Submit to Special Issue Submit Abstract to Special Issue Review for IJGI Propose a Special Issue

Journal Browser

► Journal Browser

Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).

Deadline for manuscript submissions: 30 September 2024 | Viewed by 21417

Share This Special Issue

Special Issue Editors

Prof. Dr. Christos Chalkias

E-Mail Website
Guest Editor

Department of Geography, Harokopio University, 70 El. Venizelou Str., 17671 Kallithea, Greece
Interests: GIScience; applied geography; spatial analysis; web cartography; health geography; GIS-based modelling
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Marinos Kavouras

E-Mail Website
Guest Editor

School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 9, H. Polytechniou Str., Zografos Campus, 15780 Athens, Greece
Interests: geospatial semantics; ontological research; geovisualization; cybercartography; spatial thinking/literacy

Dr. Margarita Kokla

E-Mail Website
Guest Editor

School of Rural, Surveying and Geoinformatics Engineering, National Technical University of Athens, 9, H. Polytechniou Str., Zografos Campus, 15780 Athens, Greece
Interests: geospatial semantics; geospatial ontologies; extraction of geospatial semantic information; geovisualization
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Mara Nikolaidou

E-Mail Website
Guest Editor

Department of Informatics and Telematics, Harokopio University of Athens, 9, Omirou Str., 17778 Athens, Tavros
Interests: digital libraries & repositories; system integration; knowledge management and ontologies; system modelling and simulation
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Over recent years, there has been a tremendous increase in digital information resources, including a significant amount of semi-structured data, such as XML files and metadata records, as well as unstructured data, such as scientific reports, news articles, social media, and historical archives. These data include a wealth of information about places, events, phenomena, geospatial concepts, and relations.

Semantic information extraction aims to make this information explicit, enabling computer systems to make sense of the content and facilitate knowledge discovery and organization. Ontological approaches have been acknowledged as crucial for modeling geospatial semantics effectively, addressing semantic inconsistencies, and grounding and linking different conceptualizations. By linking semi-structured and unstructured data to ontologies and knowledge bases, it is possible to enrich the original content with well-defined meaning and support semantic annotation and searches. Semantic analysis and visualization approaches play a significant role in further discovering immanent aspects of these data, such as the historical evolution of cities and the progression of spatiotemporal phenomena and events.

Lately, deep learning algorithms have been used to automatically extract patterns and relationships from large amounts of data, including unstructured and semi-structured data. By combining deep learning approaches with semantic web techniques, such as ontologies and linked data, more powerful and effective intelligent systems can be developed that can reason over large-scale knowledge bases and perform complex tasks, such as event detection, spatial relation extraction, geographic question answering, and knowledge analysis.

The Special Issue focuses on topics related, but not limited, to:

Geospatial knowledge graphs;
Ontology design and development;
User adoption and usability;
Reasoning and inference;
Semantic Web;
Knowledge exploration;
Semantic visualization;
Geographic question answering;
Semantic information extraction;
Semantic annotation and enrichment;
Semantic-based search;
Knowledge analytics.

Prof. Dr. Christos Chalkias
Prof. Dr. Marinos Kavouras
Dr. Margarita Kokla
Prof. Dr. Mara Nikolaidou
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. ISPRS International Journal of Geo-Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

geospatial semantics
semantic information extraction
geospatial knowledge
geospatial ontologies
geospatial knowledge graphs
semantic visualization
geographic question answering
deep learning
knowledge analytics
semantic annotation

Published Papers (14 papers)

Download All Papers

Research

Jump to: Other

16 pages, 2260 KiB

Open AccessArticle

Search Engine for Open Geospatial Consortium Web Services Improving Discoverability through Natural Language Processing-Based Processing and Ranking

by Elia Ferrari, Friedrich Striewski, Fiona Tiefenbacher, Pia Bereuter, David Oesch and Pasquale Di Donato

ISPRS Int. J. Geo-Inf. 2024, 13(4), 128; https://doi.org/10.3390/ijgi13040128 - 12 Apr 2024

Viewed by 454

Abstract

The improvement of search engines for geospatial data on the World Wide Web has been a subject of research, particularly concerning the challenges in discovering and utilizing geospatial web services. Despite the establishment of standards by the Open Geospatial Consortium (OGC), the implementation of these services varies significantly among providers, leading to issues in dataset discoverability and usability. This paper presents a proof of concept for a search engine tailored to geospatial services in Switzerland. It addresses challenges such as scraping data from various OGC web service providers, enhancing metadata quality through Natural Language Processing, and optimizing search functionality and ranking methods. Semantic augmentation techniques are applied to enhance metadata completeness and quality, which are stored in a high-performance NoSQL database for efficient data retrieval. The results show improvements in dataset discoverability and search relevance, with NLP-extracted information contributing significantly to ranking accuracy. Overall, the GeoHarvester proof of concept demonstrates the feasibility of improving the discoverability and usability of geospatial web services through advanced search engine techniques. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

20 pages, 5627 KiB

Open AccessArticle

Spatio-Temporal Evolution Characteristics and Influencing Factors of INGO Activities in Myanmar

by Sicong Liu, Yinbao Zhang, Jianzhong Liu, Xinjia Zhang and Xiaoshuang Huang

ISPRS Int. J. Geo-Inf. 2024, 13(4), 109; https://doi.org/10.3390/ijgi13040109 - 25 Mar 2024

Viewed by 675

Abstract

Myanmar is among the regions with the most frequent activities of International Non-Government Organizations (INGOs). Analyzing the spatio-temporal patterns of these activities holds crucial importance for optimizing organizational coordination and enhancing governmental oversight. This study focuses on the spatio-temporal evolution characteristics and influencing factors of INGO activities in Myanmar from 2010 to 2021, utilizing spatial autocorrelation and regression analysis. The results show that the number of INGOs in Myanmar has shown a gradual slowdown in growth trends, with the number of activities exhibiting a wave-like pattern, primarily driven by spontaneous activities of INGOs. The spatial distribution of INGO activities in Myanmar is concentrated in the southern plains, with the core located in Yangon, Naypyitaw, and Loilen. Furthermore, there is significant spatial polarization in the hotspot area of INGO acticities. The hotspots followed an evolutionary path from “South Myanmar” to “North Myanmar” and then back to “South Myanmar”. INGO activities in Myanmar are more focused on the local economic level, urbanization level, medical level, education level, and total population size, providing the necessary support and services for the local society and making up for the “government malfunction” and “market malfunction”. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

20 pages, 13777 KiB

Open AccessArticle

A Semantic-Spatial Aware Data Conflation Approach for Place Knowledge Graphs

by Lianlian He, Hao Li and Rui Zhang

ISPRS Int. J. Geo-Inf. 2024, 13(4), 106; https://doi.org/10.3390/ijgi13040106 - 22 Mar 2024

Viewed by 812

Abstract

Recent advances in knowledge graphs show great promise to link various data together to provide a semantic network. Place is an important part in the big picture of the knowledge graph since it serves as a powerful glue to link any data to its georeference. A key technical challenge in constructing knowledge graphs with location nodes as geographical references is the matching of place entities. Traditional methods typically rely on rule-based matching or machine-learning techniques to determine if two place names refer to the same location. However, these approaches are often limited in the feature selection of places for matching criteria, resulting in imbalanced consideration of spatial and semantic features. Deep feature-based methods such as deep learning methods show great promise for improved place data conflation. This paper introduces a Semantic-Spatial Aware Representation Learning Model (SSARLM) for Place Matching. SSARLM liberates the tedious manual feature extraction step inherent in traditional methods, enabling an end-to-end place entity matching pipeline. Furthermore, we introduce an embedding fusion module designed for the unified encoding of semantic and spatial information. In the experiment, we evaluate the approach to named places from Guangzhou and Shanghai cities in GeoNames, OpenStreetMap (OSM), and Baidu Map. The SSARLM is compared with several classical and commonly used binary classification machine learning models, and the state-of-the-art large language model, GPT-4. The results demonstrate the benefit of pre-trained models in data conflation of named places. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

21 pages, 4101 KiB

Open AccessArticle

Dynamic Graph Convolutional Network-Based Prediction of the Urban Grid-Level Taxi Demand–Supply Imbalance Using GPS Trajectories

by Haiqiang Yang and Zihan Li

ISPRS Int. J. Geo-Inf. 2024, 13(2), 34; https://doi.org/10.3390/ijgi13020034 - 24 Jan 2024

Viewed by 1309

Abstract

The objective imbalance between the taxi supply and demand exists in various areas of the city. Accurately predicting this imbalance helps taxi companies with dispatching, thereby increasing their profits and meeting the travel needs of residents. The application of Graph Convolutional Networks (GCNs) in traffic forecasting has inspired the development of a spatial–temporal model for grid-level prediction of the taxi demand–supply imbalance. However, spatial–temporal GCN prediction models conventionally capture only static inter-grid correlation features. This research aims to address the dynamic influences caused by taxi mobility and the variations of other transportation modes on the demand–supply dynamics between grids. To achieve this, we employ taxi trajectory data and develop a model that incorporates dynamic GCN and Gated Recurrent Units (GRUs) to predict grid-level imbalances. This model captures the dynamic inter-grid influences between neighboring grids in the spatial dimension. It also identifies trends and periodic changes in the temporal dimension. The validation of this model, using taxi trajectory data from Shenzhen city, indicates superior performance compared to classical time-series models and spatial–temporal GCN models. An ablation study is conducted to analyze the impact of various factors on the predictive accuracy. This study demonstrates the precision and applicability of the proposed model. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

33 pages, 17787 KiB

Open AccessArticle

Improving Three-Dimensional Building Segmentation on Three-Dimensional City Models through Simulated Data and Contextual Analysis for Building Extraction

by Frédéric Leroux, Mickaël Germain, Étienne Clabaut, Yacine Bouroubi and Tony St-Pierre

ISPRS Int. J. Geo-Inf. 2024, 13(1), 20; https://doi.org/10.3390/ijgi13010020 - 07 Jan 2024

Viewed by 1799

Abstract

Digital twins are increasingly gaining popularity as a method for simulating intricate natural and urban environments, with the precise segmentation of 3D objects playing an important role. This study focuses on developing a methodology for extracting buildings from textured 3D meshes, employing the PicassoNet-II semantic segmentation architecture. Additionally, we integrate Markov field-based contextual analysis for post-segmentation assessment and cluster analysis algorithms for building instantiation. Training a model to adapt to diverse datasets necessitates a substantial volume of annotated data, encompassing both real data from Quebec City, Canada, and simulated data from Evermotion and Unreal Engine. The experimental results indicate that incorporating simulated data improves segmentation accuracy, especially for under-represented features, and the DBSCAN algorithm proves effective in extracting isolated buildings. We further show that the model is highly sensible for the method of creating 3D meshes. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

29 pages, 14905 KiB

Open AccessArticle

Semantic Segmentation and Roof Reconstruction of Urban Buildings Based on LiDAR Point Clouds

by Xiaokai Sun, Baoyun Guo, Cailin Li, Na Sun, Yue Wang and Yukai Yao

ISPRS Int. J. Geo-Inf. 2024, 13(1), 19; https://doi.org/10.3390/ijgi13010019 - 05 Jan 2024

Viewed by 2114

Abstract

In urban point cloud scenarios, due to the diversity of different feature types, it becomes a primary challenge to effectively obtain point clouds of building categories from urban point clouds. Therefore, this paper proposes the Enhanced Local Feature Aggregation Semantic Segmentation Network (ELFA-RandLA-Net) based on RandLA-Net, which enables ELFA-RandLA-Net to perceive local details more efficiently by learning geometric and semantic features of urban feature point clouds to achieve end-to-end building category point cloud acquisition. Then, after extracting a single building using clustering, this paper utilizes the RANSAC algorithm to segment the single building point cloud into planes and automatically identifies the roof point cloud planes according to the point cloud cloth simulation filtering principle. Finally, to solve the problem of building roof reconstruction failure due to the lack of roof vertical plane data, we introduce the roof vertical plane inference method to ensure the accuracy of roof topology reconstruction. The experiments on semantic segmentation and building reconstruction of Dublin data show that the IoU value of semantic segmentation of buildings for the ELFA-RandLA-Net network is improved by 9.11% compared to RandLA-Net. Meanwhile, the proposed building reconstruction method outperforms the classical PolyFit method. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

18 pages, 3722 KiB

Open AccessArticle

Enhancing Crop Classification Accuracy through Synthetic SAR-Optical Data Generation Using Deep Learning

by Ali Mirzaei, Hossein Bagheri and Iman Khosravi

ISPRS Int. J. Geo-Inf. 2023, 12(11), 450; https://doi.org/10.3390/ijgi12110450 - 02 Nov 2023

Cited by 2 | Viewed by 1773

Abstract

Crop classification using remote sensing data has emerged as a prominent research area in recent decades. Studies have demonstrated that fusing synthetic aperture radar (SAR) and optical images can significantly enhance the accuracy of classification. However, a major challenge in this field is the limited availability of training data, which adversely affects the performance of classifiers. In agricultural regions, the dominant crops typically consist of one or two specific types, while other crops are scarce. Consequently, when collecting training samples to create a map of agricultural products, there is an abundance of samples from the dominant crops, forming the majority classes. Conversely, samples from other crops are scarce, representing the minority classes. Addressing this issue requires overcoming several challenges and weaknesses associated with the traditional data generation methods. These methods have been employed to tackle the imbalanced nature of training data. Nevertheless, they still face limitations in effectively handling minority classes. Overall, the issue of inadequate training data, particularly for minority classes, remains a hurdle that the traditional methods struggle to overcome. In this research, we explore the effectiveness of a conditional tabular generative adversarial network (CTGAN) as a synthetic data generation method based on a deep learning network, for addressing the challenge of limited training data for minority classes in crop classification using the fusion of SAR-optical data. Our findings demonstrate that the proposed method generates synthetic data with a higher quality, which can significantly increase the number of samples for minority classes, leading to a better performance of crop classifiers. For instance, according to the G-mean metric, we observed notable improvements in the performance of the XGBoost classifier of up to 5% for minority classes. Furthermore, the statistical characteristics of the synthetic data were similar to real data, demonstrating the fidelity of the generated samples. Thus, CTGAN can be employed as a solution for addressing the scarcity of training data for minority classes in crop classification using SAR–optical data. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

18 pages, 5667 KiB

Open AccessArticle

Automated Generation of Room Usage Semantics from Point Cloud Data

by Guoray Cai and Yimu Pan

ISPRS Int. J. Geo-Inf. 2023, 12(10), 427; https://doi.org/10.3390/ijgi12100427 - 17 Oct 2023

Viewed by 1381

Abstract

Room usage semantics in models of large indoor environments such as public buildings and business complex are critical in many practical applications, such as health and safety regulations, compliance, and emergency response. Existing models such as IndoorGML have very limited semantic information at room level, and it remains difficult to capture semantic knowledge of rooms in an efficient way. In this paper, we formulate the task of generating rooms usage semantics as a special case of room classification problems. Although methods for room classification tasks have been developed in the field of social robotics studies and indoor maps, they do not deal with room usage and occupancy aspects of semantics, and they ignore the value of furniture objects in understanding room usage. We propose a method for generating room usage semantics based on the spatial configuration of room objects (e.g., furniture, walls, windows, doors). This method uses deep learning architecture to support a room usage classifier that can learn spatial configuration features directly from semantically labelled point cloud (SLPC) data that represent room scenes with furniture objects in place. We experimentally assessed the capacity of our method in classifying rooms in office buildings using the Stanford 3D (S3DIS) dataset. The results showed that our method was able to achieve an overall accuracy of 91% on top-level room categories (e.g., offices, conference rooms, lounges, storage) and above 97% accuracy in recognizing offices and conference rooms. We further show that our classifier can distinguish fine-grained categories of of offices and conference rooms such as shared offices, single-occupancy offices, large conference rooms, and small conference rooms, with comparable intelligence to human coders. In general, our method performs better on rooms with a richer variety of objects than on rooms with few or no furniture objects. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

22 pages, 56589 KiB

Open AccessArticle

Target Search for Joint Local and High-Level Semantic Information Based on Image Preprocessing Enhancement in Indoor Low-Light Environments

by Huapeng Tang, Danyang Qin, Jiaqiang Yang, Haoze Bie, Yue Li, Yong Zhu and Lin Ma

ISPRS Int. J. Geo-Inf. 2023, 12(10), 400; https://doi.org/10.3390/ijgi12100400 - 30 Sep 2023

Viewed by 1095

Abstract

In indoor low-light environments, the lack of light makes the captured images often suffer from quality degradation problems, including missing features in dark areas, noise interference, low brightness, and low contrast. Therefore, the feature extraction algorithms are unable to extract the feature information contained in the images accurately, thereby hindering the subsequent target search task in this environment and making it difficult to determine the location information of the target. Aiming at this problem, a joint local and high-level semantic information (JLHS) target search method is proposed based on joint bilateral filtering and camera response model (JBCRM) image preprocessing enhancement. The JBCRM method improves the image quality by highlighting the dark region features and removing the noise interference in order to solve the problem of the difficult extraction of feature points in low-light images, thus providing better visual data for subsequent target search tasks. The JLHS method increases the feature matching accuracy between the target image and the offline database image by combining local and high-level semantic information to characterize the image content, thereby boosting the accuracy of the target search. Experiments show that, compared with the existing image-enhancement methods, the PSNR of the JBCRM method is increased by 34.24% at the highest and 2.61% at the lowest. The SSIM increased by 63.64% at most and increased by 12.50% at least. The Laplacian operator increased by 54.47% at most and 3.49% at least. When the mainstream feature extraction techniques, SIFT, ORB, AKAZE, and BRISK, are utilized, the number of feature points in the JBCRM-enhanced images are improved by a minimum of 20.51% and a maximum of 303.44% over the original low-light images. Compared with other target search methods, the average search error of the JLHS method is only 9.8 cm, which is 91.90% lower than the histogram-based search method. Meanwhile, the average search error is reduced by 18.33% compared to the VGG16-based target search method. As a result, the method proposed in this paper significantly improves the accuracy of the target search in low-light environments, thus broadening the application scenarios of target search in indoor environments, and providing an effective solution for accurately determining the location of the target in geospatial space. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

23 pages, 2619 KiB

Open AccessArticle

ChineseCTRE: A Model for Geographical Named Entity Recognition and Correction Based on Deep Neural Networks and the BERT Model

by Wei Zhang, Jingtao Meng, Jianhua Wan, Chengkun Zhang, Jiajun Zhang, Yuanyuan Wang, Liuchang Xu and Fei Li

ISPRS Int. J. Geo-Inf. 2023, 12(10), 394; https://doi.org/10.3390/ijgi12100394 - 27 Sep 2023

Cited by 1 | Viewed by 1400

Abstract

Social media is widely used to share real-time information and report accidents during natural disasters. Named entity recognition (NER) is a fundamental task of geospatial information applications that aims to extract location names from natural language text. As a result, the identification of location names from social media information has gradually become a demand. Named entity correction (NEC), as a complementary task of NER, plays a crucial role in ensuring the accuracy of location names and further improving the accuracy of NER. Despite numerous methods having been adopted for NER, including text statistics-based and deep learning-based methods, there has been limited research on NEC. To address this gap, we propose the CTRE model, which is a geospatial named entity recognition and correction model based on the BERT model framework. Our approach enhances the BERT model by introducing incremental pre-training in the pre-training phase, significantly improving the model’s recognition accuracy. Subsequently, we adopt the pre-training fine-tuning mode of the BERT base model and extend the fine-tuning process, incorporating a neural network framework to construct the geospatial named entity recognition model and geospatial named entity correction model, respectively. The BERT model utilizes data augmentation of VGI (volunteered geographic information) data and social media data for incremental pre-training, leading to an enhancement in the model accuracy from 85% to 87%. The F1 score of the geospatial named entity recognition model reaches an impressive 0.9045, while the precision of the geospatial named entity correction model achieves 0.9765. The experimental results robustly demonstrate the effectiveness of our proposed CTRE model, providing a reference for subsequent research on location names. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

19 pages, 4224 KiB

Open AccessArticle

Profiling Public Transit Passenger Mobility Using Adversarial Learning

by Yicong Li, Tong Zhang, Xiaofei Lv, Yingxi Lu and Wangshu Wang

ISPRS Int. J. Geo-Inf. 2023, 12(8), 338; https://doi.org/10.3390/ijgi12080338 - 12 Aug 2023

Viewed by 836

Abstract

It is important to capture passengers’ public transit behavior and their mobility to create profiles, which are critical for analyzing human activities, understanding the social and economic structure of cities, improving public transportation, assisting urban planning, and promoting smart cities. In this paper, we develop a generative adversarial machine learning network to characterize the temporal and spatial mobility behavior of public transit passengers, based on massive smart card data and road network data. The Apriori algorithm is extended with spatio-temporal constraints to extract frequent transit mobility patterns of individual passengers based on a reconstructed personal trip dataset. This individual-level pattern information is used to construct personalized feature vectors. For regular and frequent public transit passengers, we identify similar transit mobility groups using spatio-temporal constraints to construct a group feature vector. We develop a generative adversarial network to embed public transit mobility of passengers. The proposed model’s generator consists of an auto-encoder, which extracts a low-dimensional and compact representation of passenger behavior, and a pre-trained sub-generator containing generalization features of public transit passengers. Shenzhen City is taken as the study area in this paper, and experiments were carried out based on smart card data, road network data, and bus GPS data. Clustering analysis of embedding vector representation and estimation of the top K transit destinations were conducted, verifying that the proposed method can profile passenger transit mobility in a comprehensive and compact manner. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

22 pages, 50394 KiB

Open AccessArticle

Multi-Supervised Feature Fusion Attention Network for Clouds and Shadows Detection

by Huiwen Ji, Min Xia, Dongsheng Zhang and Haifeng Lin

ISPRS Int. J. Geo-Inf. 2023, 12(6), 247; https://doi.org/10.3390/ijgi12060247 - 18 Jun 2023

Cited by 11 | Viewed by 1252

Abstract

Cloud and cloud shadow detection are essential in remote sensing imagery applications. Few semantic segmentation models were designed specifically for clouds and their shadows. Based on the visual and distribution characteristics of clouds and their shadows in remote sensing imagery, this paper provides a multi-supervised feature fusion attention network. We design a multi-scale feature fusion block (FFB) for the problems caused by the complex distribution and irregular boundaries of clouds and shadows. The block consists of a fusion convolution block (FCB), a channel attention block (CAB), and a spatial attention block (SPA). By multi-scale convolution, FCB reduces excessive semantic differences between shallow and deep feature maps. CAB focuses on global and local features through multi-scale channel attention. Meanwhile, it fuses deep and shallow feature maps with non-linear weighting to optimize fusion performance. SPA focuses on task-relevant areas through spatial attention. With the three blocks above, FCB alleviates the difficulties of fusing multi-scale features. Additionally, it makes the network resistant to background interference while optimizing boundary detection. Our proposed model designs a class feature attention block (CFAB) to increase the robustness of cloud detection. The network achieves good performance on the self-made cloud and shadow dataset. This dataset is taken from Google Earth and contains remote sensing imagery from several satellites. The proposed model achieved a mean intersection over union (MIoU) of 94.10% on our dataset, which is 0.44% higher than the other models. Moreover, it shows high generalization capability due to its superior prediction results on HRC_WHU and SPARCS datasets. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

18 pages, 5387 KiB

Open AccessArticle

Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation

by Rokaya Eltehewy, Ahmed Abouelfarag and Sherine Nagy Saleh

ISPRS Int. J. Geo-Inf. 2023, 12(6), 245; https://doi.org/10.3390/ijgi12060245 - 17 Jun 2023

Cited by 3 | Viewed by 1877

Abstract

Rapid damage identification and classification in disastrous situations and natural disasters are crucial for efficiently directing aid and resources. With the development of deep learning techniques and the availability of imagery content on social media platforms, extensive research has focused on damage assessment. Through the use of geospatial data related to such incidents, the visual characteristics of these images can quickly determine the safety situation in the region. However, training accurate disaster classification models has proven to be challenging due to the lack of labeled imagery data in this domain. This paper proposes a disaster classification framework, which combines a set of synthesized diverse disaster images generated using generative adversarial networks (GANs) and domain-specific fine-tuning of a deep convolutional neural network (CNN)-based model. The proposed model utilizes bootstrap aggregating (bagging) to further stabilize the target predictions. Since past work in this domain mainly suffers from limited data resources, a sample dataset that highlights the issue of imbalanced classification of multiple natural disasters was constructed and augmented. Qualitative and quantitative experiments show the validity of the data augmentation method employed in producing a balanced dataset. Further experiments with various evaluation metrics verified the proposed framework’s accuracy and generalization ability across different classes for the task of disaster classification in comparison to other state-of-the-art techniques. Furthermore, the framework outperforms the other models by an average validation accuracy of 11%. These results provide a deep learning solution for real-time disaster monitoring systems to mitigate the loss of lives and properties. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures

Figure 1

Other

Jump to: Research

10 pages, 1472 KiB

Open AccessBrief Report

Is ChatGPT a Good Geospatial Data Analyst? Exploring the Integration of Natural Language into Structured Query Language within a Spatial Database

by Yongyao Jiang and Chaowei Yang

ISPRS Int. J. Geo-Inf. 2024, 13(1), 26; https://doi.org/10.3390/ijgi13010026 - 10 Jan 2024

Viewed by 2483

Abstract

With recent advancements, large language models (LLMs) such as ChatGPT and Bard have shown the potential to disrupt many industries, from customer service to healthcare. Traditionally, humans interact with geospatial data through software (e.g., ArcGIS 10.3) and programming languages (e.g., Python). As a pioneer study, we explore the possibility of using an LLM as an interface to interact with geospatial datasets through natural language. To achieve this, we also propose a framework to (1) train an LLM to understand the datasets, (2) generate geospatial SQL queries based on a natural language question, (3) send the SQL query to the backend database, (4) parse the database response back to human language. As a proof of concept, a case study was conducted on real-world data to evaluate its performance on various queries. The results show that LLMs can be accurate in generating SQL code for most cases, including spatial joins, although there is still room for improvement. As all geospatial data can be stored in a spatial database, we hope that this framework can serve as a proxy to improve the efficiency of spatial data analyses and unlock the possibility of automated geospatial analytics. Full article

(This article belongs to the Special Issue Unlocking the Power of Geospatial Data: Semantic Information Extraction, Ontology Engineering, and Deep Learning for Knowledge Discovery)

► Show Figures