Geocomputation and Artificial Intelligence for Mapping

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Geomatics geomatics	-	-	2021	22.1 Days	CHF 1000
ISPRS International Journal of Geo-Information ijgi	2.8	6.9	2012	35.8 Days	CHF 1900
Remote Sensing remotesensing	4.2	8.3	2009	23.9 Days	CHF 2700

18 pages, 5055 KiB

Open AccessArticle

Investigating the Performance of Open-Vocabulary Classification Algorithms for Pathway and Surface Material Detection in Urban Environments

by Kauê de Moraes Vestena, Silvana Phillipi Camboim, Maria Antonia Brovelli and Daniel Rodrigues dos Santos

ISPRS Int. J. Geo-Inf. 2024, 13(12), 422; https://doi.org/10.3390/ijgi13120422 - 24 Nov 2024

Viewed by 1150

Abstract

Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can [...] Read more.

Mapping pavement types, especially in sidewalks, is essential for urban planning and mobility studies. Identifying pavement materials is a key factor in assessing mobility, such as walkability and wheelchair usability. However, satellite imagery in this scenario is limited, and in situ mapping can be costly. A promising solution is to extract such geospatial features from street-level imagery. This study explores using open-vocabulary classification algorithms to segment and identify pavement types and surface materials in this scenario. Our approach uses large language models (LLMs) to improve the accuracy of classifying different pavement types. The methodology involves two experiments: the first uses free prompting with random street-view images, employing Grounding Dino and SAM algorithms to assess performance across categories. The second experiment evaluates standardized pavement classification using the Deep Pavements dataset and a fine-tuned CLIP algorithm optimized for detecting OSM-compliant pavement categories. The study presents open resources, such as the Deep Pavements dataset and a fine-tuned CLIP-based model, demonstrating a significant improvement in the true positive rate (TPR) from 56.04% to 93.5%. Our findings highlight both the potential and limitations of current open-vocabulary algorithms and emphasize the importance of diverse training datasets. This study advances urban feature mapping by offering a more intuitive and accurate approach to geospatial data extraction, enhancing urban accessibility and mobility mapping. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

21 pages, 7459 KiB

Open AccessArticle

Deep Learning for Urban Tree Canopy Coverage Analysis: A Comparison and Case Study

by Grayson R. Morgan, Danny Zlotnick, Luke North, Cade Smith and Lane Stevenson

Geomatics 2024, 4(4), 412-432; https://doi.org/10.3390/geomatics4040022 - 14 Nov 2024

Viewed by 1662

Abstract

Urban tree canopy (UTC) coverage, or area, is an important metric for monitoring changes in UTC over large areas within a municipality. Several methods have been used to obtain these data, but remote sensing image classification is one of the fastest and most [...] Read more.

Urban tree canopy (UTC) coverage, or area, is an important metric for monitoring changes in UTC over large areas within a municipality. Several methods have been used to obtain these data, but remote sensing image classification is one of the fastest and most reliable over large areas. However, most studies have tested only one or two classification methods to accomplish this while using costly satellite imagery or LiDAR data. This study seeks to compare three urban tree canopy cover classifiers by testing a deep learning U-Net convolutional neural network (CNN), support vector machine learning classifier (SVM) and a random forests machine learning classifier (RF) on cost-free 2012 aerial imagery over a small southern USA city and midsize, growing southern USA city. The results of the experiment are then used to decide the best classifier and apply it to more recent aerial imagery to determine canopy changes over a 10-year period. The changes are subsequently compared visually and statistically with recent urban heat maps derived from thermal Landsat 9 satellite data to compare the means of temperatures within areas of UTC loss and no change. The U-Net CNN classifier proved to provide the best overall accuracy for both cities (89.8% and 91.4%), while also requiring the most training and classification time. When compared spatially with city heat maps, city periphery regions were most impacted by substantial changes in UTC area as cities grow and the outer regions get warmer. Furthermore, areas of UTC loss had higher temperatures than those areas with no canopy change. The broader impacts of this study reach the urban forestry managers at the local, state/province, and national levels as they seek to provide data-driven decisions for policy makers. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

26 pages, 31855 KiB

Open AccessArticle

Road Network Intelligent Selection Method Based on Heterogeneous Graph Attention Neural Network

by Haohua Zheng, Jianchen Zhang, Heying Li, Guangxia Wang, Jianzhong Guo and Jiayao Wang

ISPRS Int. J. Geo-Inf. 2024, 13(9), 300; https://doi.org/10.3390/ijgi13090300 - 25 Aug 2024

Cited by 2 | Viewed by 1262

Abstract

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research toward the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. [...] Read more.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research toward the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where the feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another for extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we use a set of metrics considering both quantitative and qualitative aspects of the road network. On road types with similar sample sizes, the HAN model outperforms other models in both transductive and inductive tasks. Its accuracy (ACC) is higher by 1.62% and 0.67%, and its F1-score is higher by 1.43% and 0.81%, respectively. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

21 pages, 13694 KiB

Open AccessArticle

An Improved ANN-Based Label Placement Method Considering Surrounding Features for Schematic Metro Maps

by Zhiwei Wu, Tian Lan, Chenzhen Sun, Donglin Cheng, Xing Shi, Meisheng Chen and Guangjun Zeng

ISPRS Int. J. Geo-Inf. 2024, 13(8), 294; https://doi.org/10.3390/ijgi13080294 - 19 Aug 2024

Cited by 1 | Viewed by 1070

Abstract

On schematic metro maps, high-quality label placement is helpful to passengers performing route planning and orientation tasks. It has been reported that the artificial neural network (ANN) has the potential to place labels with learned labeling knowledge. However, the previous ANN-based method only [...] Read more.

On schematic metro maps, high-quality label placement is helpful to passengers performing route planning and orientation tasks. It has been reported that the artificial neural network (ANN) has the potential to place labels with learned labeling knowledge. However, the previous ANN-based method only considered the effects of station points and their connected edges. Indeed, unconnected but surrounding features (points, edges, and labels) also significantly affect the quality of label placement. To address this, we have proposed an improved method. The relations between label positions and both connected and surrounding features are first modeled based on labeling natural intelligence (i.e., the experience, knowledge, and rules of labeling established by cartographers). Then, ANN is employed to learn such relations. Quantitative evaluations show that our method reaches lower percentages of label–point overlap (0.00%), label–edge overlap (4.12%), and label–label overlap (20.58%) compared to the benchmark (4.17%, 14.29%, and 35.11%, respectively). On the other hand, our method effectively avoids ambiguous labels and ensures labels from the same line are placed on the same side. Qualitative evaluations show that approximately 75% of users prefer our results. This novel method has the potential to advance the automated generation of schematic metro maps. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

27 pages, 2909 KiB

Open AccessArticle

Extracting Geoscientific Dataset Names from the Literature Based on the Hierarchical Temporal Memory Model

by Kai Wu, Zugang Chen, Xinqian Wu, Guoqing Li, Jing Li, Shaohua Wang, Haodong Wang and Hang Feng

ISPRS Int. J. Geo-Inf. 2024, 13(7), 260; https://doi.org/10.3390/ijgi13070260 - 21 Jul 2024

Viewed by 1584

Abstract

Extracting geoscientific dataset names from the literature is crucial for building a literature–data association network, which can help readers access the data quickly through the Internet. However, the existing named-entity extraction methods have low accuracy in extracting geoscientific dataset names from unstructured text [...] Read more.

Extracting geoscientific dataset names from the literature is crucial for building a literature–data association network, which can help readers access the data quickly through the Internet. However, the existing named-entity extraction methods have low accuracy in extracting geoscientific dataset names from unstructured text because geoscientific dataset names are a complex combination of multiple elements, such as geospatial coverage, temporal coverage, scale or resolution, theme content, and version. This paper proposes a new method based on the hierarchical temporal memory (HTM) model, a brain-inspired neural network with superior performance in high-level cognitive tasks, to accurately extract geoscientific dataset names from unstructured text. First, a word-encoding method based on the Unicode values of characters for the HTM model was proposed. Then, over 12,000 dataset names were collected from geoscience data-sharing websites and encoded into binary vectors to train the HTM model. We conceived a new classifier scheme for the HTM model that decodes the predictive vector for the encoder of the next word so that the similarity of the encoders of the predictive next word and the real next word can be computed. If the similarity is greater than a specified threshold, the real next word can be regarded as part of the name, and a successive word set forms the full geoscientific dataset name. We used the trained HTM model to extract geoscientific dataset names from 100 papers. Our method achieved an F1-score of 0.727, outperforming the GPT-4- and Claude-3-based few-shot learning (FSL) method, with F1-scores of 0.698 and 0.72, respectively. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

24 pages, 13627 KiB

Open AccessArticle

Enhancing Place Emotion Analysis with Multi-View Emotion Recognition from Geo-Tagged Photos: A Global Tourist Attraction Perspective

by Yu Wang, Shunping Zhou, Qingfeng Guan, Fang Fang, Ni Yang, Kanglin Li and Yuanyuan Liu

ISPRS Int. J. Geo-Inf. 2024, 13(7), 256; https://doi.org/10.3390/ijgi13070256 - 16 Jul 2024

Cited by 1 | Viewed by 1161

Abstract

User-generated geo-tagged photos (UGPs) have emerged as a valuable tool for analyzing large-scale tourist place emotions with unprecedented detail. This process involves extracting and analyzing human emotions associated with specific locations. However, previous studies have been limited to analyzing individual faces in the [...] Read more.

User-generated geo-tagged photos (UGPs) have emerged as a valuable tool for analyzing large-scale tourist place emotions with unprecedented detail. This process involves extracting and analyzing human emotions associated with specific locations. However, previous studies have been limited to analyzing individual faces in the UGPs. This approach falls short of representing the contextual scene characteristics, such as environmental elements and overall scene context, which may contain implicit emotional knowledge. To address this issue, we propose an innovative computational framework for global tourist place emotion analysis leveraging UGPs. Specifically, we first introduce a Multi-view Graph Fusion Network (M-GFN) to effectively recognize multi-view emotions from UGPs, considering crowd emotions and scene implicit sentiment. After that, we designed an attraction-specific emotion index (AEI) to quantitatively measure place emotions based on the identified multi-view emotions at various tourist attractions with place types. Complementing the AEI, we employ the emotion intensity index (EII) and Pearson correlation coefficient (PCC) to deepen the exploration of the association between attraction types and place emotions. The synergy of AEI, EII, and PCC allows comprehensive attraction-specific place emotion extraction, enhancing the overall quality of tourist place emotion analysis. Extensive experiments demonstrate that our framework enhances existing place emotion analysis methods, and the M-GFN outperforms state-of-the-art emotion recognition methods. Our framework can be adapted for various geo-emotion analysis tasks, like recognizing and regulating workplace emotions, underscoring the intrinsic link between emotions and geographic contexts. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

19 pages, 4490 KiB

Open AccessArticle

An Integrated Framework for Landscape Indices’ Calculation with Raster–Vector Integration and Its Application Based on QGIS

by Yaqi Huang, Minrui Zheng, Tianle Li, Fei Xiao and Xinqi Zheng

ISPRS Int. J. Geo-Inf. 2024, 13(7), 242; https://doi.org/10.3390/ijgi13070242 - 6 Jul 2024

Cited by 1 | Viewed by 2132

Abstract

Landscape-index calculation tools play a pivotal role in ecosystem studies and urban-planning research, enabling objective assessments of landscape patterns’ similarities and differences. However, the existing tools encounter limitations, such as the inability to visualize landscape indices spatially and the challenge of computing indices [...] Read more.

Landscape-index calculation tools play a pivotal role in ecosystem studies and urban-planning research, enabling objective assessments of landscape patterns’ similarities and differences. However, the existing tools encounter limitations, such as the inability to visualize landscape indices spatially and the challenge of computing indices for both vector and raster data simultaneously. Based on the QGIS development platform, this study presents an innovative framework for landscape-index calculation that addresses these limitations. The framework seamlessly integrates both vector and raster data, comprising three main modules: data input, landscape-index calculation, and visualization. In the data-input module, the tool accommodates various data formats, including vector, raster, and tabular data. The landscape indices’ calculation module allows users to select indices at patch, class, and landscape scales. Notably, the framework provides a comprehensive set of 165 indices for vector data and 20 for raster data, empowering users to selectively calculate landscape indices for vector or raster data to their specific needs and leverage the strengths of each data type. Moreover, the landscape-index visualization module enhances spatial visualization capabilities, meeting user demands for an insightful analysis. By addressing these challenges and offering enhanced functionalities, this framework aims to advance landscape indices’ development and foster more comprehensive landscape analyses. And it presents a novel approach for landscape-index development. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

18 pages, 6796 KiB

Open AccessArticle

Integration of Spatial and Co-Existence Relationships to Improve Administrative Region Target Detection in Map Images

by Kaixuan Du, Fu Ren, Yong Wang, Xianghong Che, Jiping Liu, Jiaxin Hou and Zewei You

ISPRS Int. J. Geo-Inf. 2024, 13(6), 216; https://doi.org/10.3390/ijgi13060216 - 20 Jun 2024

Cited by 1 | Viewed by 1198

Abstract

Administrative regions are fundamental geographic elements on maps, thus making their detection in map images crucial to enhancing intelligent map interpretation. However, existing methods in this field primarily depend on the texture features within the images and do not account for the influence [...] Read more.

Administrative regions are fundamental geographic elements on maps, thus making their detection in map images crucial to enhancing intelligent map interpretation. However, existing methods in this field primarily depend on the texture features within the images and do not account for the influence of spatial and co-existence relationships among different targets. In this study, taking the administrative regions of the Chinese Mainland, Taiwan, Tibet, and Henan as test targets, we employed the spatial and co-existence relationships of pairs of targets to improve target detection performance. Firstly, these four regions were detected using a simple Single-Target Cascading detection model based on RetinaNet. Subsequently, the detection results were adjusted with the spatial and co-existence relationships of each pair of targets. The adjusted outcomes demonstrate a significant increase in target detection accuracy, as well as precision (from 0.62 to 0.96) and F1 score (from 0.76 to 0.88), for the Chinese Mainland target. This study contributes to the advancement of intelligent map interpretation. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

14 pages, 4207 KiB

Open AccessArticle

Improved A* Navigation Path-Planning Algorithm Based on Hexagonal Grid

by Zehua An, Xiaoping Rui and Chaojie Gao

ISPRS Int. J. Geo-Inf. 2024, 13(5), 166; https://doi.org/10.3390/ijgi13050166 - 16 May 2024

Cited by 4 | Viewed by 3193

Abstract

Navigation systems are extensively used in everyday life, but the conventional A* algorithm has several limitations in path planning applications within these systems, such as low degrees of freedom in path planning, inadequate consideration of the effects of special regions, and excessive nodes [...] Read more.

Navigation systems are extensively used in everyday life, but the conventional A* algorithm has several limitations in path planning applications within these systems, such as low degrees of freedom in path planning, inadequate consideration of the effects of special regions, and excessive nodes and turns. Addressing these limitations, an enhanced A* algorithm was proposed using regular hexagonal grid mapping. First, the approach to map modeling using hexagonal grids was described. Subsequently, the A* algorithm was refined by optimizing the calculation of movement costs, thus allowing the algorithm to integrate environmental data more effectively and flexibly adjust node costs while ensuring path optimality. A quantitative method was also introduced to assess map complexity and adaptive heuristics that decrease the number of traversed nodes and increase the search speed. Moreover, a turning penalty measure was implemented to minimize unnecessary turns on the planned paths. Simulation results confirmed that the improved A* algorithm exhibits superior performance, which can dynamically adjust movement costs, enhance search efficiency, reduce turns, improve overall path planning quality, and solve critical path planning issues in navigation systems, greatly aiding the development and design of these systems and making them better suited to meet modern navigation requirements. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

11 pages, 2019 KiB

Open AccessArticle

Vector-Algebra Algorithms to Draw the Curve of Alignment, the Great Ellipse, the Normal Section, and the Loxodrome

by Thomas H. Meyer

Geomatics 2024, 4(2), 138-148; https://doi.org/10.3390/geomatics4020008 - 8 May 2024

Viewed by 1596

Abstract

This paper recasts four geodetic curves—the great ellipse, the normal section, the loxodrome, and the curve of alignment—into a parametric form of vector-algebra formula. These formulas allow these curves to be drawn using simple, efficient, and robust algorithms. The curve of alignment, which [...] Read more.

This paper recasts four geodetic curves—the great ellipse, the normal section, the loxodrome, and the curve of alignment—into a parametric form of vector-algebra formula. These formulas allow these curves to be drawn using simple, efficient, and robust algorithms. The curve of alignment, which seems to be quite obscure, ought not to be. Like the great ellipse and the loxodrome, and unlike the normal section, the curve of alignment from point A to point B (both on the same ellipsoid) is the same as the curve of alignment from point B to point A. The algorithm used to draw the curve of alignment is much simpler than any of the others and its shape is quite similar to that of the geodesic, which suggests it would be a practical surrogate when drawing these curves. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

29 pages, 10941 KiB

Open AccessArticle

Classification of Lakebed Geologic Substrate in Autonomously Collected Benthic Imagery Using Machine Learning

by Joseph K. Geisz, Phillipe A. Wernette and Peter C. Esselman

Remote Sens. 2024, 16(7), 1264; https://doi.org/10.3390/rs16071264 - 3 Apr 2024

Cited by 5 | Viewed by 1898

Abstract

Mapping benthic habitats with bathymetric, acoustic, and spectral data requires georeferenced ground-truth information about habitat types and characteristics. New technologies like autonomous underwater vehicles (AUVs) collect tens of thousands of images per mission making image-based ground truthing particularly attractive. Two types of machine [...] Read more.

Mapping benthic habitats with bathymetric, acoustic, and spectral data requires georeferenced ground-truth information about habitat types and characteristics. New technologies like autonomous underwater vehicles (AUVs) collect tens of thousands of images per mission making image-based ground truthing particularly attractive. Two types of machine learning (ML) models, random forest (RF) and deep neural network (DNN), were tested to determine whether ML models could serve as an accurate substitute for manual classification of AUV images for substrate type interpretation. RF models were trained to predict substrate class as a function of texture, edge, and intensity metrics (i.e., features) calculated for each image. Models were tested using a manually classified image dataset with 9-, 6-, and 2-class schemes based on the Coastal and Marine Ecological Classification Standard (CMECS). Results suggest that both RF and DNN models achieve comparable accuracies, with the 9-class models being least accurate (~73–78%) and the 2-class models being the most accurate (~95–96%). However, the DNN models were more efficient to train and apply because they did not require feature estimation before training or classification. Integrating ML models into benthic habitat mapping process can improve our ability to efficiently and accurately ground-truth large areas of benthic habitat using AUV or similar images. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Graphical abstract

15 pages, 6045 KiB

Open AccessArticle

Spatial Process Analysis of the Evolution of Farmland Landscape in China

by Yan Fu, Qingwen Qi, Lili Jiang and Yapeng Zhao

ISPRS Int. J. Geo-Inf. 2024, 13(3), 98; https://doi.org/10.3390/ijgi13030098 - 18 Mar 2024

Cited by 1 | Viewed by 1666

Abstract

Accurately identifying the patterns of evolution in farmland plays an important role in optimizing farmland management. The aim of this study is to classify the evolution patterns of farmland in China and explore related mechanisms, providing a reference for constructing a systematic farmland [...] Read more.

Accurately identifying the patterns of evolution in farmland plays an important role in optimizing farmland management. The aim of this study is to classify the evolution patterns of farmland in China and explore related mechanisms, providing a reference for constructing a systematic farmland management plan. Using land cover data from five periods in China, nine types of farmland evolution process are described and identified based on landscape process models. We analyzed these processes’ spatiotemporal dynamics and, by examining regional variations, achieved a zoned mapping of China’s farmland evolution. In this study, we combined natural and socioeconomic factors to analyze the mechanisms driving the evolution of farmland landscapes in China. The results indicated that from 1980 to 2020, areas of both lost and restored farmland showed a trend of first increasing and then decreasing, while the total area of farmland fluctuated. The remaining farmland types consisted mainly of core and edge. Their distribution was similar to that of the major agricultural regions in China. Expansion was the main means of farmland restoration. Farmland fragmentation was widespread, and, over time, it became increasingly severe. Shrinkage and subdivision dominated the farmland fragmentation. Altitude and slope had the greatest impact on the evolution patterns of farmland. Increasing urban industrialization and an increase in population density led to an increase in the demand for food production, which placed greater demands on the farmlands in the region. The farmland evolution pattern is a result of the interactions among multiple factors. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

25 pages, 7452 KiB

Open AccessArticle

Smart Urban Cadastral Map Enrichment—A Machine Learning Method

by Alireza Hajiheidari, Mahmoud Reza Delavar and Abbas Rajabifard

ISPRS Int. J. Geo-Inf. 2024, 13(3), 80; https://doi.org/10.3390/ijgi13030080 - 4 Mar 2024

Viewed by 2871

Abstract

Enriching and updating maps are among the most important tasks of any urban management organization for informed decision making. Urban cadastral map enrichment is a time-consuming and costly process, which needs an expert’s opinion for quality control. This research proposes a smart framework [...] Read more.

Enriching and updating maps are among the most important tasks of any urban management organization for informed decision making. Urban cadastral map enrichment is a time-consuming and costly process, which needs an expert’s opinion for quality control. This research proposes a smart framework to enrich a cadastral base map using a more up-to-date map automatically by machine learning algorithms. The proposed framework has three main steps, including parcel matching, parcel change detection and base map enrichment. The matching step is performed by checking the center point of each parcel in the other map parcels. Support vector machine and random forest classification algorithms are used to detect the changed parcels in the base map. The proposed models employ the genetic algorithm for feature selection and grey wolf optimization and Harris hawks optimization for hyperparameter optimization to improve accuracy and performance. By assessing the accuracies of the models, the random forest model with feature selection and grey wolf optimization, with an F1-score of 0.9018, was selected for the parcel change detection method. Finally, the detected changed parcels in the base map are deleted and relocated automatically with corresponding parcels in the more up-to-date map by the affine transformation. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

18 pages, 2787 KiB

Open AccessArticle

Enhancing the K-Means Algorithm through a Genetic Algorithm Based on Survey and Social Media Tourism Objectives for Tourism Path Recommendations

by Mohamed A. Damos, Jun Zhu, Weilian Li, Elhadi Khalifa, Abubakr Hassan, Rashad Elhabob, Alaa Hm and Esra Ei

ISPRS Int. J. Geo-Inf. 2024, 13(2), 40; https://doi.org/10.3390/ijgi13020040 - 27 Jan 2024

Cited by 2 | Viewed by 3102

Abstract

Social media platforms play a vital role in determining valuable tourist objectives, which greatly aids in optimizing tourist path planning. As data classification and analysis methods have advanced, machine learning (ML) algorithms such as the k-means algorithm have emerged as powerful tools for [...] Read more.

Social media platforms play a vital role in determining valuable tourist objectives, which greatly aids in optimizing tourist path planning. As data classification and analysis methods have advanced, machine learning (ML) algorithms such as the k-means algorithm have emerged as powerful tools for sorting through data collected from social media platforms. However, traditional k-means algorithms have drawbacks, including challenges in determining initial seed values. This paper presents a novel approach to enhance the k-means algorithm based on survey and social media tourism data for tourism path recommendations. The main contribution of this paper is enhancing the traditional k-means algorithm by employing the genetic algorithm (GA) to determine the number of clusters (k), select the initial seeds, and recommend the best tourism path based on social media tourism data. The GA enhances the k-means algorithm by using a binary string to represent initial centers and to apply GA operators. To assess its effectiveness, we applied this approach to recommend the optimal tourism path in the Red Sea State, Sudan. The results clearly indicate the superiority of our approach, with an algorithm optimization time of 0.01 s. In contrast, traditional k-means and hierarchical cluster algorithms required 0.27 and 0.7 s, respectively. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

21 pages, 23946 KiB

Open AccessArticle

A Deep-Learning-Based Multimodal Data Fusion Framework for Urban Region Function Recognition

by Mingyang Yu, Haiqing Xu, Fangliang Zhou, Shuai Xu and Hongling Yin

ISPRS Int. J. Geo-Inf. 2023, 12(12), 468; https://doi.org/10.3390/ijgi12120468 - 21 Nov 2023

Cited by 6 | Viewed by 2917

Abstract

Accurate and efficient classification maps of urban functional zones (UFZs) are crucial to urban planning, management, and decision making. Due to the complex socioeconomic UFZ properties, it is increasingly challenging to identify urban functional zones by using remote-sensing images (RSIs) alone. Point-of-interest (POI) [...] Read more.

Accurate and efficient classification maps of urban functional zones (UFZs) are crucial to urban planning, management, and decision making. Due to the complex socioeconomic UFZ properties, it is increasingly challenging to identify urban functional zones by using remote-sensing images (RSIs) alone. Point-of-interest (POI) data and remote-sensing image data play important roles in UFZ extraction. However, many existing methods only use a single type of data or simply combine the two, failing to take full advantage of the complementary advantages between them. Therefore, we designed a deep-learning framework that integrates the above two types of data to identify urban functional areas. In the first part of the complementary feature-learning and fusion module, we use a convolutional neural network (CNN) to extract visual features and social features. Specifically, we extract visual features from RSI data, while POI data are converted into a distance heatmap tensor that is input into the CNN with gated attention mechanisms to extract social features. Then, we use a feature fusion module (FFM) with adaptive weights to fuse the two types of features. The second part is the spatial-relationship-modeling module. We designed a new spatial-relationship-learning network based on a vision transformer model with long- and short-distance attention, which can simultaneously learn the global and local spatial relationships of the urban functional zones. Finally, a feature aggregation module (FGM) utilizes the two spatial relationships efficiently. The experimental results show that the proposed model can fully extract visual features, social features, and spatial relationship features from RSIs and POIs for more accurate UFZ recognition. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

16 pages, 14995 KiB

Open AccessArticle

Automatic Detection and Mapping of Dolines Using U-Net Model from Orthophoto Images

by Ali Polat, İnan Keskin and Özlem Polat

ISPRS Int. J. Geo-Inf. 2023, 12(11), 456; https://doi.org/10.3390/ijgi12110456 - 7 Nov 2023

Cited by 2 | Viewed by 2316

Abstract

A doline is a natural closed depression formed as a result of karstification, and it is the most common landform in karst areas. These depressions damage many living areas and various engineering structures, and this type of collapse event has created natural hazards [...] Read more.

A doline is a natural closed depression formed as a result of karstification, and it is the most common landform in karst areas. These depressions damage many living areas and various engineering structures, and this type of collapse event has created natural hazards in terms of human safety, agricultural activities, and the economy. Therefore, it is important to detect dolines and reveal their properties. In this study, a solution that automatically detects dolines is proposed. The proposed model was employed in a region where many dolines are found in the northwestern part of Sivas City, Turkey. A U-Net model with transfer learning techniques was applied for this task. DenseNet121 gave the best results for the segmentation of the dolines via ResNet34, and EfficientNetB3 and DenseNet121 were used with the U-Net model. The Intersection over Union (IoU) and F-score were used as model evaluation metrics. The IoU and F-score of the DenseNet121 model were calculated as 0.78 and 0.87 for the test data, respectively. Dolines were successfully predicted for the selected test area. The results were converted into a georeferenced vector file. The doline inventory maps can be easily and quickly created using this method. The results can be used in geomorphology, susceptibility, and site selection studies. In addition, this method can be used to segment other landforms in earth science studies. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

24 pages, 14625 KiB

Open AccessArticle

Semantic Segmentation of Urban Airborne LiDAR Point Clouds Based on Fusion Attention Mechanism and Multi-Scale Features

by Jingxue Wang, Huan Li, Zhenghui Xu and Xiao Xie

Remote Sens. 2023, 15(21), 5248; https://doi.org/10.3390/rs15215248 - 5 Nov 2023

Cited by 4 | Viewed by 2707

Abstract

Semantic segmentation of point clouds provided by airborne LiDAR survey in urban scenes is a great challenge. This is due to the fact that point clouds at boundaries of different types of objects are easy to be mixed and have geometric spatial similarity. [...] Read more.

Semantic segmentation of point clouds provided by airborne LiDAR survey in urban scenes is a great challenge. This is due to the fact that point clouds at boundaries of different types of objects are easy to be mixed and have geometric spatial similarity. In addition, the 3D descriptions of the same type of objects have different scales. To address above problems, a fusion attention convolutional network (SMAnet) was proposed in this study. The fusion attention module includes a self-attention module (SAM) and multi-head attention module (MAM). The SAM can capture feature information according to correlation of adjacent point cloud and it can distinguish the mixed point clouds with similar geometric features effectively. The MAM strengthens connections among point clouds according to different subspace features, which is beneficial for distinguishing point clouds at different scales. In feature extraction, lightweight multi-scale feature extraction layers are used to effectively utilize local information of different neighbor fields. Additionally, in order to solve the feature externalization problem and expand the network receptive field, the SoftMax-stochastic pooling (SSP) algorithm is proposed to extract global features. The ISPRS 3D Semantic Labeling Contest dataset was chosen in this study for point cloud segmentation experimentation. Results showed that the overall accuracy and average F1-score of SMAnet reach 85.7% and 75.1%, respectively. It is therefore superior to common algorithms at present. The proposed model also achieved good results on the GML(B) dataset, which proves that the model has good generalization ability. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Graphical abstract

17 pages, 7646 KiB

Open AccessArticle

Large-Scale Automatic Identification of Industrial Vacant Land

by Yihao Sun, Han Hu, Yawen Han, Ziyan Wang and Xiaodi Zheng

ISPRS Int. J. Geo-Inf. 2023, 12(10), 409; https://doi.org/10.3390/ijgi12100409 - 5 Oct 2023

Cited by 1 | Viewed by 2122

Abstract

Many cities worldwide have large amounts of industrial vacant land (IVL) due to development and transformation, posing a growing problem. However, the large-scale identification of IVL is hindered by obstacles such as high cost, high variability, and closed-source data. Moreover, it is difficult [...] Read more.

Many cities worldwide have large amounts of industrial vacant land (IVL) due to development and transformation, posing a growing problem. However, the large-scale identification of IVL is hindered by obstacles such as high cost, high variability, and closed-source data. Moreover, it is difficult to distinguish industrial vacant land from operational industrial land based solely upon image features. To address these issues, we propose a method for the large-scale automatic identification of IVL. The framework uses deep learning to train remote-sensing images of potential industrial vacant land to generate a semantic segmentation model and further use population density and surface temperature data to filter model predictions. The feasibility of the proposed methodology was validated through a case study in Tangshan City, Hebei Province, China. The study indicates two major conclusions: (1) The proposed IVL identification framework can efficiently generate industrial vacant land mapping. (2) HRNet exhibits the highest accuracy and strongest robustness after training compared with other semantic segmentation backbone networks, ensuring high-quality performance and stability, as evidenced by a model accuracy of 97.84%. Based on the above advantages, the identification framework provides a reference method for various countries and regions to identify industrial vacant land on a large scale, which is of great significance for advancing the research and transformation of industrial vacant land worldwide. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

22 pages, 9732 KiB

Open AccessArticle

Gated Recurrent Unit Embedded with Dual Spatial Convolution for Long-Term Traffic Flow Prediction

by Qingyong Zhang, Lingfeng Zhou, Yixin Su, Huiwen Xia and Bingrong Xu

ISPRS Int. J. Geo-Inf. 2023, 12(9), 366; https://doi.org/10.3390/ijgi12090366 - 5 Sep 2023

Cited by 6 | Viewed by 1813

Abstract

Considering the spatial and temporal correlation of traffic flow data is essential to improve the accuracy of traffic flow prediction. This paper proposes a traffic flow prediction model named Dual Spatial Convolution Gated Recurrent Unit (DSC-GRU). In particular, the GRU is embedded with [...] Read more.

Considering the spatial and temporal correlation of traffic flow data is essential to improve the accuracy of traffic flow prediction. This paper proposes a traffic flow prediction model named Dual Spatial Convolution Gated Recurrent Unit (DSC-GRU). In particular, the GRU is embedded with the DSC unit to enable the model to synchronously capture the spatiotemporal dependence. When considering spatial correlation, current prediction models consider only nearest-neighbor spatial features and ignore or simply overlay global spatial features. The DSC unit models the adjacent spatial dependence by the traditional static graph and the global spatial dependence through a novel dependency graph, which is generated by calculating the correlation between nodes based on the correlation coefficient. More than that, the DSC unit quantifies the different contributions of the adjacent and global spatial correlation with a modified gated mechanism. Experimental results based on two real-world datasets show that the DSC-GRU model can effectively capture the spatiotemporal dependence of traffic data. The prediction precision is better than the baseline and state-of-the-art models. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

22 pages, 7358 KiB

Open AccessArticle

Multi-Objective Multi-Satellite Imaging Mission Planning Algorithm for Regional Mapping Based on Deep Reinforcement Learning

by Yaxin Chen, Xin Shen, Guo Zhang and Zezhong Lu

Remote Sens. 2023, 15(16), 3932; https://doi.org/10.3390/rs15163932 - 8 Aug 2023

Cited by 9 | Viewed by 2505

Abstract

Satellite imaging mission planning is used to optimize satellites to obtain target images efficiently. Many evolutionary algorithms (EAs) have been proposed for satellite mission planning. EAs typically require evolutionary parameters, such as the crossover and mutation rates. The performance of EAs is considerably [...] Read more.

Satellite imaging mission planning is used to optimize satellites to obtain target images efficiently. Many evolutionary algorithms (EAs) have been proposed for satellite mission planning. EAs typically require evolutionary parameters, such as the crossover and mutation rates. The performance of EAs is considerably affected by parameter setting. However, most parameter configuration methods of the current EAs are artificially set and lack the overall consideration of multiple parameters. Thus, parameter configuration becomes suboptimal and EAs cannot be effectively utilized. To obtain satisfactory optimization results, the EA comp ensates by extending the evolutionary generation or improving the evolutionary strategy, but it significantly increases the computational consumption. In this study, a multi-objective learning evolutionary algorithm (MOLEA) was proposed to solve the optimal configuration problem of multiple evolutionary parameters and used to solve effective imaging satellite task planning for region mapping. In the MOLEA, population state encoding provided comprehensive population information on the configuration of evolutionary parameters. The evolutionary parameters of each generation were configured autonomously through deep reinforcement learning (DRL), enabling each generation of parameters to gain the best evolutionary benefits for future evolution. Furthermore, the HV of the multi-objective evolutionary algorithm (MOEA) was used to guide reinforcement learning. The superiority of the proposed MOLEA was verified by comparing the optimization performance, stability, and running time of the MOLEA with existing multi-objective optimization algorithms by using four satellites to image two regions of Hubei and Congo (K). The experimental results showed that the optimization performance of the MOLEA was significantly improved, and better imaging satellite task planning solutions were obtained. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

18 pages, 5135 KiB

Open AccessArticle

Research on SUnet Winter Wheat Identification Method Based on GF-2

by Ke Zhou, Zhengyan Zhang, Le Liu, Ru Miao, Yang Yang, Tongcan Ren and Ming Yue

Remote Sens. 2023, 15(12), 3094; https://doi.org/10.3390/rs15123094 - 13 Jun 2023

Cited by 8 | Viewed by 2619

Abstract

Introduction: Winter wheat plays a crucial role in ensuring food security and sustainable agriculture. Accurate identification and recognition of winter wheat in remote sensing images are essential for monitoring crop growth and yield estimation. In recent years, attention-based convolutional neural networks have shown [...] Read more.

Introduction: Winter wheat plays a crucial role in ensuring food security and sustainable agriculture. Accurate identification and recognition of winter wheat in remote sensing images are essential for monitoring crop growth and yield estimation. In recent years, attention-based convolutional neural networks have shown promising results in various image recognition tasks. Therefore, this study aims to explore the application of attention-based convolutional neural networks for winter wheat identification on GF-2 high-resolution images and propose improvements to enhance recognition accuracy. Method: This study built a multi-band winter wheat sample dataset based on GF-2 images. In order to highlight the characteristics of winter wheat, this study added two bands, NDVI and NDVI_increase, to the dataset and proposed a SUNet network model. In this study, the batch normalization layer was added to the basic structure of the UNet convolutional network to speed up network convergence and improve accuracy. In the jump phase, shuffle attention was added to the shallow features extracted from the coding structure for feature optimization and spliced with the deep features extracted by upsampling. The SUNet made the network pay more attention to the important features to improve winter wheat recognition accuracy. In order to overcome the sample imbalance problem, this study used the focus loss function instead of the traditional cross-entropy loss function. Result: The experimental data show that its mean intersection over union, overall classification accuracy, recall, F1 score and kappa coefficient are 0.9514, 0.9781, 0.9707, 0.9663 and 0.9501, respectively. The results of these evaluation indicators are better than those of other comparison methods. Compared with the UNet, the evaluation indicators have increased by 0.0253, 0.0118, 0.021, 0.0185, and 0.0272, respectively. Conclusion: The SUNet network can effectively improve winter wheat recognition accuracy in multi-band GF-2 images. Furthermore, with the support of a cloud platform, it can provide data guarantee and computing support for winter wheat information extraction. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)

► Show Figures

Figure 1

22 pages, 14614 KiB

Open AccessArticle

Mean Inflection Point Distance: Artificial Intelligence Mapping Accuracy Evaluation Index—An Experimental Case Study of Building Extraction

by Ding Yu, Aihua Li, Jinrui Li, Yan Xu and Yinping Long

Remote Sens. 2023, 15(7), 1848; https://doi.org/10.3390/rs15071848 - 30 Mar 2023

Cited by 1 | Viewed by 2456

Abstract

Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary [...] Read more.

Mapping is a fundamental application of remote sensing images, and the accurate evaluation of remote sensing image information extraction using artificial intelligence is critical. However, the existing evaluation method, based on Intersection over Union (IoU), is limited in evaluating the extracted information’s boundary accuracy. It is insufficient for determining mapping accuracy. Furthermore, traditional remote sensing mapping methods struggle to match the inflection points encountered in artificial intelligence contour extraction. In order to address these issues, we propose the mean inflection point distance (MPD) as a new segmentation evaluation method. MPD can accurately calculate error values and solve the problem of multiple inflection points, which traditional remote sensing mapping cannot match. We tested three algorithms on the Vaihingen dataset: Mask R-CNN, Swin Transformer, and PointRend. The results show that MPD is highly sensitive to mapping accuracy, can calculate error values accurately, and is applicable for different scales of mapping accuracy while maintaining high visual consistency. This study helps to assess the accuracy of automatic mapping using remote sensing artificial intelligence. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)
(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

17 pages, 3626 KiB

Open AccessArticle

The Effect of Negative Samples on the Accuracy of Water Body Extraction Using Deep Learning Networks

by Jia Song and Xiangbing Yan

Remote Sens. 2023, 15(2), 514; https://doi.org/10.3390/rs15020514 - 15 Jan 2023

Cited by 6 | Viewed by 2470

Abstract

Water resources are important strategic resources related to human survival and development. Water body extraction from remote sensing images is a very important research topic for the monitoring of global and regional surface water changes. Deep learning networks are one of the most [...] Read more.

Water resources are important strategic resources related to human survival and development. Water body extraction from remote sensing images is a very important research topic for the monitoring of global and regional surface water changes. Deep learning networks are one of the most effective approaches and training data is indispensable for ensuring the network accurately extracts water bodies. The training data for water body extraction includes water body samples and non-water negative samples. Cloud shadows are essential negative samples due to the high similarity between water bodies and cloud shadows, but few studies quantitatively evaluate the impact of cloud shadow samples on the accuracy of water body extraction. Therefore, the training datasets with different proportions of cloud shadows were produced, and each of them includes two types of cloud shadow samples: the manually-labeled cloud shadows and unlabeled cloud shadows. The training datasets are applied on a novel transformer-based water body extraction network to investigate how the negative samples affect the accuracy of the water body extraction network. The evaluation results of Overall Accuracy (OA) of 0.9973, mean Intersection over Union (mIoU) of 0.9753, and Kappa of 0.9747 were obtained, and it was found that when the training dataset contains a certain proportion of cloud shadows, the trained network can handle the misclassification of cloud shadows well and more accurately extract water bodies. Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)
(This article belongs to the Section AI Remote Sensing)

► Show Figures

Figure 1

23 pages, 7463 KiB

Open AccessArticle

Supervised versus Semi-Supervised Urban Functional Area Prediction: Uncertainty, Robustness and Sensitivity

by Rui Deng, Yanning Guan, Danlu Cai, Tao Yang, Klaus Fraedrich, Chunyan Zhang, Jiakui Tang, Zhouwei Liao, Zhishou Wei and Shan Guo

Remote Sens. 2023, 15(2), 341; https://doi.org/10.3390/rs15020341 - 6 Jan 2023

Cited by 1 | Viewed by 2985

Abstract

To characterize a community-scale urban functional area using geo-tagged data and available land-use information, several supervised and semi-supervised models are presented and evaluated in Hong Kong for comparing their uncertainty, robustness and sensitivity. The following results are noted: (i) As the training set [...] Read more.

To characterize a community-scale urban functional area using geo-tagged data and available land-use information, several supervised and semi-supervised models are presented and evaluated in Hong Kong for comparing their uncertainty, robustness and sensitivity. The following results are noted: (i) As the training set size grows, models’ accuracies are improved, particularly for multi-layer perceptron (MLP) or random forest (RF). The graph convolutional network (GCN) (MLP or RF) model reveals top accuracy when the proportion of training samples is less (greater) than 10% of the total number of functional areas; (ii) With a large amount of training samples, MLP shows the highest prediction accuracy and good performances in cross-validation, but less stability on same training sets; (iii) With a small amount of training samples, GCN provides viable results, by incorporating the auxiliary information provided by the proposed semantic linkages, which is meaningful in real-world predictions; (iv) When the training samples are less than 10%, one should be cautious using MLP to test the optimal epoch for obtaining the best accuracy, due to its model overfitting problem. The above insights could support efficient and scalable urban functional area mapping, even with insufficient land-use information (e.g., covering only ~20% of Beijing in the case study). Full article

(This article belongs to the Topic Geocomputation and Artificial Intelligence for Mapping)
(This article belongs to the Section AI Remote Sensing)

► Show Figures

Graphical abstract

Topic Menu

Topic Editors

Geocomputation and Artificial Intelligence for Mapping

Topic Information

Keywords

Participating Journals

Published Papers (24 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI