Special Issue "Artificial Intelligence Solutions for Geospatial Analysis: An Integrated Approach"

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

Deadline for manuscript submissions: closed (31 July 2019).

Special Issue Editor

Guest Editor
Prof. Dr. Jason K. Levy Website E-Mail
Disaster Preparedness and Emergency Management, University of Hawaii, Kapolei, HI 96707, USA
Interests: disaster risk governance; sustainable hazard mitigation; stochastic and statistical hydrology; sociohydrology; fluvial and marine disasters; global climate change, computational intelligence for water management; hydrologic resilience; process-based modeling of coupled human–water systems; inundation; economics of water resources management; drought

Special Issue Information

Dear Colleagues,

With this Special Issue on "Artificial Intelligence (AI) for Geospatial Data Analysis" we aim at taking an integrated approach to AI solutions that includes not only algorithms for intelligent geospatial data analysis, but also environmental and social dimensions, thereby fostering a robust collaboration between the Computer Science, Remote Sensing, GIScience, Social Science, and Machine Learning communities.

The intelligent collection, analysis and management Big GeoData calls for highly integrated, comprehensive and systematic approaches that relies on the expertise of scholars familiar with new AI approaches together with ethics, values and environmental issues. Artificial Intelligence (AI) techniques, algorithms and approaches are transforming society.  The best AI solutions for geospatial analysis are those that include both "hard" approaches (i.e., traditional rule-based and systems) and "soft" approaches technologies (including fuzzy–neural networks) rather than relying exclusively on "connectionist" or "symbolic" paradigms. This is critically important as AI techniques, particularly machine learning, are revolutionizing the broad field of geospatial analysis. As of 2018, there were approximately three quintillion bytes of data created each day, and the pace of data creation, storage and management is increasing.

Topics include, but are not limited to:

* Integrated approaches to computer vision, speech recognition and natural language processing Object reconstruction, recognition, and classification at large scale * Application to all levels of automated systems (from semi-autonomous to fully autonomous systems

* Social science considerations off supervised, weakly supervised, transfer, and human-in-the-loop learning * Big GeoData creation, analysis and management * Applications to civilian applications, militaries, disaster management, autonomous driving, vegetation and landscape mapping.

Prospective authors are cordially invited to contribute to this Special Issue by submitting an original article that deals with one of the sub-fields until 31 January 2019. All submitting authors are strongly encouraged to test their method on a relevant benchmark data set, to compare against baseline approaches and to publicly release source code and potentially the data used in the paper, on acceptance.

Prof. Dr. Jason K. Levy
Guest Editor

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 papers will be 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 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Geospatial Artificial Intelligence (AI)
  • Machine Learning (e.g. Random Forests, Support Vector Machines) and Deep Learning (i.e., Neural Networks)
  • Connectionism(s) vs. Symbolic Reasoning (i.e., Good Old Fashioned AI (GOFAI))
  • Dynamical AI systems
  • Planning, resource allocation, and decision-making

Published Papers (8 papers)

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

Research

Jump to: Review

Open AccessArticle
Generation of Lane-Level Road Networks Based on a Trajectory-Similarity-Join Pruning Strategy
ISPRS Int. J. Geo-Inf. 2019, 8(9), 416; https://doi.org/10.3390/ijgi8090416 - 16 Sep 2019
Abstract
With the development of autonomous driving, lane-level maps have attracted significant attention. Since the lane-level road network is an important part of the lane-level map, the efficient, low-cost, and automatic generation of lane-level road networks has become increasingly important. We propose a new [...] Read more.
With the development of autonomous driving, lane-level maps have attracted significant attention. Since the lane-level road network is an important part of the lane-level map, the efficient, low-cost, and automatic generation of lane-level road networks has become increasingly important. We propose a new method here that generates lane-level road networks using only position information based on an autonomous vehicle and the existing lane-level road networks from the existing road-level professionally surveyed without lane details. This method uses the parallel relationship between the centerline of a lane and the centerline of the corresponding segment. Since the direct point-by-point computation is huge, we propose a method based on a trajectory-similarity-join pruning strategy (TSJ-PS). This method uses a filter-and-verify search framework. First, it performs quick segmentation based on the minimum distance and then uses the similarity of two trajectories to prune the trajectory similarity join. Next, it calculates the centerline trajectory for lanes using the simulation transformation model by the unpruned trajectory points. Finally, we demonstrate the efficiency of the algorithm and generate a lane-level road network via experiments on a real road. Full article
Open AccessArticle
Satellite-Based Bathymetric Modeling Using a Wavelet Network Model
ISPRS Int. J. Geo-Inf. 2019, 8(9), 405; https://doi.org/10.3390/ijgi8090405 - 12 Sep 2019
Abstract
Accurate bathymetric modeling is required for safe maritime navigation in shallow waters as well as for other marine operations. Traditionally, bathymetric modeling is commonly carried out using linear models, such as the Stumpf method. Linear methods are developed to derive bathymetry using the [...] Read more.
Accurate bathymetric modeling is required for safe maritime navigation in shallow waters as well as for other marine operations. Traditionally, bathymetric modeling is commonly carried out using linear models, such as the Stumpf method. Linear methods are developed to derive bathymetry using the strong linear correlation between the grey values of satellite imagery visible bands and the water depth where the energy of these visible bands, received at the satellite sensor, is inversely proportional to the depth of water. However, without satisfying homogeneity of the seafloor topography, this linear method fails. The current state-of-the-art is represented by artificial neural network (ANN) models, which were developed using a non-linear, static modeling function. However, more accurate modeling can be achieved using a highly non-linear, dynamic modeling function. This paper investigates a highly non-linear wavelet network model for accurate satellite-based bathymetric modeling with dynamic non-linear wavelet activation function that has been proven to be a valuable modeling method for many applications. Freely available Level-1C satellite imagery from the Sentinel-2A satellite was employed to develop and justify the proposed wavelet network model. The top-of-atmosphere spectral reflectance values for the multispectral bands were employed to establish the wavelet network model. It is shown that the root-mean-squared (RMS) error of the developed wavelet network model was about 1.82 m, and the correlation between the wavelet network model depth estimate and “truth” nautical chart depths was about 95%, on average. To further justify the proposed model, a comparison was made among the developed, highly non-linear wavelet network method, the Stumpf log-ratio method, and the ANN method. It is concluded that the developed, highly non-linear wavelet network model is superior to the Stumpf log-ratio method by about 37% and outperforms the ANN model by about 21%, on average, on the basis of the RMS errors. Also, the accuracy of the bathymetry-derived wavelet network model was evaluated on the basis of the International Hydrographic Organization (IHO)’s standards for all survey orders. It is shown that the accuracy of the bathymetry derived from the wavelet network model does not meet the IHO’s standards for all survey orders; however, the wavelet network model can still be employed as an accurate and powerful tool for survey planning when conducting hydrographic surveys for new, shallow water areas. Full article
Show Figures

Graphical abstract

Open AccessArticle
Development of an Object-Based Interpretive System Based on Weighted Scoring Method in a Multi-Scale Manner
ISPRS Int. J. Geo-Inf. 2019, 8(9), 398; https://doi.org/10.3390/ijgi8090398 - 05 Sep 2019
Abstract
For an accurate interpretation of high-resolution images, correct training samples are required, whose automatic production is an important step. However, the proper way to use them and the reduction of their defects should also be taken into consideration. To this end, in this [...] Read more.
For an accurate interpretation of high-resolution images, correct training samples are required, whose automatic production is an important step. However, the proper way to use them and the reduction of their defects should also be taken into consideration. To this end, in this study, the application of different combinations of training data in a layered structure provided different scores for each observation. For each observation (segment) in a layer, the scores corresponded to the obtained misclassification cost for all classes. Next, these scores were properly weighted by considering the stability of different layers, the adjacency analysis of each segment in a multi-scale manner and the main properties of the basic classes. Afterwards, by integrating the scores of all classes weighted in all layers, the final scores were produced. Finally, the labels were achieved in the form of collective wisdom, obtained from the weighted scores of all segments. In the present study, the aim was to develop a hybrid intelligent system that can exploit both expert knowledge and machine learning algorithms to improve the accuracy and efficiency of the object-based classification. To evaluate the efficiency of the proposed method, the results of this research were assessed and compared with those of other methods in the semi-urban domain. The experimental results indicated the reliability and efficiency of the proposed method. Full article
Show Figures

Figure 1

Open AccessArticle
Spatial Keyword Query of Region-Of-Interest Based on the Distributed Representation of Point-Of-Interest
ISPRS Int. J. Geo-Inf. 2019, 8(6), 287; https://doi.org/10.3390/ijgi8060287 - 20 Jun 2019
Abstract
The tremendous advance in information technology has promoted the rapid development of location-based services (LBSs), which play an indispensable role in people’s daily lives. Compared with a traditional LBS based on Point-Of-Interest (POI), which is an isolated location point, an increasing number of [...] Read more.
The tremendous advance in information technology has promoted the rapid development of location-based services (LBSs), which play an indispensable role in people’s daily lives. Compared with a traditional LBS based on Point-Of-Interest (POI), which is an isolated location point, an increasing number of demands have concentrated on Region-Of-Interest (ROI) exploration, i.e., geographic regions that contain many POIs and express rich environmental information. The intention behind the POI is to search the geographical regions related to the user’s requirements, which contain some spatial objects, such as POIs and have certain environmental characteristics. In order to achieve effective ROI exploration, we propose an ROI top-k keyword query method that considers the environmental information of the regions. Specifically, the Word2Vec model has been introduced to achieve the distributed representation of POIs and capture their environmental semantics, which are then leveraged to describe the environmental characteristic information of the candidate ROI. Given a keyword query, different query patterns are designed to measure the similarities between the query keyword and the candidate ROIs to find the k candidate ROIs that are most relevant to the query. In the verification step, an evaluation criterion has been developed to test the effectiveness of the distributed representations of POIs. Finally, after generating the POI vectors in high quality, we validated the performance of the proposed ROI top-k query on a large-scale real-life dataset where the experimental results demonstrated the effectiveness of our proposals. Full article
Show Figures

Figure 1

Open AccessArticle
Predicting Station-Level Short-Term Passenger Flow in a Citywide Metro Network Using Spatiotemporal Graph Convolutional Neural Networks
ISPRS Int. J. Geo-Inf. 2019, 8(6), 243; https://doi.org/10.3390/ijgi8060243 - 28 May 2019
Cited by 2
Abstract
Predicting the passenger flow of metro networks is of great importance for traffic management and public safety. However, such predictions are very challenging, as passenger flow is affected by complex spatial dependencies (nearby and distant) and temporal dependencies (recent and periodic). In this [...] Read more.
Predicting the passenger flow of metro networks is of great importance for traffic management and public safety. However, such predictions are very challenging, as passenger flow is affected by complex spatial dependencies (nearby and distant) and temporal dependencies (recent and periodic). In this paper, we propose a novel deep-learning-based approach, named STGCNNmetro (spatiotemporal graph convolutional neural networks for metro), to collectively predict two types of passenger flow volumes—inflow and outflow—in each metro station of a city. Specifically, instead of representing metro stations by grids and employing conventional convolutional neural networks (CNNs) to capture spatiotemporal dependencies, STGCNNmetro transforms the city metro network to a graph and makes predictions using graph convolutional neural networks (GCNNs). First, we apply stereogram graph convolution operations to seamlessly capture the irregular spatiotemporal dependencies along the metro network. Second, a deep structure composed of GCNNs is constructed to capture the distant spatiotemporal dependencies at the citywide level. Finally, we integrate three temporal patterns (recent, daily, and weekly) and fuse the spatiotemporal dependencies captured from these patterns to form the final prediction values. The STGCNNmetro model is an end-to-end framework which can accept raw passenger flow-volume data, automatically capture the effective features of the citywide metro network, and output predictions. We test this model by predicting the short-term passenger flow volume in the citywide metro network of Shanghai, China. Experiments show that the STGCNNmetro model outperforms seven well-known baseline models (LSVR, PCA-kNN, NMF-kNN, Bayesian, MLR, M-CNN, and LSTM). We additionally explore the sensitivity of the model to its parameters and discuss the distribution of prediction errors. Full article
Show Figures

Figure 1

Open AccessArticle
Tree Species Classification Using Hyperion and Sentinel-2 Data with Machine Learning in South Korea and China
ISPRS Int. J. Geo-Inf. 2019, 8(3), 150; https://doi.org/10.3390/ijgi8030150 - 20 Mar 2019
Abstract
Remote sensing (RS) has been used to monitor inaccessible regions. It is considered a useful technique for deriving important environmental information from inaccessible regions, especially North Korea. In this study, we aim to develop a tree species classification model based on RS and [...] Read more.
Remote sensing (RS) has been used to monitor inaccessible regions. It is considered a useful technique for deriving important environmental information from inaccessible regions, especially North Korea. In this study, we aim to develop a tree species classification model based on RS and machine learning techniques, which can be utilized for classification in North Korea. Two study sites were chosen, the Korea National Arboretum (KNA) in South Korea and Mt. Baekdu (MTB; a.k.a., Mt. Changbai in Chinese) in China, located in the border area between North Korea and China, and tree species classifications were examined in both regions. As a preliminary step in developing a classification algorithm that can be applied in North Korea, common coniferous species at both study sites, Korean pine (Pinus koraiensis) and Japanese larch (Larix kaempferi), were chosen as targets for investigation. Hyperion data have been used for tree species classification due to the abundant spectral information acquired from across more than 200 spectral bands (i.e., hyperspectral satellite data). However, it is impossible to acquire recent Hyperion data because the satellite ceased operation in 2017. Recently, Sentinel-2 satellite multispectral imagery has been used in tree species classification. Thus, it is necessary to compare these two kinds of satellite data to determine the possibility of reliably classifying species. Therefore, Hyperion and Sentinel-2 data were employed, along with machine learning techniques, such as random forests (RFs) and support vector machines (SVMs), to classify tree species. Three questions were answered, showing that: (1) RF and SVM are well established in the hyperspectral imagery for tree species classification, (2) Sentinel-2 data can be used to classify tree species with RF and SVM algorithms instead of Hyperion data, and (3) training data that were built in the KNA cannot be used for the tree classification of MTB. Random forests and SVMs showed overall accuracies of 0.60 and 0.51 and kappa values of 0.20 and 0.00, respectively. Moreover, combined training data from the KNA and MTB showed high classification accuracies in both regions; RF and SVM values exhibited accuracies of 0.99 and 0.97 and kappa values of 0.98 and 0.95, respectively. Full article
Show Figures

Figure 1

Open AccessArticle
A High-Definition Road-Network Model for Self-Driving Vehicles
ISPRS Int. J. Geo-Inf. 2018, 7(11), 417; https://doi.org/10.3390/ijgi7110417 - 29 Oct 2018
Cited by 1
Abstract
High-definition (HD) maps have gained increasing attention in highly automated driving technology and show great significance for self-driving cars. An HD road network (HDRN) is one of the most important parts of an HD map. To date, there have been few studies focusing [...] Read more.
High-definition (HD) maps have gained increasing attention in highly automated driving technology and show great significance for self-driving cars. An HD road network (HDRN) is one of the most important parts of an HD map. To date, there have been few studies focusing on road and road-segment extraction in the automatic generation of an HDRN. To improve the precision of an HDRN further and represent the topological relations between road segments and lanes better, in this paper, we propose an HDRN model (HDRNM) for a self-driving car. The HDRNM divides the HDRN into a road-segment network layer and a road-network layer. It includes road segments, attributes and geometric topological relations between lanes, as well as relations between road segments and lanes. We define the place in a road segment where the attribute changes as a linear event point. The road segment serves as a linear benchmark, and the linear event point from the road segment is mapped to its lanes via their relative positions to segment the lanes. Then, the HDRN is automatically generated from road centerlines collected by a mobile mapping vehicle through a multi-directional constraint principal component analysis method. Finally, an experiment proves the effectiveness of this HDRNM. Full article
Show Figures

Figure 1

Review

Jump to: Research

Open AccessReview
From Manual to Intelligent: A Review of Input Data Preparation Methods for Geographic Modeling
ISPRS Int. J. Geo-Inf. 2019, 8(9), 376; https://doi.org/10.3390/ijgi8090376 - 28 Aug 2019
Abstract
One of the key concerns in geographic modeling is the preparation of input data that are sufficient and appropriate for models. This requires considerable time, effort, and expertise since geographic models and their application contexts are complex and diverse. Moreover, both data and [...] Read more.
One of the key concerns in geographic modeling is the preparation of input data that are sufficient and appropriate for models. This requires considerable time, effort, and expertise since geographic models and their application contexts are complex and diverse. Moreover, both data and data pre-processing tools are multi-source, heterogeneous, and sometimes unavailable for a specific application context. The traditional method of manually preparing input data cannot effectively support geographic modeling, especially for complex integrated models and non-expert users. Therefore, effective methods are urgently needed that are not only able to prepare appropriate input data for models but are also easy to use. In this review paper, we first analyze the factors that influence data preparation and discuss the three corresponding key tasks that should be accomplished when developing input data preparation methods for geographic models. Then, existing input data preparation methods for geographic models are discussed through classifying into three categories: manual, (semi-)automatic, and intelligent (i.e., not only (semi-)automatic but also adaptive to application context) methods. Supported by the adoption of knowledge representation and reasoning techniques, the state-of-the-art methods in this field point to intelligent input data preparation for geographic models, which includes knowledge-supported discovery and chaining of data pre-processing functionalities, knowledge-driven (semi-)automatic workflow building (or service composition in the context of geographic web services) of data preprocessing, and artificial intelligent planning-based service composition as well as their parameter-settings. Lastly, we discuss the challenges and future research directions from the following aspects: Sharing and reusing of model data and workflows, integration of data discovery and processing functionalities, task-oriented input data preparation methods, and construction of knowledge bases for geographic modeling, all assisting with the development of an easy-to-use geographic modeling environment with intelligent input data preparation. Full article
Show Figures

Graphical abstract

Back to TopTop