Geographic Information Extraction and Retrieval

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

Deadline for manuscript submissions: closed (30 April 2020) | Viewed by 18203

Special Issue Editors


E-Mail Website
Guest Editor
LIUPPA lab., University of Pau and Pays Adour, 64000 Pau, France
Interests: geographic information sciences; extraction of spatial, temporal, and thematic properties; named entity resolution; handling context and semantics

E-Mail Website
Guest Editor
Instituto Superior Técnico and INESC-ID, University of Lisbon, Lisbon, Portugal
Interests: geographic text analysis; geographic information sciences; applied data science and machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Increasing amounts of unstructured data, in the form of text or multimedia contents, are being made available for indexing, retrieval, and analysis. These include various kinds of documents, such as news articles, scientific publications, or even informal messages on social-media platforms like Twitter. Most of these data also contain geospatial references, associating topics, things, or events to locations. However, the effective analysis and use of these data involves many important technical and methodological challenges.

Handling symbolic spatial, temporal, and topical references (e.g., associations to place names through natural language qualifiers such as “near”) involves a fusion of information retrieval and content analysis methods. The analysis of unstructured contents is generally supported by multimedia processing and natural language processing methods. On the other hand, methods from the toolset of geographical information systems can analyze numeric representations of spatial and/or temporal information (e.g., georeferenced coordinates). In recent years, the combination of the aforementioned areas/techniques has already resulted in several advancements related to the analysis of geospatial references in unstructured contents. However, several challenges and opportunities for improvement still persist, particularly in the context of recent developments in artificial intelligence and machine learning.

For this Special Issue, we invite the community of professionals and researchers interested in the fields of geographic information extraction, retrieval, and related applications to submit their work. The scope of submissions includes but is not limited to, the following topics:

  1. Corpus collection, preparation, and annotation:
    1. Identification and annotation of resources (e.g., text collections, images, videos, and associated metadata);
    2. Construction, modeling, and the use of ontologies, gazetteers, and thesauri for geographic information extraction and retrieval;
    3. Data models and representation schema for spatial and spatiotemporal (unstructured/semistructured) data;
    4. Corpus linguistics methods for geographical text analysis.
  2. Geographic information extraction, indexing, and retrieval:
    1. Analysis of geospatial language and geospatial semantics;
    2. Geoparsing and geocoding unstructured contents (e.g., text documents, images, user queries, etc.);
    3. Spatio-textual data indexing and ranked retrieval methods;
    4. User interfaces for geographic information extraction and retrieval.
  3. Applications for geographic information extraction and retrieval:
    1. Industrial applications (e.g., tourism, media access and retrieval, etc.);
    2. Research applications (e.g., digital humanities, computational social sciences, etc.);
    3. Gold standards and in-domain evaluation.
Associate Prof. Christian Sallaberry


Prof. Bruno Martins
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.

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

20 pages, 2471 KiB  
Article
Semantic Integration of Raster Data for Earth Observation: An RDF Dataset of Territorial Unit Versions with their Land Cover
by Ba-Huy Tran, Nathalie Aussenac-Gilles, Catherine Comparot and Cassia Trojahn
ISPRS Int. J. Geo-Inf. 2020, 9(9), 503; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9090503 - 21 Aug 2020
Cited by 14 | Viewed by 3199
Abstract
Semantic technologies are at the core of Earth Observation (EO) data integration, by providing an infrastructure based on RDF representation and ontologies. Because many EO data come in raster files, this paper addresses the integration of data calculated from rasters as a way [...] Read more.
Semantic technologies are at the core of Earth Observation (EO) data integration, by providing an infrastructure based on RDF representation and ontologies. Because many EO data come in raster files, this paper addresses the integration of data calculated from rasters as a way of qualifying geographic units through their spatio-temporal features. We propose (i) a modular ontology that contributes to the semantic and homogeneous description of spatio-temporal data to qualify predefined areas; (ii) a Semantic Extraction, Transformation, and Load (ETL) process, allowing us to extract data from rasters and to link them to the corresponding spatio-temporal units and features; and (iii) a resulting dataset that is published as an RDF triplestore, exposed through a SPARQL endpoint, and exploited by a semantic interface. We illustrate the integration process with raster files providing the land cover of a specific French winery geographic area, its administrative units, and their land registers over different periods. The results have been evaluated with regards to three use-cases exploiting these EO data: integration of time series observations; EO process guidance; and data cross-comparison. Full article
(This article belongs to the Special Issue Geographic Information Extraction and Retrieval)
Show Figures

Figure 1

23 pages, 2241 KiB  
Article
POI Mining for Land Use Classification: A Case Study
by Renato Andrade, Ana Alves and Carlos Bento
ISPRS Int. J. Geo-Inf. 2020, 9(9), 493; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9090493 - 20 Aug 2020
Cited by 52 | Viewed by 5160
Abstract
The modern planning and management of urban spaces is an essential topic for smart cities and depends on up-to-date and reliable information on land use and the functional roles of the places that integrate urban areas. In the last few years, driven by [...] Read more.
The modern planning and management of urban spaces is an essential topic for smart cities and depends on up-to-date and reliable information on land use and the functional roles of the places that integrate urban areas. In the last few years, driven by the increased availability of geo-referenced data from social media, embedded sensors, and remote sensing images, various techniques have become popular for land use analysis. In this paper, we first highlight and discuss the different data types and methods usually adopted in this context, as well as their purposes. Then, based on a systematic state-of-the-art study, we focused on exploring the potential of points of interest (POIs) for land use classification, as one of the most common categories of crowdsourced data. We developed an application to automatically collect POIs for the study area, creating a dataset that was used to generate a large number of features. We used a ranking technique to select, among them, the most suitable features for classifying land use. As ground truth data, we used CORINE Land Cover (CLC), which is a solid and reliable dataset available for the whole European territory. It was used an artificial neural network (ANN) in different scenarios and our results reveal values of more than 90% for the accuracy and F-score in one experiment performed. Our analysis suggests that POI data have promising potential to characterize geographic spaces. The work described here aims to provide an alternative to the current methodologies for land use and land cover (LULC) classification, which are usually time-consuming and depend on expensive data types. Full article
(This article belongs to the Special Issue Geographic Information Extraction and Retrieval)
Show Figures

Figure 1

13 pages, 1428 KiB  
Article
Map Metadata: the Basis of the Retrieval System of Digital Collections
by Marta Kuźma and Hans Bauer
ISPRS Int. J. Geo-Inf. 2020, 9(7), 444; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9070444 - 17 Jul 2020
Cited by 3 | Viewed by 2812
Abstract
The article presents research on the evaluation of hidden map metadata. A hidden map is a map being part of a book that illustrates certain facts described in the book (e.g., military campaigns, political processes, migrations). The evaluation regards their completeness. Metadata completeness [...] Read more.
The article presents research on the evaluation of hidden map metadata. A hidden map is a map being part of a book that illustrates certain facts described in the book (e.g., military campaigns, political processes, migrations). The evaluation regards their completeness. Metadata completeness is the degree to which objects are described using all metadata elements. The analysis took into account the metadata of archival maps accessed via the GeoPortOst geoportal. Over 3000 hidden maps from the period 1572–2018 were analyzed, and the map set was divided into 8 collections. The main purpose of cartographers and librarians is to facilitate understanding of the relationship between individual information (librarians) and spatial data (cartographers). To this end, the research focused on the kind of information about old maps that should be stored in metadata to describe them in terms of space, time, content and context so as to increase their interoperability. The following metadata were taken into account in the assessment: title of content, type of content, date, date range, rights, language, subject, distribution format, geographic location, scale of map, reference system, mapping methods, map format, and source materials used to develop the map. The completeness of individual metadata as well as the completeness of metadata for individual collections was assessed. Finally, good practices of individual collections and metadata that could increase the interoperability of the entire collection were identified. The evaluation enables the owners to show the strengths and weaknesses of a given collection in a quick and easy way. Full article
(This article belongs to the Special Issue Geographic Information Extraction and Retrieval)
Show Figures

Figure 1

18 pages, 3108 KiB  
Article
DKP: A Geographic Data and Knowledge Platform for Supporting Climate Service Design
by Martine Collard, Erick Stattner, Wilfried Segretier, Reynald Eugenie and Nathan Jadoul
ISPRS Int. J. Geo-Inf. 2020, 9(5), 337; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9050337 - 22 May 2020
Viewed by 2615
Abstract
This article falls within the related areas of climate services and geographic information. We present the architecture and features of the Data and Knowledge Platform (DKP), innovative geographic software that was designed as support for climate-service elaboration in the context of change on [...] Read more.
This article falls within the related areas of climate services and geographic information. We present the architecture and features of the Data and Knowledge Platform (DKP), innovative geographic software that was designed as support for climate-service elaboration in the context of change on given geographic areas. It is intended for a community of stakeholders who need visual and geographic tools to design services improving the resilience of society regarding specific local issues. The platform provides different functions for seeking all available geographic information. Anticipating large volumes of data that are to be stored, we opted for a NoSQL database rather than a textual repository. In this paper, we present the different features of the platform and its ability to support visual climate service co-design, and we illustrate our statement with an example. Full article
(This article belongs to the Special Issue Geographic Information Extraction and Retrieval)
Show Figures

Figure 1

22 pages, 6403 KiB  
Article
Similarity Retention Loss (SRL) Based on Deep Metric Learning for Remote Sensing Image Retrieval
by Hongwei Zhao, Lin Yuan and Haoyu Zhao
ISPRS Int. J. Geo-Inf. 2020, 9(2), 61; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9020061 - 21 Jan 2020
Cited by 4 | Viewed by 3075
Abstract
Recently, with the rapid growth of the number of datasets with remote sensing images, it is urgent to propose an effective image retrieval method to manage and use such image data. In this paper, we propose a deep metric learning strategy based on [...] Read more.
Recently, with the rapid growth of the number of datasets with remote sensing images, it is urgent to propose an effective image retrieval method to manage and use such image data. In this paper, we propose a deep metric learning strategy based on Similarity Retention Loss (SRL) for content-based remote sensing image retrieval. We have improved the current metric learning methods from the following aspects—sample mining, network model structure and metric loss function. On the basis of redefining the hard samples and easy samples, we mine the positive and negative samples according to the size and spatial distribution of the dataset classes. At the same time, Similarity Retention Loss is proposed and the ratio of easy samples to hard samples in the class is used to assign dynamic weights to the hard samples selected in the experiment to learn the sample structure characteristics within the class. For negative samples, different weights are set based on the spatial distribution of the surrounding samples to maintain the consistency of similar structures among classes. Finally, we conduct a large number of comprehensive experiments on two remote sensing datasets with the fine-tuning network. The experiment results show that the method used in this paper achieves the state-of-the-art performance. Full article
(This article belongs to the Special Issue Geographic Information Extraction and Retrieval)
Show Figures

Figure 1

Back to TopTop