ISPRS Int. J. Geo-Inf., Volume 10, Issue 4 (April 2021) – 75 articles

Environmental degradation, for example, by wind erosion, is a serious global problem. Despite the enormous research on this topic, complex methods considering all relevant factors remain unpublished. The main intent of our paper is to develop a methodological road map to identify key soil–climatic conditions that make soil vulnerable to wind and demonstrate the road map in a case study using a relevant data source. Potential wind erosion (PWE) results from soil erosivity and climate erosivity. Soil erosivity directly reflects the wind-erodible fraction and indirectly reflects the soil-crust factor, vegetation-cover factor and surface-roughness factor. The climatic erosivity directly reflects the drought in the surface layer, erosive wind occurrence and clay soil-specific winter regime, making these soils vulnerable to wind erosion. The novelty of our method lies in the following: (1) all relevant soil–climatic data of wind erosion are combined; (2) different soil types “sand” and “clay” are evaluated simultaneously with respect to the different mechanisms of wind erosion; and (3) a methodological road map enables its application for various conditions. Based on our method, it is possible to set threshold values that, when exceeded, trigger landscape adjustments, more detailed in situ measurements or indicate the need for specific management. Full article

Modeling the distribution of daily and hourly human mobility metrics is beneficial for studying underlying human travel patterns. In previous studies, some probability distribution functions were employed in order to establish a base for human mobility research. However, the selection of the most suitable distribution is still a challenging task. In this paper, we focus on modeling the distributions of travel distance, travel time, and travel speed. The daily and hourly trip data are fitted with several candidate distributions, and the best one is selected based on the Bayesian information criterion. A case study with online car-hailing data in Xi’an, China, is presented to demonstrate and evaluate the model fit. The results indicate that travel distance and travel time of daily and hourly human mobility tend to follow Gamma distribution, and travel speed can be approximated by Burr distribution. These results can contribute to a better understanding of online car-hailing travel patterns and establish a base for human mobility research. Full article

Earth observation (EO) data play a crucial role in monitoring ecosystems and environmental processes. Time series of satellite data are essential for long-term studies in this context. Working with large volumes of satellite data, however, can still be a challenge, as the computational environment with respect to storage, processing and data handling can be demanding, which sometimes can be perceived as a barrier when using EO data for scientific purposes. In particular, open-source developments which comprise all components of EO data handling and analysis are still scarce. To overcome this difficulty, we present Tools for Analyzing Time Series of Satellite Imagery (TATSSI), an open-source platform written in Python that provides routines for downloading, generating, gap-filling, smoothing, analyzing and exporting EO time series. Since TATSSI integrates quality assessment and quality control flags when generating time series, data quality analysis is the backbone of any analysis made with the platform. We discuss TATSSI’s 3-layered architecture (data handling, engine and three application programming interfaces (API)); by allowing three APIs (a native graphical user interface, some Jupyter Notebooks and the Python command line) this development is exceptionally user-friendly. Furthermore, to demonstrate the application potential of TATSSI, we evaluated MODIS time series data for three case studies (irrigation area changes, evaluation of moisture dynamics in a wetland ecosystem and vegetation monitoring in a burned area) in different geographical regions of Mexico. Our analyses were based on methods such as the spatio-temporal distribution of maxima over time, statistical trend analysis and change-point decomposition, all of which were implemented in TATSSI. Our results are consistent with other scientific studies and results in these areas and with related in-situ data. Full article

Passengers were unsatisfied with the navigation signs in Taipei station based on the Report on the Taiwan Railway Passenger Survey. This study conducted two experiments. Experiment 1 involved 14 participants using the present Taipei Main Station floor map to wayfinding, plan routes, and provide route descriptions for four specified destinations in the station. All participants were requested to recall the route that had just been taken and draw a cognitive map. In Experiment 2, 14 other participants were asked to perform the same tasks as Experiment 1 but with the new map. This study’s results showed that the codes used by the participants in Experiment 1 revealed the differences in walking route distance and number of turns. Escalators and stairs that connected floors were often used as reference landmarks for wayfinding. In Experiment 2, the overall wayfinding performance of the participants was improved by using the new map. The wayfinding time was reduced and the time spent in wayfinding among users was more uniform, and their route planning strategies used became consistent. The new map that facilitates consistent action strategies among users and corresponds perfectly to the actual environment is able to create useful spatial knowledge for users. Full article

This paper examines OpenStreetMap data quality at different stages of a participatory mapping process in seven slums in Africa and Asia. Data were drawn from an OpenStreetMap-based participatory mapping process developed as part of a research project focusing on understanding inequalities in healthcare access of slum residents in the Global South. Descriptive statistics and qualitative analysis were employed to examine the following research question: What is the spatial data quality of collaborative remote mapping achieved by volunteer mappers in morphologically complex urban areas? Findings show that the completeness achieved by remote mapping largely depends on the morphology and characteristics of slums such as building density and rooftop architecture, varying from 84% in the best case, to zero in the most difficult site. The major scientific contribution of this study is to provide evidence on the spatial data quality of remotely mapped data through volunteer mapping efforts in morphologically complex urban areas such as slums; the results could provide insights into how much fieldwork would be needed in what level of complexity and to what extent the involvement of local volunteers in these efforts is required. Full article

Prevention quality indicators (PQIs) constitute a set of measures that can be combined with hospital inpatient data to identify the quality of care for ambulatory care sensitive conditions (ACSC). Geographical information system (GIS) web mapping and applications contribute to a better representation of PQI spatial distribution. Unlike many countries in the world, in Portugal, this type of application remains underdeveloped. The main objective of this work was to facilitate the assessment of geographical patterns and trends of health data in Portugal. Therefore, two innovative open source applications were developed. Leaflet Javascript Library, PostGIS, and GeoServer were used to create a web map application prototype. Python language was used to develop the GIS application. The geospatial assessment of geographical patterns of health data in Portugal can be obtained through a GIS application and a web map application. Both tools proposed allowed for an easy and intuitive assessment of geographical patterns and time trends of PQI values in Portugal, alongside other relevant health data, i.e., the location of health care facilities, which, in turn, showed some association between the location of facilities and quality of health care. However, in the future, more research is still required to map other relevant data, for more in-depth analyses. Full article

Assessing the supply and demand of urban green space (UGS) ecosystem services (ESs) can provide relevant insights for urban planning. This study presents an analysis method for the spatial distribution of UGS ES supply and demand at administrative unit and 1-m grid scales and directly compares the matches of ES supply and demand in spatially explicit maps at two scales. Based on the analysis results at administrative unit scale, administrative units with an unbalanced UGS ES supply and demand were divided into three types: (Ⅰ) lack of green space; (Ⅱ) unreasonable green space structure; (Ⅲ) comprehensive, and different optimization schemes were put forward. According to the analysis results at 1-m scale, the regions with an unbalanced ES supply and demand of an administrative unit were divided into the following: (1) severe ES shortage area; (2) moderate ES shortage area; (3) mild ES shortage area, and the severe ES shortage area was taken as the UGS optimization area. We take the UGS within the 5th Ring Road of Beijing as an example and propose suggestions for optimizing the UGS pattern based on the evaluation of the supply and demand of UGS carbon sequestration services and purification services for particulate matter with an aerodynamic diameter <2.5 µm (PM_2.5). This study provides an easy-to-use evaluation method for the spatial distribution of UGS ES supply and demand and proposes different optimization suggestions for the unbalanced area, thus playing a role in UGS construction activities and green space structure optimization. Full article

Soils provide important regulating ecosystem services and have crucial implications for human well-being and environmental conservation. However, soil degradation and particularly soil erosion jeopardize the maintenance and existence of these services. This study explores the spatio–temporal relationships of soil erosion to understand the distribution patterns of sediment retention services in mainland Portugal. Based on Corine Land Cover maps from 1990 to 2018, the InVEST Sediment Delivery Ratio (SDR) model was used to evaluate the influence of sediment dynamics for soil and water conservation. Spatial differences in the sediment retention levels were observed within the NUTS III boundaries, showing which areas are more vulnerable to soil erosion processes. Results indicated that the Region of Leiria, Douro and the coastal regions have decreased importantly in sediment retention capacity over the years. However, in most of the territory (77.52%), changes in sediment retention were little or were not important (i.e., less than 5%). The statistical validation of the model proved the consistency of the results, demonstrating that the InVEST SDR model is an appropriate tool for estimating soil loss potential by water at regional/national levels, although having its limitations. These findings can be relevant to support strategies for more efficient land-use planning regarding soil erosion mitigation practices and to stimulate further investigation at a national level on this important ecosystem service. Full article

The space–time behaviour of COVID-19 needs to be analysed from microdata to understand the spread of the virus. Hence, 3D space–time bins and analysis of associated emerging hotspots are useful methods for revealing the areas most at risk from the pandemic. To implement these methods, we have developed the SITAR Fast Action Territorial Information System using ESRI technologies. We first modelled emerging hotspots of COVID-19 geocoded cases for the region of Cantabria (Spain), then tested the predictive potential of the method with the accumulated cases for two months ahead. The results reveal the difference in risk associated with areas with COVID-19 cases. The study not only distinguishes whether a bin is statistically significant, but also identifies temporal trends: a reiterative pattern is detected in 58.31% of statistically significant bins (most with oscillating behaviour over the period). In the testing method phase, with positive cases for two months ahead, we found that only 7.37% of cases were located outside the initial 3D bins. Furthermore, 83.02% of new cases were in statistically significant previous emerging hotspots. To our knowledge, this is the first study to show the usefulness of the 3D bins and GIS emerging hotspots model of COVID-19 microdata in revealing strategic patterns of the pandemic for geoprevention plans. Full article

In the light of climate change and burgeoning urbanization, heat loads in urban areas have emerged as serious issues, affecting the well-being of the population and the environment. In response to a pressing need for more standardised and communicable research into urban climate, the concept of local climate zones (LCZs) has been created. This concept aims to define the morphological types of (urban) surface with respect to the formation of local climatic conditions, largely thermal. This systematic review paper analyses studies that have applied the concept of LCZs to European urban areas. The methodology utilized pre-determined keywords and five steps of literature selection. A total of 91 studies were found eligible for analysis. The results show that the concept of LCZs has been increasingly employed and become well established in European urban climate research. Dozens of measurements, satellite observations, and modelling outcomes have demonstrated the characteristic thermal responses of LCZs in European cities. However, a substantial number of the studies have concentrated on the methodological development of the classification process, generating a degree of inconsistency in the delineation of LCZs. Recent trends indicate an increasing prevalence of the accessible remote-sensing based approach over accurate GIS-based methods in the delineation of LCZs. In this context, applications of the concept in fine-scale modelling appear limited. Nevertheless, the concept of the LCZ has proven appropriate and valuable to the provision of metadata for urban stations, (surface) urban heat island analysis, and the assessment of outdoor thermal comfort and heat risk. Any further development of LCZ mapping appears to require a standardised objective approach that may be globally applicable. Full article

Indonesia currently has 269 million people or 3.49% of the world’s total population and is ranked as the fourth most populous country in the world. Analysis by the Ministry of Public Works and Public Housing of Indonesia in 2010 shows that Java’s biocapacity is already experiencing a deficit. Therefore, optimization needs to be done to reduce deficits. This study aims to optimize and assess spatial allocation accuracy based on land-use/land cover suitability. In this study, the ecological footprint (EF) is utilized as a spatial allocation assessment based on physiological needs. The concept of land suitability aims for optimal and sustainable land use. Moreover, the land suitability model was conducted using the support vector machine (SVM). SVM is used to find the best hyperplane by maximizing the distance between classes. A hyperplane is a function that can be used to separate land-use/land cover types. The land suitability model’s overall-accuracy model was 86.46%, with a kappa coefficient value of 0.812. The final results show that agricultural land, plantations, and pastureland are still experiencing deficits, but there is some reduction. The deficit reduction for agricultural land reached 510,588.49 ha, 18,986.14 ha for plantations, and 1015.94 ha for pastures. The results indicate that the SVM algorithm is efficient in mapping the land-use suitability and optimizing spatial allocation. Full article

Point-Of-Interest (POI) recommendation not only assists users to find their preferred places, but also helps businesses to attract potential customers. Recent studies have proposed many approaches to the POI recommendation. However, the lack of negative samples and the complexities of check-in contexts limit their effectiveness significantly. This paper focuses on the problem of context-specific POI recommendation based on the check-in behaviors recorded by Location-Based Social Network (LBSN) services, which aims at recommending a list of POIs for a user to visit at a given context (such as time and weather). Specifically, a bidirectional influence correlativity metric is proposed to measure the semantic feature of user check-in behavior, and a contextual smoothing method to effectively alleviate the problem of data sparsity. In addition, the check-in probability is computed based on the geographical distance between the user’s home and the POI. Furthermore, to handle the problem of no negative feedback in LBSN, a weighted random sampling method is proposed based on contextual popularity. Finally, the recommendation results is obtained by utilizing Factorization Machine with Bayesian Personalized Ranking (BPR) loss. Experiments on a real dataset collected from Foursquare show that the proposed approach has better performance than others. Full article

In this work, we focus our attention on the similarity among works of art based on human poses and the actions they represent, moving from the concept of Pathosformel in Aby Warburg. This form of similarity is investigated by performing a pose clustering of the human poses, which are modeled as 2D skeletons and are defined as sets of 14 points connected by limbs. To build a dataset of properly annotated artwork images (that is, including the 2D skeletons of the human figures represented), we relied on one of the most popular, recent, and accurate deep learning frameworks for pose tracking of human figures, namely OpenPose. To measure the similarity between human poses, two alternative distance functions are proposed. Moreover, we developed a modified version of the K-Medians algorithm to cluster similar poses and to find a limited number of poses that are representative of the whole dataset. The proposed approach was also compared to two popular clustering strategies, that is, K-Means and the Nearest Point Algorithm, showing higher robustness to outliers. Finally, we assessed the validity of the proposed framework, which we named POSE-ID-on, in both a qualitative and in a quantitative way by simulating a supervised setting, since we lacked a proper reference for comparison. Full article

Through the power of new sensing technologies, we are increasingly digitizing the real world. However, instruments produce unstructured data, mainly in the form of point clouds for 3D data and images for 2D data. Nevertheless, many applications (such as navigation, survey, infrastructure analysis) need structured data containing objects and their geometry. Various computer vision approaches have thus been developed to structure the data and identify objects therein. They can be separated into model-driven, data-driven, and knowledge-based approaches. Model-driven approaches mainly use the information on the objects contained in the data and are thus limited to objects and context. Among data-driven approaches, we increasingly find deep learning strategies because of their autonomy in detecting objects. They identify reliable patterns in the data and connect these to the object of interest. Deep learning approaches have to learn these patterns in a training stage. Knowledge-based approaches use characteristic knowledge from different domains allowing the detection and classification of objects. The knowledge must be formalized and substitutes the training for deep learning. Semantic web technologies allow the management of such human knowledge. Deep learning and knowledge-based approaches have already shown good results for semantic segmentation in various examples. The common goal but the different strategies of the two approaches engaged our interest in doing a comparison to get an idea of their strengths and weaknesses. To fill this knowledge gap, we applied two implementations of such approaches to a mobile mapping point cloud. The detected object categories are car, bush, tree, ground, streetlight and building. The deep learning approach uses a convolutional neural network, whereas the knowledge-based approach uses standard semantic web technologies such as SPARQL and OWL2to guide the data processing and the subsequent classification as well. The LiDAR point cloud used was acquired by a mobile mapping system in an urban environment and presents various complex scenes, allowing us to show the advantages and disadvantages of these two types of approaches. The deep learning and knowledge-based approaches produce a semantic segmentation with an average F1 score of 0.66 and 0.78, respectively. Further details are given by analyzing individual object categories allowing us to characterize specific properties of both types of approaches. Full article

The main purpose of this study was to investigate the factors that discouraged Taiwan hoteliers from applying for green hotel certification. The analytic hierarchy process (AHP) method was used to perform a weighted analysis that comprehensively identified important hindering factors based on information from hotel industry, government, academic, and consumer representatives. Overall, in order of importance, the five dimensions of hindering factors identified by these experts and scholars were hotel internal environment, consumers’ environmental protection awareness, environmental protection incentive policy, hotel laws and regulations policy, and hotel external environment. Among the 26 examined hindering factor indices, the three highest-weighted indices overall for hoteliers applying for green hotel certification were as follows: environmental protection is not the main consideration of consumers seeking accommodations, lack of support by investment owners (shareholders), and lack of relevant subsidy incentives. The major contribution of this study is that hoteliers can understand important hindering factors associated with applying for green hotel certification; therefore, strategies that can encourage or enhance the green certification of hotels can be proposed to improve corporate image in the hotel industry, implement social responsibility in this industry, and obtain consumers’ approval of and accommodation-willingness for green hotels. Full article

High-resolution digital elevation models (HR-DEMs) originating from airborne laser scanning (ALS) point clouds must be transformed into Culvert-modified DEMs for hydrological and geomorphological analysis. To produce a culvert-modified DEM, information on the locations of drainage structures (DSs) (e.g., bridges and culverts) is essential. Nevertheless, DS mapping techniques, whether in connection with the development of new methods or an application setting of existing methods, have always been complicated. Consequently, wide area DS data are rare, making it challenging to produce a culvert-modified DEM in a wide area capacity. Alternatively, the breach algorithm (BA) method is a standard procedure to obtain culvert-modified DEMs in the absence of DS data, solving the problem to some extent. This paper addresses this shortcoming using a newly developed drainage structure mapping algorithm (DSMA) for obtaining a culvert-modified DEM for an area of 36 km² in Vermont, USA. Benchmark DS data are used as a standard reference to assess the performance of the DSMA method compared to the BA method. A consistent methodological framework is formulated to obtain a culvert-modified DEM using DS data, mapped using the DSMA and resultant culvert-modified DEM is then compared with BA method respectively. The DSs found from the culvert-modified DEMs were reported as true positive (TP), false positive (FP), and false negative (FN). Based on TP, FP, and FN originating from the culvert-modified DEMs of both methods, the evaluation metrics of the false positive rate (FPR) (i.e., the commission error) and false negative rate (FNR) (i.e., the omission error) were computed. Our evaluation showed that the newly developed DSMA-based DS data resulted in an FPR of 0.05 with federal highway authorities (FHWA) roads and 0.12 with non-FHWA roads. The FNR with FHWA roads was 0.07, and with non-FHWA roads, it was 0.38. The BA method showed an FPR of 0.28 with FHWA roads and 0.62 with non-FHWA roads. Similarly, the FNR for the BA method was 0.32 with FHWA roads and 0.61 with non-FHWA roads. The statistics based on the FPR and FNR showed that the DSMA-based culvert-modified DEM was more accurate compared with the BA method, and the formulated framework for producing culvert-modified DEMs using DSMA-based DS data was robust. Full article

The early identification of potential landslide hazards is of great practical significance for disaster early warning and prevention. The study used different machine learning methods to identify potential active landslides along a 15 km buffer zone on both sides of Jinsha River (Panzhihua-Huize section), China. The morphology and texture features of landslides were characterized with InSAR deformation monitoring data and high-resolution optical remote sensing data, combined with 17 landslide influencing factors. In the study area, 83 deformation accumulation areas of potential landslide hazards and 54 deformation accumulation areas of non-potential landslide hazards were identified through spatial overlay analysis with 64 potential active landslides, which have been confirmed by field verification. The Naive Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM) and Random Forest (RF) algorithms were trained and tested through attribute selection and parameter optimization. Among the 17 landslide influencing factors, Drainage Density, NDVI, Slope and Weathering Degree play an indispensable role in the machine learning and recognition of landslide hazards in our study area, while other influencing factors play a certain role in different algorithms. A multi-index (Precision, Recall, F1) comparison shows that the SVM (0.867, 0.829, 0.816) has better recognition precision skill for small-scale unbalanced landslide deformation datasets, followed by RF (0.765, 0.756, 0.741), DT (0.755, 0.756, 0.748) and NB (0.659, 0.659, 0.659). Different from the previous study on landslide susceptibility and hazard mapping based on machine learning, this study focuses on how to find out the potential active landslide points more accurately, rather than evaluating the landslide susceptibility of specific areas to tell us which areas are more sensitive to landslides. This study verified the feasibility of early identification of landslide hazards by using different machine learning methods combined with deformation information and multi-source landslide influencing factors rather than by relying on human–computer interaction. This study shows that the efficiency of potential hazard identification can be increased while reducing the subjective bias caused by relying only on human experts. Full article

Floods are among the most common natural hazards around the world. Mapping and evaluating potential flood hazards are essential for flood risk management and mitigation strategies, particularly in coastal areas. Several factors play significant roles in flooding and recognizing the role of these flood-related factors may enhance flood disaster prediction and mitigation strategies. This study focuses on using Shannon’s entropy model to predict the role of seven factors in causing floods in the Governorate of Muscat, Sultanate of Oman, and mapping coastal flood-prone areas. The seven selected factors (including ground elevation, slope degree, hydrologic soil group (HSG), land use, distance from the coast, distance from the wadi, and distance from the road) were initially prepared and categorized into classes based on their contribution to flood occurrence. In the next step, the entropy model was used to determine the weight and contribution of each factor in overall susceptibility. Finally, results from the previous two steps were combined using ArcGIS software to produce the final coastal flood susceptibility index map that was categorized into five susceptibility zones. The result indicated that land use and HSG are the most causative factors of flooding in the area, and about 133.5 km² of the extracted area is threatened by coastal floods. The outcomes of this study can provide decision-makers with essential information for identifying flood risks and enhancing adaptation and mitigation strategies. For future work, it is recommended to evaluate the reliability of the obtained result by comparing it with a real flooding event, such as flooding during cyclones Gonu and Phet. Full article

Public urban green spaces are important for the urban quality of life. Still, comprehensive open data sets on urban green spaces are not available for most cities. As open and globally available data sets, the potential of Sentinel-2 satellite imagery and OpenStreetMap (OSM) data for urban green space mapping is high but limited due to their respective uncertainties. Sentinel-2 imagery cannot distinguish public from private green spaces and its spatial resolution of 10 m fails to capture fine-grained urban structures, while in OSM green spaces are not mapped consistently and with the same level of completeness everywhere. To address these limitations, we propose to fuse these data sets under explicit consideration of their uncertainties. The Sentinel-2 derived Normalized Difference Vegetation Index was fused with OSM data using the Dempster–Shafer theory to enhance the detection of small vegetated areas. The distinction between public and private green spaces was achieved using a Bayesian hierarchical model and OSM data. The analysis was performed based on land use parcels derived from OSM data and tested for the city of Dresden, Germany. The overall accuracy of the final map of public urban green spaces was 95% and was mainly influenced by the uncertainty of the public accessibility model. Full article

Due to the vast amount of available tracking sensors in recent years, high-frequency and high-volume streams of data are generated every day. The maritime domain is no different as all larger vessels are obliged to be equipped with a vessel tracking system that transmits their location periodically. Consequently, automated methodologies able to extract meaningful information from high-frequency, large volumes of vessel tracking data need to be developed. The automatic identification of vessel mobility patterns from such data in real time is of utmost importance since it can reveal abnormal or illegal vessel activities in due time. Therefore, in this work, we present a novel approach that transforms streaming vessel trajectory patterns into images and employs deep learning algorithms to accurately classify vessel activities in near real time tackling the Big Data challenges of volume and velocity. Two real-world data sets collected from terrestrial, vessel-tracking receivers were used to evaluate the proposed methodology in terms of both classification and streaming execution performance. Experimental results demonstrated that the vessel activity classification performance can reach an accuracy of over $96\%$ while achieving sub-second latencies in streaming execution performance. Full article

For full description of images’ semantic information, image retrieval tasks are increasingly using deep convolution features trained by neural networks. However, to form a compact feature representation, the obtained convolutional features must be further aggregated in image retrieval. The quality of aggregation affects retrieval performance. In order to obtain better image descriptors for image retrieval, we propose two modules in our method. The first module is named generalized regional maximum activation of convolutions (GR-MAC), which pays more attention to global information at multiple scales. The second module is called saliency joint weighting, which uses nonparametric saliency weighting and channel weighting to focus feature maps more on the salient region without discarding overall information. Finally, we fuse the two modules to obtain more representative image feature descriptors that not only consider the global information of the feature map but also highlight the salient region. We conducted experiments on multiple widely used retrieval data sets such as roxford5k to verify the effectiveness of our method. The experimental results prove that our method is more accurate than the state-of-the-art methods. Full article

The discovery of spatio-temporal dependencies within urban road networks that cause Recurrent Congestion (RC) patterns is crucial for numerous real-world applications, including urban planning and the scheduling of public transportation services. While most existing studies investigate temporal patterns of RC phenomena, the influence of the road network topology on RC is often overlooked. This article proposes the ST-Discovery algorithm, a novel unsupervised spatio-temporal data mining algorithm that facilitates effective data-driven discovery of RC dependencies induced by the road network topology using real-world traffic data. We factor out regularly reoccurring traffic phenomena, such as rush hours, mainly induced by the daytime, by modelling and systematically exploiting temporal traffic load outliers. We present an algorithm that first constructs connected subgraphs of the road network based on the traffic speed outliers. Second, the algorithm identifies pairs of subgraphs that indicate spatio-temporal correlations in their traffic load behaviour to identify topological dependencies within the road network. Finally, we rank the identified subgraph pairs based on the dependency score determined by our algorithm. Our experimental results demonstrate that ST-Discovery can effectively reveal topological dependencies in urban road networks. Full article

Basin geomorphology is a complete system of landforms and topographic features that play a crucial role in the basin-scale flood risk evaluation. Nepal is a country characterized by several rivers and under the influence of frequent floods. Therefore, identifying flood risk areas is of paramount importance. The East Rapti River, a tributary of the Ganga River, is one of the flood-affected basins, where two major cities are located, making it crucial to assess and mitigate flood risk in this river basin. A morphometric calculation was made based on the Shuttle Radar Topographic Mission (SRTM) 30-m Digital Elevation Model (DEM) in the Geographic Information System (GIS) environment. The watershed, covering 3037.29 km² of the area has 14 sub-basins (named as basin A up to N), where twenty morphometric parameters were used to identify flash flood potential sub-basins. The resulting flash flood potential maps were categorized into five classes ranging from very low to very high-risk. The result shows that the drainage density, topographic relief, and rainfall intensity have mainly contributed to flash floods in the study area. Hence, flood risk was analyzed pixel-wise based on slope, drainage density, and precipitation. Existing landcover types extracted from the potential risk area indicated that flash flood is more frequent along the major Tribhuvan Rajpath highway. The landcover data shows that human activities are highly concentrated along the west (Eastern part of Bharatpur) and the east (Hetauda) sections. The study concludes that the high human concentrated sub-basin “B” has been categorized as a high flood risk sub-basin; hence, a flood-resilient city planning should be prioritized in the basin. Full article

Operating with ignorance is an important concern of geographical information science when the objective is to discover knowledge from the imperfect spatial data. Data mining (driven by knowledge discovery tools) is about processing available (observed, known, and understood) samples of data aiming to build a model (e.g., a classifier) to handle data samples that are not yet observed, known, or understood. These tools traditionally take semantically labeled samples of the available data (known facts) as an input for learning. We want to challenge the indispensability of this approach, and we suggest considering the things the other way around. What if the task would be as follows: how to build a model based on the semantics of our ignorance, i.e., by processing the shape of “voids” within the available data space? Can we improve traditional classification by also modeling the ignorance? In this paper, we provide some algorithms for the discovery and visualization of the ignorance zones in two-dimensional data spaces and design two ignorance-aware smart prototype selection techniques (incremental and adversarial) to improve the performance of the nearest neighbor classifiers. We present experiments with artificial and real datasets to test the concept of the usefulness of ignorance semantics discovery. Full article

Building and road extraction from remote sensing images is of great significance to urban planning. At present, most of building and road extraction models adopt deep learning semantic segmentation method. However, the existing semantic segmentation methods did not pay enough attention to the feature information between hidden layers, which led to the neglect of the category of context pixels in pixel classification, resulting in these two problems of large-scale misjudgment of buildings and disconnection of road extraction. In order to solve these problem, this paper proposes a Non-Local Feature Search Network (NFSNet) that can improve the segmentation accuracy of remote sensing images of buildings and roads, and to help achieve accurate urban planning. By strengthening the exploration of hidden layer feature information, it can effectively reduce the large area misclassification of buildings and road disconnection in the process of segmentation. Firstly, a Self-Attention Feature Transfer (SAFT) module is proposed, which searches the importance of hidden layer on channel dimension, it can obtain the correlation between channels. Secondly, the Global Feature Refinement (GFR) module is introduced to integrate the features extracted from the backbone network and SAFT module, it enhances the semantic information of the feature map and obtains more detailed segmentation output. The comparative experiments demonstrate that the proposed method outperforms state-of-the-art methods, and the model complexity is the lowest. Full article

Global sensitivity analysis, like variance-based methods for massive raster datasets, is especially computationally costly and memory-intensive, limiting its applicability for commodity cluster computing. The computational effort depends mainly on the number of model runs, the spatial, spectral, and temporal resolutions, the number of criterion maps, and the model complexity. The current Spatially-Explicit Uncertainty and Sensitivity Analysis (SEUSA) approach employs a cluster-based parallel and distributed Python–Dask solution for large-scale spatial problems, which validates and quantifies the robustness of spatial model solutions. This paper presents the design of a framework to perform SEUSA as a Service in a cloud-based environment scalable to very large raster datasets and applicable to various domains, such as landscape assessment, site selection, risk assessment, and land-use management. It incorporates an automated Kubernetes service for container virtualization, comprising a set of microservices to perform SEUSA as a Service. Implementing the proposed framework will contribute to a more robust assessment of spatial multi-criteria decision-making applications, facilitating a broader access to SEUSA by the research community and, consequently, leading to higher quality decision analysis. Full article

Topographic features of territory have a significant impact on the spatial distribution of soil properties. This research is focused on digital soil mapping (DSM) of main agrochemical soil properties—values of soil organic carbon (SOC), nitrogen, potassium, calcium, magnesium, sodium, phosphorus, pH, and thickness of the humus-accumulative (AB) horizon of arable lands in the Trans-Ural steppe zone (Republic of Bashkortostan, Russia). The methods of multiple linear regression (MLR) and support vector machine (SVM) were used for the prediction of soil nutrients spatial distribution and variation. We used 17 topographic indices calculated using the SRTM (Shuttle Radar Topography Mission) digital elevation model. Results showed that SVM is the best method in predicting the spatial variation of all soil agrochemical properties with comparison to MLR. According to the coefficient of determination R², the best predictive models were obtained for content of nitrogen (R² = 0.74), SOC (R² = 0.66), and potassium (R² = 0.62). In our study, elevation, slope, and MMRTF (multiresolution ridge top flatness) index are the most important variables. The developed methodology can be used to study the spatial distribution of soil nutrients and large-scale mapping in similar landscapes. Full article

Generation of a thematic map is important for scientists and agriculture engineers in analyzing different crops in a given field. Remote sensing data are well-accepted for image classification on a vast area of crop investigation. However, most of the research has currently focused on the classification of pixel-based image data for analysis. The study was carried out to develop a multi-category crop hyperspectral image classification system to identify the major crops in the Chiayi Golden Corridor. The hyperspectral image data from CASI (Compact Airborne Spectrographic Imager) were used as the experimental data in this study. A two-stage classification was designed to display the performance of the image classification. More specifically, the study used a multi-class classification by support vector machine (SVM) + convolutional neural network (CNN) for image classification analysis. SVM is a supervised learning model that analyzes data used for classification. CNN is a class of deep neural networks that is applied to analyzing visual imagery. The image classification comparison was made among four crops (paddy rice, potatoes, cabbages, and peanuts), roads, and structures for classification. In the first stage, the support vector machine handled the hyperspectral image classification through pixel-based analysis. Then, the convolution neural network improved the classification of image details through various blocks (cells) of segmentation in the second stage. A series of discussion and analyses of the results are presented. The repair module was also designed to link the usage of CNN and SVM to remove the classification errors. Full article

Semantic segmentation has been widely used in the basic task of extracting information from images. Despite this progress, there are still two challenges: (1) it is difficult for a single-size receptive field to acquire sufficiently strong representational features, and (2) the traditional encoder-decoder structure directly integrates the shallow features with the deep features. However, due to the small number of network layers that shallow features pass through, the feature representation ability is weak, and noise information will be introduced to affect the segmentation performance. In this paper, an Adaptive Multi-Scale Module (AMSM) and Adaptive Fuse Module (AFM) are proposed to solve these two problems. AMSM adopts the idea of channel and spatial attention and adaptively fuses three-channel branches by setting branching structures with different void rates, and flexibly generates weights according to the content of the image. AFM uses deep feature maps to filter shallow feature maps and obtains the weight of deep and shallow feature maps to filter noise information in shallow feature maps effectively. Based on these two symmetrical modules, we have carried out extensive experiments. On the ISPRS Vaihingen dataset, the F1-score and Overall Accuracy (OA) reached 86.79% and 88.35%, respectively. Full article

The industry of intangible cultural heritage (ICH) tourism continues to grow, and social media can serve as an essential tool to promote this trend. Although ICH tourism development is outstanding in China, the language structure and restricted use of social media render ICH difficult for non-Chinese speakers to understand. Using content analysis, this study investigates the structure and relationships among cognitive elements of ICH tourism based on 9074 blogs posted between 2011 and 2020 on Weibo.com, one of the most popular social media platforms in China. The main analysis process consisted of matrix construction, dimension classification, and semantic network analysis. Findings indicated that the cognitive image of ICH tourism on social media can be divided into seven dimensions: institutions, ICH and inheritors, tourism products, traditional festivals and seasons, tourism facilities and services, visitors, and regions. This network vividly illustrates ICH tourism and depicts the roles of organizers, residents, inheritors, and tourists. Among these elements, institutions hold the greatest power to regulate and control ICH tourism activities, and folklore appears to be the most common type of ICH resource that can be developed into tourism activities. Practically, the results offer insight for policymakers regarding ways to better balance the relationships among heritage protection, the business economy, and people’s well-being. Such strategies can promote the industrialization of ICH tourism. In addition, through content analysis, this paper confirms the effectiveness of social media in providing a richer understanding of ICH tourism. Full article