Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.9
2.8
Journals
IJGI
Special Issues
Advances in AI-Driven Geospatial Analysis and Data Generation
share announcement

Advances in AI-Driven Geospatial Analysis and Data Generation

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

Deadline for manuscript submissions: closed (31 August 2024) | Viewed by 29462

Special Issue Editors

Prof. Dr. Hartwig H. Hochmair

E-Mail Website
Guest Editor
Fort Lauderdale Research and Education Center, Geomatics Sciences, University of Florida, Fort Lauderdale, FL 33314, USA
Interests: crowd-sourced spatial data; social media; non-motorized transportation; location-based services
Special Issues, Collections and Topics in MDPI journals
Dr. Levente Juhász

E-Mail Website
Guest Editor
Geographic Information Systems (GIS) Center, Florida International University, Miami, FL 33199, USA
Interests: user-generated spatial data; human-computer interaction; spatial databases; collaborative mapping
Special Issues, Collections and Topics in MDPI journals
Dr. Hao Li

E-Mail Website
Guest Editor
Department of Aerospace and Geodesy, Technical University of Munich, Lise-Meitner-Str. 9, 85521 Ottobrunn, Germany
Interests: volunteered geographic information; geospatial machine learning; multi-sensor data fusion; geo-semantics; remote sensing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent years, the integration of Artificial Intelligence (AI) with geospatial technologies has revolutionized the field of geodata science. In particular, the advent of Geospatial Artificial Intelligence (GeoAI) and Generative AI has significantly expanded the capabilities of traditional geospatial methods, allowing for unprecedented advancements in the mapping, extraction, generation, and analysis of spatial information. The integration of cutting-edge AI techniques with geospatial science has led to advancements across diverse disciplines and offered novel solutions to complex spatial challenges. GeoAI, with its specialized focus on geospatial data and analysis, harnesses the power of machine learning, deep learning, and other AI methodologies to tackle problems in geospatial domains. GeoAI methods have recently also encompassed Generative AI, which introduces a paradigm shift in spatial data generation, and has been used in geospatial tasks, such as in map labeling, image segmentation, the creation of synthetic spatial data, or AI-powered route optimization.

This Special Issue seeks to explore the transformative potential of AI in the realm of spatial data applications. It invites the submission of original research papers and review articles centered around the use of AI for mapping, extraction, generation, analysis, and communication of spatial data, which exemplify the novel methodologies, algorithms, and applications stemming from the integration of AI in processing and generation of spatial data. In addition to contributions that apply AI in geographic contexts, we encourage synergistic research that advances both the spatial sciences and AI research at large.

Topics of interest may include, but are not limited to:

  • Geospatial artificial intelligence (GeoAI);
  • Generative AI for geographic problems;
  • Foundation models in geographic context;
  • Spatial understanding, reasoning and literacy of large language models;
  • Big/crowdsourced data and AI;
  • AI assistants for mapping and cartography;
  • Multimodal AI systems for geospatial science;
  • AI and location intelligence;
  • AI-based spatial data analysis;
  • Machine learning and deep learning in GIS;
  • Conversional agents for spatial tasks;
  • Novel approaches for data storage and transfer (cloud-native, streaming, etc.);
  • Novel technologies in geocomputation and processing (serverless, edge AI, etc.);
  • Ethical, legal and privacy considerations of GeoAI.

Prof. Dr. Hartwig H. Hochmair
Dr. Levente Juhász
Dr. Hao Li
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

  • GeoAI
  • Large language models
  • Generative AI
  • Machine learning
  • Deep learning
  • Geoprivacy
  • Geoethics

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (14 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 575 KiB  
Article
Large Language Model-Driven Structured Output: A Comprehensive Benchmark and Spatial Data Generation Framework
by Diya Li, Yue Zhao, Zhifang Wang, Calvin Jung and Zhe Zhang
ISPRS Int. J. Geo-Inf. 2024, 13(11), 405; https://doi.org/10.3390/ijgi13110405 - 10 Nov 2024
Viewed by 1522
Abstract
Large language models (LLMs) have demonstrated remarkable capabilities in document processing, data analysis, and code generation. However, the generation of spatial information in a structured and unified format remains a challenge, limiting their integration into production environments. In this paper, we introduce a [...] Read more.
Large language models (LLMs) have demonstrated remarkable capabilities in document processing, data analysis, and code generation. However, the generation of spatial information in a structured and unified format remains a challenge, limiting their integration into production environments. In this paper, we introduce a benchmark for generating structured and formatted spatial outputs from LLMs with a focus on enhancing spatial information generation. We present a multi-step workflow designed to improve the accuracy and efficiency of spatial data generation. The steps include generating spatial data (e.g., GeoJSON) and implementing a novel method for indexing R-tree structures. In addition, we explore and compare a series of methods commonly used by developers and researchers to enable LLMs to produce structured outputs, including fine-tuning, prompt engineering, and retrieval-augmented generation (RAG). We propose new metrics and datasets along with a new method for evaluating the quality and consistency of these outputs. Our findings offer valuable insights into the strengths and limitations of each approach, guiding practitioners in selecting the most suitable method for their specific use cases. This work advances the field of LLM-based structured spatial data output generation and supports the seamless integration of LLMs into real-world applications. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

23 pages, 4147 KiB  
Article
Modeling Population Mobility Flows: A Hybrid Approach Integrating a Gravity Model and Machine Learning
by Jingjing Liu, Lei Xu, Le Ma and Nengcheng Chen
ISPRS Int. J. Geo-Inf. 2024, 13(11), 379; https://doi.org/10.3390/ijgi13110379 - 30 Oct 2024
Viewed by 1058
Abstract
Population mobility between cities significantly affects traffic congestion, disease spread, and societal well-being. As globalization and urbanization accelerate, understanding the dynamics of population mobility becomes increasingly important. Traditional population migration models reveal the factors influencing migration, while machine learning methods provide effective tools [...] Read more.
Population mobility between cities significantly affects traffic congestion, disease spread, and societal well-being. As globalization and urbanization accelerate, understanding the dynamics of population mobility becomes increasingly important. Traditional population migration models reveal the factors influencing migration, while machine learning methods provide effective tools for creating data-driven models to handle the nonlinear relationships between origin and destination characteristics and migration. To deepen the understanding of population mobility issues, this study presents GraviGBM, an expandable population mobility simulation model that combines the gravity model with machine learning, significantly enhancing simulation accuracy. By employing SHAPs (SHapley Additive exPlanations), we interpret the modeling results and explore the relationship between urban characteristics and population migration. Additionally, this study includes a case analysis of COVID-19, extending the model’s application during public health emergencies and evaluating the contribution of model variables in this context. The results show that GraviGBM performs exceptionally well in simulating inter-city population migration, with an RMSE of 4.28, far lower than the RMSE of the gravity model (45.32). This research indicates that distance emerged as the primary factor affecting mobility before the pandemic, with economic factors and population also playing significant roles. During the pandemic, distance remained dominant, but the significance of short distances gained importance. Pandemic-related indicators became prominent, while economics, population density, and transportation substantially lost their influence. A city-to-city flow analysis shows that when population sizes are comparable, economic factors prevail, but when economic profiles match, living conditions dictate migration. During the pandemic, residents from hard-hit areas moved to more distant cities, seeking normalcy. This research offers a comprehensive perspective on population mobility, yielding valuable insights for future urban planning, pandemic response, and decision-making processes. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

14 pages, 8341 KiB  
Article
Detecting Urban Traffic Anomalies Using Traffic-Monitoring Data
by Yunkun Mao, Yilin Shi and Binbin Lu
ISPRS Int. J. Geo-Inf. 2024, 13(10), 351; https://doi.org/10.3390/ijgi13100351 - 4 Oct 2024
Viewed by 1825
Abstract
Traffic anomaly detection is crucial for urban management, yet current research is often confined to small-scale endeavors. This study collected 9 months of real-time Wuhan traffic-monitoring data from Amap. We propose Traffic-ConvLSTM, a multi-scale spatial-temporal technique based on long short-term memory (LSTM) networks [...] Read more.
Traffic anomaly detection is crucial for urban management, yet current research is often confined to small-scale endeavors. This study collected 9 months of real-time Wuhan traffic-monitoring data from Amap. We propose Traffic-ConvLSTM, a multi-scale spatial-temporal technique based on long short-term memory (LSTM) networks and convolutional neural networks (CNNs) to effectively achieve long-term anomaly detection at the city level. First, we converted traffic track points into an image representation, which enables spatial correlation between traffic flow and roads and correlations between traffic flow and roads, as well as the surrounding environment, to be captured. Second, the model utilizes convolution kernels of different sizes to extract spatial features at road-, regional-, and city-level scales while incorporating the temporal features of different time steps to capture hourly, daily, and weekly dynamics. Additionally, varying weights are assigned to the convolution kernels and temporal features of varying spatio-temporal scales to capture the heterogeneous strengths of spatio-temporal correlations within patterns of traffic anomalies. The proposed Traffic-ConvLSTM model exhibits improved performance over existing techniques in the task of identifying long-term and large-scale traffic anomaly occurrences. Furthermore, the analysis reveals significant traffic anomalies during holidays and urban sporting events. The diverse travel patterns observed in response to various activities offer insights for large-scale urban traffic anomaly management, providing recommendations for city-level traffic-control strategies. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

27 pages, 6999 KiB  
Article
Improved Road Extraction Models through Semi-Supervised Learning with ACCT
by Hao Yu, Shihong Du, Zhenshan Tan, Xiuyuan Zhang and Zhijiang Li
ISPRS Int. J. Geo-Inf. 2024, 13(10), 347; https://doi.org/10.3390/ijgi13100347 - 29 Sep 2024
Viewed by 848
Abstract
Improving the performance and reducing the training cost of road extraction models in the absence of samples is important for updating road maps. Despite the success of recent road extraction models on standard datasets, they often fail to perform when applied to new [...] Read more.
Improving the performance and reducing the training cost of road extraction models in the absence of samples is important for updating road maps. Despite the success of recent road extraction models on standard datasets, they often fail to perform when applied to new datasets or real-world scenarios where labeled samples are not available. In this paper, our focus diverges from the typical quest to pinpoint the optimal road extraction model or evaluate generalization prowess across models. Instead, we propose a method called Asymmetric Consistent Co-Training (ACCT) to train existing road extraction models faster and make them perform better in new scenarios lacking samples. ACCT uses two models with different structures and a supervision module to enhance accuracy through mutual learning. Labeled and unlabeled images are processed by both models to generate road maps from different perspectives. The supervision module ensures consistency between predictions by computing losses based on labeling status. ACCT iteratively adjusts parameters using unlabeled data, improving generalization. Empirical evaluations show that ACCT improves IoU by 2.79% to 10.26% using only 1/8 of the labeled data compared to fully supervised methods. It also reduces parameters by over 49% compared to state-of-the-art semi-supervised methods while maintaining similar accuracy. These results highlight the potential of leveraging large amounts of unlabeled data to enhance road extraction models as data acquisition technology advances. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

24 pages, 210044 KiB  
Article
Scale- and Resolution-Adapted Shaded Relief Generation Using U-Net
by Marianna Farmakis-Serebryakova, Magnus Heitzler and Lorenz Hurni
ISPRS Int. J. Geo-Inf. 2024, 13(9), 326; https://doi.org/10.3390/ijgi13090326 - 12 Sep 2024
Viewed by 1263
Abstract
On many maps, relief shading is one of the most significant graphical elements. Modern relief shading techniques include neural networks. To generate such shading automatically at an arbitrary scale, one needs to consider how the resolution of the input digital elevation model (DEM) [...] Read more.
On many maps, relief shading is one of the most significant graphical elements. Modern relief shading techniques include neural networks. To generate such shading automatically at an arbitrary scale, one needs to consider how the resolution of the input digital elevation model (DEM) relates to the neural network process and the maps used for training. Currently, there is no clear guidance on which DEM resolution to use to generate relief shading at specific scales. To address this gap, we trained the U-Net models on swisstopo manual relief shadings of Switzerland at four different scales and using four different resolutions of SwissALTI3D DEM. An interactive web application designed for this study allows users to outline a random area and compare histograms of varying brightness between predictions and manual relief shadings. The results showed that DEM resolution and output scale influence the appearance of the relief shading, with an overall scale/resolution ratio. We present guidelines for generating relief shading with neural networks for arbitrary areas and scales. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

27 pages, 20774 KiB  
Article
Genetic Programming to Optimize 3D Trajectories
by André Kotze, Moritz Jan Hildemann, Vítor Santos and Carlos Granell
ISPRS Int. J. Geo-Inf. 2024, 13(8), 295; https://doi.org/10.3390/ijgi13080295 - 20 Aug 2024
Viewed by 1147
Abstract
Trajectory optimization is a method of finding the optimal route connecting a start and end point. The suitability of a trajectory depends on not intersecting any obstacles, as well as predefined performance metrics. In the context of unmanned aerial vehicles (UAVs), the goal [...] Read more.
Trajectory optimization is a method of finding the optimal route connecting a start and end point. The suitability of a trajectory depends on not intersecting any obstacles, as well as predefined performance metrics. In the context of unmanned aerial vehicles (UAVs), the goal is to minimize the route cost, in terms of energy or time, while avoiding restricted flight zones. Artificial intelligence techniques, including evolutionary computation, have been applied to trajectory optimization with varying degrees of success. This work explores the use of genetic programming (GP) for 3D trajectory optimization by developing a novel GP algorithm to optimize trajectories in a 3D space by encoding 3D geographic trajectories as function trees. The effects of parameterization are also explored and discussed, demonstrating the advantages and drawbacks of custom parameter settings along with additional evolutionary computational techniques. The results demonstrate the effectiveness of the proposed algorithm, which outperforms existing methods in terms of speed, automaticity, and robustness, highlighting the potential for GP-based algorithms to be applied to other complex optimization problems in science and engineering. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

18 pages, 4952 KiB  
Article
Graph Representation Learning for Street-Level Crime Prediction
by Haishuo Gu, Jinguang Sui and Peng Chen
ISPRS Int. J. Geo-Inf. 2024, 13(7), 229; https://doi.org/10.3390/ijgi13070229 - 1 Jul 2024
Cited by 1 | Viewed by 1189
Abstract
In contemporary research, the street network emerges as a prominent and recurring theme in crime prediction studies. Meanwhile, graph representation learning shows considerable success, which motivates us to apply the methodology to crime prediction research. In this article, a graph representation learning approach [...] Read more.
In contemporary research, the street network emerges as a prominent and recurring theme in crime prediction studies. Meanwhile, graph representation learning shows considerable success, which motivates us to apply the methodology to crime prediction research. In this article, a graph representation learning approach is utilized to derive topological structure embeddings within the street network. Subsequently, a heterogeneous information network that incorporates both the street network and urban facilities is constructed, and embeddings through link prediction tasks are obtained. Finally, the two types of high-order embeddings, along with other spatio-temporal features, are fed into a deep neural network for street-level crime prediction. The proposed framework is tested using data from Beijing, and the outcomes demonstrate that both types of embeddings have a positive impact on crime prediction, with the second embedding showing a more significant contribution. Comparative experiments indicate that the proposed deep neural network offers superior efficiency in crime prediction. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

27 pages, 10814 KiB  
Article
UPGAN: An Unsupervised Generative Adversarial Network Based on U-Shaped Structure for Pansharpening
by Xin Jin, Yuting Feng, Qian Jiang, Shengfa Miao, Xing Chu, Huangqimei Zheng and Qianqian Wang
ISPRS Int. J. Geo-Inf. 2024, 13(7), 222; https://doi.org/10.3390/ijgi13070222 - 26 Jun 2024
Viewed by 1321
Abstract
Pansharpening is the fusion of panchromatic images and multispectral images to obtain images with high spatial resolution and high spectral resolution, which have a wide range of applications. At present, methods based on deep learning can fit the nonlinear features of images and [...] Read more.
Pansharpening is the fusion of panchromatic images and multispectral images to obtain images with high spatial resolution and high spectral resolution, which have a wide range of applications. At present, methods based on deep learning can fit the nonlinear features of images and achieve excellent image quality; however, the images generated with supervised learning approaches lack real-world applicability. Therefore, in this study, we propose an unsupervised pansharpening method based on a generative adversarial network. Considering the fine tubular structures in remote sensing images, a dense connection attention module is designed based on dynamic snake convolution to recover the details of spatial information. In the stage of image fusion, the fusion of features in groups is applied through the cross-scale attention fusion module. Moreover, skip layers are implemented at different scales to integrate significant information, thus improving the objective index values and visual appearance. The loss function contains four constraints, allowing the model to be effectively trained without reference images. The experimental results demonstrate that the proposed method outperforms other widely accepted state-of-the-art methods on the QuickBird and WorldView2 data sets. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

25 pages, 30680 KiB  
Article
Oil Palm Bunch Ripeness Classification and Plantation Verification Platform: Leveraging Deep Learning and Geospatial Analysis and Visualization
by Supattra Puttinaovarat, Supaporn Chai-Arayalert and Wanida Saetang
ISPRS Int. J. Geo-Inf. 2024, 13(5), 158; https://doi.org/10.3390/ijgi13050158 - 8 May 2024
Cited by 1 | Viewed by 1672
Abstract
Oil palm cultivation thrives as a prominent agricultural endeavor within the southern region of Thailand, where the country ranks third globally in production, following Malaysia and Indonesia. The assessment of oil palm bunch ripeness serves various purposes, notably in determining purchasing prices, pre-harvest [...] Read more.
Oil palm cultivation thrives as a prominent agricultural endeavor within the southern region of Thailand, where the country ranks third globally in production, following Malaysia and Indonesia. The assessment of oil palm bunch ripeness serves various purposes, notably in determining purchasing prices, pre-harvest evaluations, and evaluating the impacts of disasters or low market prices. Presently, two predominant methods are employed for this assessment, namely human evaluation, and machine learning for ripeness classification. Human assessment, while boasting high accuracy, necessitates the involvement of farmers or experts, resulting in prolonged processing times, especially when dealing with extensive datasets or dispersed fields. Conversely, machine learning, although capable of accurately classifying harvested oil palm bunches, faces limitations concerning its inability to process images of oil palm bunches on trees and the absence of a platform for on-tree ripeness classification. Considering these challenges, this study introduces the development of a classification platform leveraging machine learning (deep learning) in conjunction with geospatial analysis and visualization to ascertain the ripeness of oil palm bunches while they are still on the tree. The research outcomes demonstrate that oil palm bunch ripeness can be accurately and efficiently classified using a mobile device, achieving an impressive accuracy rate of 99.89% with a training dataset comprising 8779 images and a validation accuracy of 96.12% with 1160 images. Furthermore, the proposed platform facilitates the management and processing of spatial data by comparing coordinates derived from images with oil palm plantation data obtained through crowdsourcing and the analysis of cloud or satellite images of oil palm plantations. This comprehensive platform not only provides a robust model for ripeness assessment but also offers potential applications in government management contexts, particularly in scenarios necessitating real-time information on harvesting status and oil palm plantation conditions. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

20 pages, 18444 KiB  
Article
Exploration of an Open Vocabulary Model on Semantic Segmentation for Street Scene Imagery
by Zichao Zeng and Jan Boehm
ISPRS Int. J. Geo-Inf. 2024, 13(5), 153; https://doi.org/10.3390/ijgi13050153 - 5 May 2024
Cited by 1 | Viewed by 2492
Abstract
This study investigates the efficacy of an open vocabulary, multi-modal, foundation model for the semantic segmentation of images from complex urban street scenes. Unlike traditional models reliant on predefined category sets, Grounded SAM uses arbitrary textual inputs for category definition, offering enhanced flexibility [...] Read more.
This study investigates the efficacy of an open vocabulary, multi-modal, foundation model for the semantic segmentation of images from complex urban street scenes. Unlike traditional models reliant on predefined category sets, Grounded SAM uses arbitrary textual inputs for category definition, offering enhanced flexibility and adaptability. The model’s performance was evaluated across single and multiple category tasks using the benchmark datasets Cityscapes, BDD100K, GTA5, and KITTI. The study focused on the impact of textual input refinement and the challenges of classifying visually similar categories. Results indicate strong performance in single-category segmentation but highlighted difficulties in multi-category scenarios, particularly with categories bearing close textual or visual resemblances. Adjustments in textual prompts significantly improved detection accuracy, though challenges persisted in distinguishing between visually similar objects such as buses and trains. Comparative analysis with state-of-the-art models revealed Grounded SAM’s competitive performance, particularly notable given its direct inference capability without extensive dataset-specific training. This feature is advantageous for resource-limited applications. The study concludes that while open vocabulary models such as Grounded SAM mark a significant advancement in semantic segmentation, further improvements in integrating image and text processing are essential for better performance in complex scenarios. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

21 pages, 11156 KiB  
Article
Map Reading and Analysis with GPT-4V(ision)
by Jinwen Xu and Ran Tao
ISPRS Int. J. Geo-Inf. 2024, 13(4), 127; https://doi.org/10.3390/ijgi13040127 - 11 Apr 2024
Cited by 3 | Viewed by 2621
Abstract
In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore [...] Read more.
In late 2023, the image-reading capability added to a Generative Pre-trained Transformer (GPT) framework provided the opportunity to potentially revolutionize the way we view and understand geographic maps, the core component of cartography, geography, and spatial data science. In this study, we explore reading and analyzing maps with the latest version of GPT-4-vision-preview (GPT-4V), to fully evaluate its advantages and disadvantages in comparison with human eye-based visual inspections. We found that GPT-4V is able to properly retrieve information from various types of maps in different scales and spatiotemporal resolutions. GPT-4V can also perform basic map analysis, such as identifying visual changes before and after a natural disaster. It has the potential to replace human efforts by examining batches of maps, accurately extracting information from maps, and linking observed patterns with its pre-trained large dataset. However, it is encumbered by limitations such as diminished accuracy in visual content extraction and a lack of validation. This paper sets an example of effectively using GPT-4V for map reading and analytical tasks, which is a promising application for large multimodal models, large language models, and artificial intelligence. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

19 pages, 4802 KiB  
Article
Identifying Spatial Determinants of Rice Yields in Main Producing Areas of China Using Geospatial Machine Learning
by Qingyan Wang, Longzhi Sun and Xuan Yang
ISPRS Int. J. Geo-Inf. 2024, 13(3), 76; https://doi.org/10.3390/ijgi13030076 - 28 Feb 2024
Viewed by 2741
Abstract
Rice yield is essential to global food security under increasingly frequent and severe climate change events. Spatial analysis of rice yields becomes more critical for regional action to ensure yields and reduce climate impacts. However, the understanding of the spatially varied geographical, climate, [...] Read more.
Rice yield is essential to global food security under increasingly frequent and severe climate change events. Spatial analysis of rice yields becomes more critical for regional action to ensure yields and reduce climate impacts. However, the understanding of the spatially varied geographical, climate, soil, and environmental factors of rice yields needs to be improved, leading to potentially biased local rice yield prediction and responses to climate change. This study develops a spatial machine learning-based approach that integrates machine learning and spatial stratified heterogeneity models to identify the determinants and spatial interactions of rice yields in the main rice-producing areas of China, the world’s largest rice-producing nation. A series of satellite remote sensing-derived variables are collected to characterize varied geographical, climate, soil, and environmental conditions and explain the spatial disparities of rice yields. The first step is to explore the spatial clustering patterns of the rice yield distributions using spatially global and local autocorrelation models. Next, a Geographically Optimal Zones-based Heterogeneity (GOZH) model, which integrates spatial stratified heterogeneity models and machine learning, is employed to explore the power of determinants (PD) of individual spatial variables in influencing the spatial disparities of rice yields. Third, geographically optimal zones are identified with the machine learning-derived optimal spatial overlay of multiple geographical variables. Finally, the overall PD of various variables affecting rice yield distributions is calculated using the multiple variables-determined geographically optimal zones and the GOZH model. The comparison between the developed spatial machine learning-based approach and previous related models demonstrates that the GOZH model is an effective and robust approach for identifying the spatial determinants and their spatial interactions with rice yields. The identified spatial determinants and their interactions are essential for enhancing regional agricultural management practices and optimizing resource allocation within diverse main rice-producing regions. The comprehensive understanding of the spatial determinants and heterogeneity of rice yields of this study has a broad impact on agricultural strategies and food security. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

23 pages, 13368 KiB  
Article
Learning Daily Human Mobility with a Transformer-Based Model
by Weiying Wang and Toshihiro Osaragi
ISPRS Int. J. Geo-Inf. 2024, 13(2), 35; https://doi.org/10.3390/ijgi13020035 - 24 Jan 2024
Cited by 1 | Viewed by 2491
Abstract
The generation and prediction of daily human mobility patterns have raised significant interest in many scientific disciplines. Using various data sources, previous studies have examined several deep learning frameworks, such as the RNN and GAN, to synthesize human movements. Transformer models have been [...] Read more.
The generation and prediction of daily human mobility patterns have raised significant interest in many scientific disciplines. Using various data sources, previous studies have examined several deep learning frameworks, such as the RNN and GAN, to synthesize human movements. Transformer models have been used frequently for image analysis and language processing, while the applications of these models on human mobility are limited. In this study, we construct a transformer model, including a self-attention-based embedding component and a Generative Pre-trained Transformer component, to learn daily movements. The embedding component takes regional attributes as input and learns regional relationships to output vector representations for locations, enabling the second component to generate different mobility patterns for various scenarios. The proposed model shows satisfactory performance for generating and predicting human mobilities, superior to a Long Short-Term Memory model in terms of several aggregated statistics and sequential characteristics. Further examination indicates that the proposed model learned the spatial structure and the temporal relationship of human mobility, which generally agrees with our empirical analysis. This observation suggests that the transformer framework can be a promising model for learning and understanding human movements. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

18 pages, 5862 KiB  
Article
Relief Supply-Demand Estimation Based on Social Media in Typhoon Disasters Using Deep Learning and a Spatial Information Diffusion Model
by Shaopan Li, Yiping Lin and Hong Huang
ISPRS Int. J. Geo-Inf. 2024, 13(1), 29; https://doi.org/10.3390/ijgi13010029 - 16 Jan 2024
Cited by 2 | Viewed by 2251
Abstract
Estimating disaster relief supplies is crucial for governments coordinating and executing disaster relief operations. Rapid and accurate estimation of disaster relief supplies can assist the government to optimize the allocation of resources and better organize relief efforts. Traditional approaches for estimating disaster supplies [...] Read more.
Estimating disaster relief supplies is crucial for governments coordinating and executing disaster relief operations. Rapid and accurate estimation of disaster relief supplies can assist the government to optimize the allocation of resources and better organize relief efforts. Traditional approaches for estimating disaster supplies are based on census data and regional risk assessments. However, these methods are often static and lack timely updates, which can result in significant disparities between the availability and demand of relief supplies. Social media, network maps, and other sources of big data contain a large amount of real-time disaster-related information that can promptly reflect the occurrence of a disaster and the relief requirements of the affected residents in a given region. Based on this information, this study presents a model to estimate the demand for disaster relief supplies using social media data. This study employs a deep learning approach to extract real-time disaster information from social media big data and integrates it with a spatial information diffusion model to estimate the population in need of relief in the affected regions. Additionally, this study estimates the demand for emergency materials based on the population in need of relief. These findings indicate that social media data can capture information on the demand for relief materials in disaster-affected regions. Moreover, integrating social media big data with traditional static data can effectively improve the accuracy and timeliness of estimating the demand for disaster relief supplies. Full article
(This article belongs to the Special Issue Advances in AI-Driven Geospatial Analysis and Data Generation)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-14
Back to TopTop