an important reference for the academic community, providing researchers with opportunities for in-depth research, and will also inject new vitality and impetus into the development and innovation in the fields of and related to computer science, remote sensing technology and aerospace science. At the same time, we also hope that scholar and researchers will continue to uphold the spirit of science and the courage to explore unknown areas, contributing to the prosperity and progress of mankind. Finally, we would like to express our sincere thanks to all for their support and participation in the conference. We believe that through the exchange and cooperation of this conference, we will jointly create a new future in the fields of computer science, remote sensing technology and aerospace science. We also believe that the publication of this Proceedings will make a positive contribution to the development of the academic community and the progress of aerospace industry! The Committee of CRSA 2024 List of Committee Member is available in this Pdf.

Promoting Competitive Football through Geodetection: Performance of Departments in Producing Talent in Cameroon

Renewing competitiveness is a permanent challenge in football to ensure its survival, as the world quickly tires of the absence of magic or of the same champion winning every time. Football governing bodies around the world have therefore invested heavily in the detection and training of new talent according to a well- defined planning model. In Cameroon, we have seen a decline in the overall level of football through the absence of results for several years on the continental stage, whether by local clubs or the national team, and this can be explained by the absence of a clear planning policy with regard to the detection of new talent. In this context, the aim of our study was to map the performance of departments in terms of their development ecosystem in producing talent in order to revitalise football in Cameroon. The methodology used consisted of a weighted hierarchical analysis of the various criteria considered in the talent development ecosystem, including the concentration of young people in the departments, as well as the infrastructure, structures such as clubs and training centres that cater for them, and also their educational and health care. The data was collected and processed using appropriate geographic information science tools and software. The results revealed three categories of departmental performance, with only 4 of Cameroon's 58 departments performing very well, 18 performing moderately well in terms of producing talent for the development ecosystem and the rest not performing at all. With a view to planning detections throughout the country, these results are convincing and will enable FECAFOOT decision-makers to draw on clear studies to launch the new generation of Cameroonian football, and also to identify concrete areas for improvement in the less successful departments.

Combining hierarchies for spatial reasoning of hierarchical relations among places in different contexts

Spatial reasoning of hierarchical relations is an important research topic in geographic information science. Existing literature focuses mainly on hierarchical relations according to ordered containment of point sets based on the 9-Intersection Model (9IM). However, in natural language descriptions, hierarchical relations expressed by prepositions such as in can have spatial configurations conflicting with those hierarchical relations based on 9IM. This paper proposes an algorithm employing combined hierarchies to infer hierarchical relations among places in different contexts. Two graph databases containing combined hierarchies conforming to administrative reach and geometric enclosure are established with places represented by polygons with misaligned boundaries on prototypical and real data. The 13170 pairs of conflicting hierarchical relations with the same start nodes but different end nodes detected in the combined hierarchies on real data validate the proposed algorithm for spatial reasoning of hierarchical relations in different contexts. This research facilitates consistent spatial reasoning of hierarchical relations in different contexts for spatial information retrieval and question answering.

Scale dimensions in public participation GIS: an overview for planning and research

Questions of spatial scale infiltrate Public Participation GIS (PPGIS) in multiple phases of the data collection from the design of a PPGIS survey to the use of the produced spatial knowledge. This paper provides an overview on how spatial scale and scale effects influence the use of PPGIS tools and the validity and usability of the spatial data they produce. The paper approached scale from two complimentary perspectives: as a concept in human geography and as an attribute of cartographic representation in geographic information science. This discussion is organized around three main viewpoints on scale and PPGIS, namely (1) scale in data collection denoting the geographic extent of the study area and the study population, (2) scale in survey design manifested in technical issues, cartographic representation, usability, and design of the mapping activities, and (3) scale and scale effects in the analysis of PPGIS data and the production of spatial knowledge. Together, these views on scale outline the main scale-related issues to consider when planning a PPGIS survey or working with secondary PPGIS data.

Terra infirma: On the base map in urban cartography and GIS

This article investigates the ways in which base maps are a fundamental, but under-recognised, starting point for planners, architects, cartographers and geographic information scientists in urban spatial planning and decision-making contexts. Focusing on the case study of a collaborative mapping project with the Wood Street Commons, an unhoused community in West Oakland, it contends that base maps create a cartographic terra infirma, fundamentally shaping the process of negotiations over urban space in ways that reinforce possessive logics and normalize property as central to the function of the city. Base maps do so by paradoxically absenting all people – with the effect of absenting the occupation of land by unhoused people, while shielding property owners from view while enacting their possession through infrastructure, parcel boundaries and land features. We argue this privileging inherent in the urban base map ultimately fuels a process of “unbecoming” ( Fraser, 2018 ) – a simultaneous invisibilizing and reproduction of spatial inequality – and in response, call for attention towards the politics of base maps from urban cartographers, planners, architects and spatial scientists alike.

Coupling Hyperbolic GCN with Graph Generation for Spatial Community Detection and Dynamic Evolution Analysis

Spatial community detection is a method that divides geographic spaces into several sub-regions based on spatial interactions, reflecting the regional spatial structure against the background of human mobility. In recent years, spatial community detection has attracted extensive research in the field of geographic information science. However, mining the community structures and their evolutionary patterns from spatial interaction data remains challenging. Most existing methods for spatial community detection rely on representing spatial interaction networks in Euclidean space, which results in significant distortion when modeling spatial interaction networks; since spatial community detection has no ground truth, this results in the detection and evaluation of communities being difficult. Furthermore, most methods usually ignore the dynamics of these spatial interaction networks, resulting in the dynamic evolution of spatial communities not being discussed in depth. Therefore, this study proposes a framework for community detection and evolutionary analysis for spatial interaction networks. Specifically, we construct a spatial interaction network based on network science theory, where geographic units serve as nodes and interaction relationships serve as edges. In order to fully learn the structural features of the spatial interaction network, we introduce a hyperbolic graph convolution module in the community detection phase to learn the spatial and non-spatial attributes of the spatial interaction network, obtain vector representations of the nodes, and optimize them based on a graph generation model to achieve the final community detection results. Considering the dynamics of spatial interactions, we analyze the evolution of the spatial community over time. Finally, using taxi trajectory data as an example, we conduct relevant experiments within the fifth ring road of Beijing. The empirical results validate the community detection capabilities of the proposed method, which can effectively describe the dynamic spatial structure of cities based on human mobility and provide an effective analytical method for urban spatial planning.

Towards National Connected Digital Twins - A Geospatial Perspective

Abstract. Digital Twins are realistic digital representations of the physical world, frequently characterised by a two way link between digital and physical. Originating in manufacturing, they are now expanding to city and national scales. In this paper we explore connections between Geographic Information Science and National Digital Twins. Six different viewpoints and perspectives are presented on the topic, highlighting the importance of: geospatial data engineering; metadata engineering; standards; challenges facing mapping agencies; governance and public values; and a ”reality check” that explores the gaps between what is required and what can currently be achieved. We present 22 recommendations and summarise the findings by presenting a high level research agenda to enable better understanding and articulation of the link between the two.

A location analytics perspective of regional science at a crossroad

Location analytics have been a mainstay in regional science since its inception. Why? Perhaps the biggest reason is the ability to tease out important spatial heterogeneity nuances, but also to communicate geographically oriented analysis, planning, management and policy issues in rigorous ways, often as mathematical models, that can be subjected to further scrutiny and evaluation. Further, addressing broad challenges facing emergency response, food production, risk mitigation, transportation, public health, crime, housing and other issues through such approaches has proven an immense benefit to society. This paper focuses on the evolving subfield within regional science of location analysis and modeling, highlighting contributions to date but also detailing exciting areas of advancement involving spatial optimization and geographic information science. The paper includes a reflection on regional science journal publication trends, but also broader patterns of location analytics activity. It is hoped that this review will lead to a reassessment of regional science priorities, and consideration of the role that our specialty areas have in maintaining core strengths as well as potential for growing the discipline in the coming years.

BB-GeoGPT: A framework for learning a large language model for geographic information science

Large language models (LLMs) exhibit impressive capabilities across diverse tasks in natural language processing. Nevertheless, challenges arise such as large model parameter size and limited model accessibility through APIs such as ChatGPT and GPT-4, which prohibits the model deployment on mobile devices and domain adaptation or fine-tuning. Moreover, while LLMs excel in general domains, their performance in specialized fields such as GIS may not always align with the expectations of domain experts. This is primarily attributed to the diverse disciplinary origins of the training data, which often lack comprehensive coverage and treatment of knowledge specific to individual disciplines (e.g., GIS). Therefore, there is a crucial need to train and adapt LLMs specifically designed for different professional fields. In this paper, our focus is on the GIS domain, where we introduce BB(BaBy)-GeoGPT, a large language model with GIS-specific knowledge. To achieve this goal, we curated a comprehensive set of resources, comprising model pretraining data (BB-GeoPT, 26,907 documents), supervised fine-tuning data (BB-GeoSFT, 35,876 instructions), and evaluation data (BB-GeoEval, 600 objective questions and 150 subjective questions). BB-GeoGPT is developed by first adapting an open-source general-domain LLM, the LLaMA-2-7B model, to our pretraining data. Subsequently, we use instruction tuning to further fine-tune the model on our BB-GeoSFT. Through extensive experiments on the evaluation dataset, BB-GeoGPT demonstrates improvements ranging from 10.55% to 47.57% for objective questions and from 7.87% to 27.73% for subjective questions, when compared to general LLMs of similar size in terms of accuracy. Moreover, our data collection strategy and the amassed data can serve as a foundation for advancing LLM research in the GIS domain, fostering further development.

Coupling cellular automata and What If? models for residential expansion simulation: A case study of Southwest Sydney, Australia

AbstractThe impact of urban expansion on achieving sustainable development goals (SDGs) has become a significant research topic in the field of geographic information science. In this article, we describe a coupled cellular automata (CA)—‐What If? model to explore SDG11 “Sustainable cities and communities.” The model calculates overall residential land use demand based on historical data archives using the What If? planning support system (PSS), and then allocates it using a CA model that incorporates variables related to SDG11.2.1 and 11.7.1. Historical datasets for years 2016 and 2021 from Southwest Sydney, Australia were used to assess model accuracy, after which two residential expansion scenarios (years 2021 and 2026) were generated. Based on the modeling results, the SDG‐related spatial variables can improve the overall accuracy of CA sub‐models using an XGBoost machine learning training methodology. The simulation results of these scenarios confirm the effectiveness of the coupled CA‐What If? model, which has the potential to generate more reliable scenario results than the standalone What If? PSS for modeling urban growth of cities across Australia and internationally.

Next track point prediction using a flexible strategy of subgraph learning on road networks

Accurately predicting the next track point of vehicle travel is crucial for various Intelligent Transportation System (ITS) applications, such as travel behavior studies, traffic control, and traffic congestion monitoring. Recent works on trajectory prediction follow a paradigm that first represents the raw trajectory and subsequently makes predictions based on that representation. Currently, trajectory representation methods tend to project trajectory points to road networks by map matching and represent trajectories based on the representation of matched roads. However, precisely matching trajectories to roads is a challenge in ITS, as the matching precision is greatly affected by the quality of the trajectory. Meanwhile, since it is difficult to discern whether trajectory matching results are accurate or confounded, how to effectively utilize this type of uncertain geographic context information is also a challenge, which is defined as the Uncertain Geographic Context Problem (UGCoP) in geographic information science. Therefore, we propose a flexible strategy of subgraph learning, referred to as SLM, for predicting the next track point of vehicles. Specifically, a subgraph generation module is first proposed to extract topology contextual information of the roads around historical trajectory points. Secondly, a subgraph learning module is designed to learn rich spatial and temporal features from generated subgraphs. Finally, the extracted spatiotemporal features will be fed into a prediction module to predict the next track points of vehicles on road networks. Our model enables the effective utilization of uncertain geographic context information of trajectories on road networks while avoiding the error brought by map matching. Extensive experiments based on trajectory datasets in two different cities confirm the effectiveness of our approach.

A general modeling scheme for spatiotemporal DGGS with emphasis on encoding and operating multiscale time grids

AbstractOne of the basic scientific problems concerning geographic information science is how to rapidly organize, query, and compute spatiotemporal big data. The spatiotemporal discrete global grid system (DGGS) provides a homogenized discrete structure for processing multiscale and multitype spatiotemporal data. To date, most research in spatiotemporal DGGS has focused on spatial discretization while neglecting temporal discretization. Here, we propose a general modeling scheme for spatiotemporal DGGS with emphasis on encoding and operating multiscale time grids. We subdivide continuous time into multiscale temporal grids, which are then encoded as integers. Moreover, we designed integer code operations, including hierarchical traversal, neighborhood finding, and temporal relationship calculations. Compared to the multiscale time segment integer coding (MTSIC) approach, the proposed method resulted in 22% higher encoding efficiency, 10.92 times faster decoding, 2.81 times better parent code finding efficiency, 41% improved efficiency, 100% accuracy in finding children codes (compared to less than 100% with MTSIC), and a 62% enhancement in temporal relationship calculation efficiency. The application of querying spatiotemporal trajectory data validates the feasibility and practicality of substituting conventional string‐based time and floating‐point location coordinates with spatiotemporal integer codes to query data. The time encoding and operation methods proposed here indicate high efficiency, superior accuracy, and broad application prospects.

Leveraging Transfer Learning and U-Nets Method for Improved Gap Filling in Himawari Sea Surface Temperature Data Adjacent to Taiwan

Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis, particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model’s enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net’s potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science.

A deep neural network model for Chinese toponym matching with geographic pre-training model

ABSTRACT Multiple tasks within the field of geographical information retrieval and geographical information sciences necessitate toponym matching, which involves the challenge of aligning toponyms that share a common referent. The multiple string similarity approaches struggle when confronted with the complexities associated with unofficial and/or historical variants of identical toponyms. Also, current state-of-the-art approaches/tools to supervised machine learning rely on labeled samples, and they do not adequately address the intricacies of character replacements either from transliterations or historical shifts in linguistic and cultural norms. To address these issues, this paper proposes a novel matching approach that leverages a deep neural network model empowered by geographic language representation model, known as GeoBERT, which stands for geographic Bidirectional Encoder Representations from Transformers (BERT). This model harnesses the groundbreaking capabilities of the GeoBERT framework by extending a generalized Enhanced Sequential Inference Model architecture and integrating multiple features to enhance the accuracy and robustness of the toponym matching. We present a comprehensive evaluation of the proposed method’s performance using three extensive datasets. The findings clearly illustrate that our approach outperforms the individual similarity metrics used in previous studies.

Quantitative monitoring of pollution in Mitrovica Lake using empirical model and geographic information science & systems

ABSTRACT Continuous monitoring of water is crucial for assessing its quality. This paper aims to evaluate water quality in the Artificial Lake of Mitrovica, an area known for heavy metal pollution due to nearby industrial activities. To achieve this, we conducted a comprehensive year-long investigation of the lake, involving the assessment of water quality, spatial analysis, and pollutant evaluation at six different sampling locations, collected in April, June, and September to ensure consistent monitoring. We utilised atomic absorption spectroscopy (AAS) to measure concentrations of arsenic, chromium, copper, nickel, lead, zinc, and cadmium. Indices such as the Heavy Metal Pollution Index (HPI) and Metal Index (MI) were used to assess water quality. Additionally, spatial analysis was conducted using QGIS and Ordinary Kriging to visualise contamination levels across the study area. While many water parameters met international standards, certain sites, particularly those with lead concentrations (Pb2+), exceeded permissible limits, indicating areas of potential concern. This study offers valuable insights for policymaking at both local levels in Mitrovica as well as nationally in Kosova. The study overall emphasises the importance of addressing heavy metal pollution in the region.

Assessing publication trends in selected GIScience journals

This study examines recent publishing trends in geographic information science (GIScience) journals. The study considers citable items (research articles, reviews) in 24 selected journals, and assesses them for the period between 2018 and 2023. The study begins by providing an overview of GIScience journal publishing trends, including growth in absolute numbers and the proportion in which they disseminate research as open access (OA). The geographic footprint of GIScience authors and international collaboration are also explored. Journals and their impact, reputation, and perceived quality are assessed using common journal metrics, including impact factor, 5-year impact factor, CiteScore, source normalized impact per paper (SNIP), SCImago Journal Rank (SJR), immediacy index, article influence score and normalized Eigenfactor. A composite index consisting of all these metrics from 2022 is established. The paper finds that GIScience is increasingly disseminated as OA. There is evidence that the Global South is underrepresented in GIScience, which necessitates greater inclusion and support in these regions. Finally, the assessment of journal metrics helps researchers identify prominent GIScience journals for disseminating their work effectively. This paper contributes to the knowledge and understanding of recent publishing trends in GIScience, offering valuable insights to researchers, practitioners and journal editors.

A Novel Address-Matching Framework Based on Region Proposal

Geocoding is a fundamental component of geographic information science that plays a crucial role in various geographical studies and applications involving text data. Current mainstream geocoding methods fall into two categories: geodesic-grid prediction and address matching. However, the geodesic-grid-prediction method’s localization accuracy is hindered by the density of grid partitioning, struggling to strike a balance between prediction accuracy and grid density. Address-matching methods mainly focus on the semantics of query text. However, they tend to ignore keyword information that can be used to distinguish candidates and introduce potential interference, which reduces matching accuracy. Inspired by the human map-usage process, we propose a two-stage address-matching approach that integrates geodesic-grid prediction and text-matching models. Initially, a multi-level text-classification model is used to generate a retrieval region proposal for an input query text. Subsequently, we search for the most relevant point of interest (POI) within the region-proposal area using a semantics-based text-retrieval model. We evaluated the proposed method using POI data from the Beijing Chaoyang District. The experimental results indicate that the proposed method provides high address-matching accuracy, increasing Recall@1 by 0.55 to 1.56 percentage points and MRR@5 by 0.54 to 1.68 percentage points.

Regional Prediction of Crop Yield Success Rate in the Philippines using Geographic Trend Analysis Algorithm

Agriculture holds an important role in the economy of the Philippines by ensuring the food security of domestic products. It involves about 40 % of Filipino workers and it contributes an average of 20 percent to the Gross Domestic Product. Crop prediction in the Philippine’s agriculture is a big problem. At the present time, farmers are having a difficult time in choosing the right crops due to unnatural climate changes, soil type, rainfall, and other environmental factors. These can affect the economic life of farmers and can make them less familiar in forecasting future crops. This project aims to guide the farmers for sowing the reasonable crops by using geographic trend analysis algorithm. The findings from this study demonstrate the potential of the Geographic Trend Analysis Algorithm as a powerful tool for regional crop yield prediction. The success rate of each region will always equate to 100% in context with the set optimal yield prediction where the crop with highest percentage appears to be the dominant one. Irrigated palay (rice) demonstrates a greater rate of success across diverse Philippine regions when contrasted with rainfed or non-irrigated palay, as well as white and yellow corn. Additionally, the methodology employed by the researchers sets the groundwork for upcoming investigations in the domain of agricultural data analytics and geographic information science. This paves the way for a data-centered and sustainable strategy toward crop production in the Philippines.