Search

In the wake of the COVID-19 pandemic, global efforts to mitigate the spread of the virus have led to widespread lockdowns and movement restrictions. Earlier studies have reported a notable positive correlation between nitrogen dioxide (NO2) levels and mobility during the initial 2020 lockdowns. However, our explorative investigation in Southeast Asia observed that, despite their similar spatial distribution, NO2 does not consistently align with mobility patterns. This observation indicates the existence of additional influential factors apart from mobility contributing to NO2 variation, necessitating a more comprehensive examination. Subsequently, we developed a trained Multi-Layer Perceptron (MLP) model and leveraged SHapley Additive exPlanations (SHAP) values. Our analysis extends beyond mobility to encompass diverse potential factors such as travel modes and meteorological factors. The model results suggest that, while as expected mobility has a strong impact on NO2 column density, a more accurate prediction requires considering different travel modes (i.e. driving and walking). Furthermore, the study reveals that spatio-temporal heterogeneity and meteorological factors also play roles in shaping NO2 level. These findings emphasize the importance of integrating such multifaceted considerations in future NO2 study for a more accurate and holistic understanding.

Spatial characteristics and geographical scales are crucial factors influencing the functioning of ecosystem services (ESs), especially the spatial flows that transcend territorial boundaries. A comprehensive understanding of the spatiotemporal evolution of these spatial spillover effects enriches our knowledge on the distribution and temporal dynamics of ecosystem service functions. By examining the spatiotemporal evolution of ecosystem service flow effects of the Yangtze River Economic Belt (YREB), the study offers scientific evidence underpinning the sustainable development of ESs among different regions. To this end, this study undertook the computation of ecosystem service values (ESV) and utilized an improved gravitational model to establish the ESV spatial correlation network (SCN) in the YREB. Subsequently, social network analysis (SNA) was employed to examine the spatiotemporal evolution of the ESV-SCN. Finally, an analytical framework was constructed to scrutinize the factors that influence the ESV-SCN under the influences of both natural and socio-economic factors. The results suggest: 1) Between the years 1990 and 2020, ESV within the YREB exhibited substantial spatial correlations and overflow effects, with a notable 3.49% increase in network density; 2) The hierarchical structure of the ESV-SCN witnessed a 44.51% decline, while network efficiency witnessed an 8.47% increase. Moreover, network accessibility strengthened, and the discernible presence of multiple overlapping effects contributed to heightened stability; 3) Both within and between various sectors of the ESV-SCN, substantial linkages and cascading effects were noted. The spatiotemporal evolution of the SCN exhibited distinct hierarchical and clustering patterns, with the complexity of the network structure steadily augmenting; 4) Natural factors such as temperature, precipitation, the proportion of forest land, alongside socio-economic factors like the level of economic development and innovation, all played indispensable roles in shaping and nurturing the ESV spatial correlation networks.

The balance between the supply and demand of ecosystem services (ESSD) is important for sustainable regional development. The hilly regions of south China have rich natural resources and are rapidly being urbanized, which significantly impacts sustainable development in the region. Therefore, how to analyze ESSD from the perspective of social ecology is imperative. Ganzhou region, which is a typical hilly region in southern China, as an example, this paper creatively integrated ESSD into the social-ecological system (SES) framework, analyzed the spatial and temporal changes of ESSD in 2005, 2010, 2015, and 2020, and constructed a system of indicators from the SES, and analyzed the driving factors of ESSD, so as to provide a reference for balancing ESSD. Based on the classical SES framework proposed by Ostrom, this study first analyses the social-ecological system profile of the Ganzhou region at the macro-scale and constructs an SES indicator system. The innovation of combining the SES framework and ecosystem services lies in integrating the social and ecosystem perspectives and merging these two concepts to understand better and manage the relationship between humans and the natural environment. It provides a comprehensive analytical approach and decision support tool for achieving sustainable development. Our results demonstrate that: (1) From 2005 to 2020, ecosystem services in the study area were highly valued, lower areas had homogeneous distribution characteristics, total demand displayed spatial differentiation, there were high-value areas in the midwest, and low-value areas were concentrated in the region’s boundary. (2) There are obvious supply and demand deficits in the southeast and east of the study area, while supply–demand is equal in the north and supply exceeds demand in other regions. From 2005 to 2020, the overall coupling coordination degree of ESSD in the study area was lower than 0.5, indicating a mild to moderate imbalance. (3) The supply of ecosystem services (ESS) was primarily driven by carbon storage, habitat quality, and water yield, while the demand was primarily driven by forest and grassland areas. Factors related to the ecosystem, resource unit, resource system, social system, governance system, and actor all have experienced two-factor interactions, which can explain up to 99% of ESSD. Based on the SES framework, this paper studies the relationship between ESSD in typical areas of the southern hills to provide a reference for research on ESSD in relevant areas and provide a scientific basis for the Chinese government to evaluate ecological protections and improve compensation policies, which is important for ensuring China's ecological security.

Regional ecological risk assessment (ERA) is an important means towards sustainable regional development. Yet, existing ERA approaches often fall short of characterizing ecological processes as dynamic processes involving uncertainty. Using Inner Mongolia, a high ecological risk area in China, this study employed a framework for regional ERA that considers ecosystem service value (ESV) and four scenarios of future land use patterns to understand its regional ecological risk. The spatially explicit risk assessment method was implemented by a model combining multi-criteria evaluation (MCE), cellular automata (CA), and Markov chain to predict future land use/cover of 2030, an adjustment-based equivalence factor method to assess the ESV in each scenario, and Sharpe Index to assess regional ecological risk. The results show the following. First, the overall ESV increases from 2020 to 2030 under all but the socio-economic development (SED) scenarios considered in this study. Second, the overall regional ecological risk of Inner Mongolia is high in the central region and low in the east, north, and west regions. The low ecological risk areas account for the largest areal proportion in the ecosystem services protection (ESP) and natural development (ND) scenarios, while the medium ecological risk areas are the largest under SED. However, some low ecological risk areas are converted into medium ecological risk in ecological and socioeconomic balance scenario (ESB) scenario. Third, NDVI is the driving factor with the strongest explanatory power for the regional ecological risk in Inner Mongolia, followed by mean annual precipitation and temperature. The present study applied a framework for regional ERA that explicitly considers spatial heterogeneity and uncertainty, which can be useful for guiding decision-making for ecological risk control and the planning of the land use of ecosystems.

Infectious disease spreading is a spatial interaction process. Assessing community vulnerability to infectious diseases thus requires not only information on local demographic and built environmental conditions, but also insights into human activity interactions with neighboring areas that can lead to the transition of vulnerability from locations to locations. This study presented an analytical framework based on the Particle Swarm Optimization model to estimate the weights of the factors for vulnerability modeling, and a local proportional parameter for use in the integration of the local and neighboring area risks. A country model and five cross-region validation models were developed for the case study of Singapore to assess the vulnerability to COVID-19. The results showed that the identified weights for the factors were robust throughout the optimization process and across various models. The local proportional parameter could be set slightly higher in between 0.6 and 0.8 (out of 1), signifying that the local effect was higher than the neighboring effect. Computation of the weights from the optimal solutions for the integrated vulnerability index showed that the factors of human activity intensity and accessibility to amenities had much higher weights, at 0.5 and 0.3, respectively. Conversely, the weights of population density, elderly population, social economic status and land use diversity were much lower. These findings underscored the importance of considering non-equal weights for factors and incorporating spatial interactions between local and neighboring areas for vulnerability modeling, to provide to a more comprehensive assessment of vulnerability to infectious diseases.

As one of the first ecological civilization demonstration areas in China, Guizhou Province, an underdeveloped region, experienced rapid economic development. The resulting human activities at an accelerated rate in Guizhou Province put great pressure on its environmental carrying capacity, especially the Karst landscape in the region. Understanding the relationship between urbanization and ecosystem services in Guizhou Province is indispensable for the sustainable development of the region in the future. Based on remote sensing data from 1990 to 2020, this study explores the spatiotemporal dynamics of ecosystem services value (ESV) and urbanization, as well as the degree of coupling and coordination (CCD) between them. The result suggested that between 1990 and 2020, the ESV of Guizhou Province showed a two-step decline due to the conversion of forest land for agricultural and urban usage. In addition, the ESV of the western region is lower than its eastern counterpart. The CCD level between ESV and urbanization has increased over time, but most areas are still in an unbalanced state of development. Most areas are mainly urbanization lagging, but the central and north-central research areas are mainly ESV lagging. Identifying the regional differences of coupling coordination types has shed light on the degree of contradiction between local urbanization and ESV, and helped find the balance between ecological sustainability and urbanization.

Classifying point cloud of urban landscapes plays essential roles in many urban applications. However, automating such a task is challenging due to irregular point distribution and complex urban scenes. Incorporating contextual information is crucial in improving classification accuracy of point clouds. In this article, we propose a hierarchical approach for point cloud classification with 3-D contextual features, which comprises three steps:segment-based classification with primitive features and a random forest classifier; extracting novel 3-D contextual features from the initial labels considering spatial relationships between neighboring segments and semantic dependencies; and refining classification with a combination of primitive features and spatial contextual features, and a hierarchical multilayer perceptron classifier that considers primitive features and spatial contextual features at different levels. The proposed method was tested on two point cloud datasets:the National University of Singapore (NUS) dataset and the Vaihingen benchmark dataset of the International Society of Photogrammetry and Remote Sensing. The evaluation results showed that the proposed method achieved an overall accuracy of 92.51% and 82.34% for the NUS dataset and Vaihingen dataset, respectively. The feature importance evaluation showed that 3-D spatial contextual features contributed useful information for discriminating different classes, such as roof, facade, grassland, tree, and ground. Quantitative comparisons further showed that the proposed method is more advantageous, especially in the detection of class roof and facade.

Recent research has shown the advantages of incorporating multisource geospatial data into the classification of urban functional zones (UFZs), particularly remote sensing and social sensing data. However, the effects of combining datasets of varying quality have not been thoroughly analyzed. In addition, human mobility patterns from social sensing data, which capture signals of human activities, are often represented by origin-destination pairs, thus ignoring spatial relationships between UFZs embedded in mobility trajectories. To address the aforementioned issues, this study proposed a graph-based UFZ classification framework that fuses semantic features from high spatial resolution (HSR) remote sensing images, points of interest, and GPS trajectory data. The framework involves three main steps: (1) High-level scene information in HSR remote sensing imageries was extracted through deep neural networks, and multisource semantic embeddings were constructed based on physical features and social sensing features from multiple geospatial data sources; (2) UFZ mobility graph was constructed by spatially joining trajectory information with UFZs to construct topological connections between functional parcel segments; and (3) UFZ segments and multisource semantic features were transformed into nodes and embeddings in the mobility graphs, and subsequently graph-based models were adopted to identify UFZs. The proposed framework was tested on Zhuhai and Singapore datasets. Results indicated that it outperformed traditional classification methods with an overall accuracy of 76.7% and 84.5% for Zhuhai and Singapore datasets, respectively. The proposed framework contributes to literature in heterogeneous data fusion and is generalizable to other UFZ classification scenarios where human mobility patterns play a role.

Rapid expansions of urban areas and the intensification of human activities have severely impacted ecosystems and ecosystem service provisions. Considering limited availability of ecosystem services, the evaluation of ecosystem service value should consider its fluctuations supply and demand due to urbanization, i.e., the ecosystem service scarcity value (ESSV). Taking typical arid and semiarid regions of China and the Ningxia Hui Autonomous Region as an example, the effects of different scarcity factors on the scarcity value of ecosystem services were compared. At the same time, a geographically weighted regression model (GWR) was developed to analyze the spatial relationships between urbanization and the scarcity value of ecosystem services. The results suggest that demand-driven scarcity is the most important factor affecting the ESSV in Ningxia, and between 1990 and 2015, the ESSV in Ningxia increased significantly, with increase being more evident from 2005 to 2015. Among the different types of ecosystem services, the scarcity values of ecosystem services such as air quality, waste treatment, soil retention, biodiversity services, and recreation and culture increased significantly from 1990 to 2015. Spatially, the total ESSV and the ESSV of different ecosystem service types exhibited evident spatial heterogeneity due, to spatial distribution characteristics of land-use type, population density and per capita GDP. The GWR modeling result shows, that the impact of urbanization on ESSV was positively correlated overall. The ESSV of food production, raw material, air quality, climate regulation and water supply are greatly affected by urbanization, while the ESSV of biodiversity services and recreation and culture are less affected by urbanization. Meanwhile, the High-Low type and Low-High type had significant aggregation effects in the study area.

This article introduces a digital platform for collaborative research on the Chinese diaspora in Southeast Asia, focusing on networks of Chinese temples and associations extending from Southeast China to the various port cities of Southeast Asia. The Singapore Historical Geographic Information System (SHGIS) and the Singapore Biographical Database (SBDB) are expandable WebGIS platforms gathering and linking data on cultural and religious networks across Southeast Asia. This inter-connected platform can be expanded to cover not only Singapore but all of Southeast Asia. We have added layers of data that go beyond Chinese Taoist, Buddhist, and popular god temples to also display the distributions of a wide range of other religious networks, including Christian churches, Islamic mosques, Hindu temples, and Theravadin, which are the Taiwanese, Japanese and Tibetan Buddhist monasteries found across the region. This digital platform covers a larger area than the Taiwan History and Culture in Time and Space (THCTS) historical GIS platform but is more regionally focused than the ECAI (Electronic Cultural Atlas Initiative) By incorporating Chinese inscriptions, extensive surveys of Chinese temples and associations, as well as archival and historical sources, this platform provides new materials and new perspectives on the Chinese diaspora in Southeast Asia. This paper: (1) outlines key research questions underlying these digital humanities platforms; (2) describes the overall architecture and the kinds of data included in the SHGIS and the SBDB; (3) reviews past research on historical GIS; and provides (4) a discussion of how incorporating Chinese epigraphy of Southeast Asia into these websites can help scholars trace networks across the entire region, potentially enabling comparative work on a wide range of religious networks in the region. Part 5 of the paper outlines technical aspects of the WebGIS platform.

Opisthorchis viverrini infection is an important, human, parasitic disease along the middle and lower Mekong River of Southeast Asia. Despite vast efforts in epidemiological research, the wide geographical variation in O. viverrini prevalence remains unexplained. To investigate the potential influence of village location, prevalence data recorded during the year 2009 for 90 villages in northeast Thailand were analysed by a geographical information systems approach based on a digital elevation model for altitude determination. Land use compositions of village surroundings were derived from images produced by the Thematic Mapper of the Landsat satellite and landscape metrics were applied to quantify spatial patterns. Pearson’s correlation coefficients were used to evaluate the associations between the environmental factors and O. viverrini prevalence. In spite of no statistical difference (P = 0.117), higher-ground villages generally had a lower level of opisthorchiasis than those situated lower down, while a significant negative correlation was detected between O. viverrini prevalence and the composition of farmland with low water content (P = 0.028), indicating the potential influence of agricultural lands with drought-tolerant crops. Strengthening this hypothesis, a significant positive association with O. viverrini prevalence was found for the combined land use classes of water and of farmland with high water content (P = 0.032), indicating that the dominance of a large land use patch capable of providing suitable habitats for the intermediate hosts might contribute to the disease. This study highlights the influence of landscapes on the epidemiology of O. viverrini infection and emphasises the need to incorporate land use planning into control strategies.

The automating classification of point clouds capturing urban scenes is critical for supporting applications that demand three-dimensional (3D) models. Achieving this goal, however, is met with challenges because of the varying densities of the point clouds and the complexity of the 3D data. In order to increase the level of automation in the point cloud classification, this study proposes a segment-based parameter learning method that incorporates a two-dimensional (2D) land cover map, in which a strategy of fusing the 2D land cover map and the 3D points is first adopted to create labelled samples, and a formalized procedure is then implemented to automatically learn the following parameters of point cloud classification: the optimal scale of the neighborhood for segmentation, optimal feature set, and the training classifier. It comprises four main steps, namely: (1) point cloud segmentation; (2) sample selection; (3) optimal feature set selection; and (4) point cloud classification. Three datasets containing the point cloud data were used in this study to validate the efficiency of the proposed method. The first two datasets cover two areas of the National University of Singapore (NUS) campus while the third dataset is a widely used benchmark point cloud dataset of Oakland, Pennsylvania. The classification parameters were learned from the first dataset consisting of a terrestrial laser-scanning data and a 2D land cover map, and were subsequently used to classify both of the NUS datasets. The evaluation of the classification results showed overall accuracies of 94.07% and 91.13%, respectively, indicating that the transition of the knowledge learned from one dataset to another was satisfactory. The classification of the Oakland dataset achieved an overall accuracy of 97.08%, which further verified the transferability of the proposed approach. An experiment of the point-based classification was also conducted on the first dataset and the result was compared to that of the segment-based classification. The evaluation revealed that the overall accuracy of the segment-based classification is indeed higher than that of the point-based classification, demonstrating the advantage of the segment-based approaches.

Naïve Geography, intelligent geographical information systems (GIS), and spatial data mining especially from social media all rely on natural-language spatial relations (NLSR) terms to incorporate commonsense spatial knowledge into conventional GIS and to enhance the semantic interoperability of spatial information in social media data. Yet, the inherent fuzziness of NLSR terms makes them challenging to interpret. This study proposes to interpret the fuzzy semantics of NLSR terms using the fuzzy random forest (FRF) algorithm. Based on a large number of fuzzy samples acquired by transforming a set of crisp samples with the random forest algorithm, two FRF models with different membership assembling strategies are trained to obtain the fuzzy interpretation of three line-region geometric representations using 69 NLSR terms. Experimental results demonstrate that the two FRF models achieve good accuracy in interpreting line-region geometric representations using fuzzy NLSR terms. In addition, fuzzy classification of FRF can interpret the fuzzy semantics of NLSR terms more fully than their crisp counterparts.

Integrated pest management (IPM) involves integrating multiple pest control methods based on site information obtained through inspection, monitoring, and reports. IPM has been deployed to achieve the judicious use of pesticides and has become one of the most important methods of securing agricultural productivity. Despite the efforts made to strengthen IPM during the past decades, overuse as well as indiscriminate use of pesticides is still common. This problem is particularly serious in underserved farming communities which suffer from ineffectiveness with respect to pest management information collection and dissemination. The recent development of volunteered geographic information (VGI) offers an opportunity to the general public to create and receive ubiquitous, cost-effective, and timely geospatial information. Therefore, this study proposes to enhance IPM through establishing a VGI-based IPM. As a starting point of this line of research, this study explored how such geospatial information can contribute to IPM enhancement. Based on this, a conceptual framework of VGI interaction was built to guide the establishment of VGI-based IPM. To implement VGI-based IPM, a mobile phone platform was developed. In addition, a case study was conducted in the town of Shuibian in Jiangxi province of China to demonstrate the effectiveness of the proposed approach. In the case study, by analyzing infestation incidents of an overwintering outbreak of striped rice stem borers voluntarily reported by farmers through mobile phones, spatiotemporal infestation patterns of the borers throughout the study area were revealed and disseminated to the farmers. These patterns include the dates and degree-days the pest infestations intensified, and the orientation or spatial structural variations of the clustering of the infestations. This case study showcased the unique merit of VGI in enhancing IPM, namely the acquisition of previously unrecorded spatial data in a cost-effective and real-time manner for discovering and disseminating previously unknown pest management knowledge.

Previous studies of meta-analyses found significantly positive correlations between primate species richness and rainfall for Africa, Madagascar and the Neotropics, with the exception of Asia, leaving the open question whether that anomaly is the result of sampling bias, biogeography, or some other factor. This study re-examines the question using modelled data, with primate species richness data from the Southeast Asian Mammals Databank and rainfall data from the Climatic Research Unit. Data processing with Geographical Information Systems resulted in 390 sample points. Reduced major axis and ordinary least squares regressions were employed to examine the relationship for six regions, including the whole study area of Southeast Asia, and the subareas of Huxley West, Huxley East, Mainland Southeast Asia, Borneo, and Sumatra. The results showed a significant positive relationship between primate species richness and mean annual rainfall for Southeast Asia (r = 0.26, P

Simplification of three-dimensional (3D) buildings is critical to improve the efficiency of visualizing urban environments while ensuring realistic urban scenes. Moreover, it underpins the construction of multi-scale 3D city models (3DCMs) which could be applied to study various urban issues. In this paper, we design a generic yet effective approach for simplifying 3D buildings. Instead of relying on both semantic information and geometric information, our approach is based solely on geometric information as many 3D buildings still do not include semantic information. In addition, it provides an integrated means to treat 3D buildings with either sloped or flat roofs. The two case studies, one exploring simplification of individual 3D buildings at varying levels of complexity while the other, investigating the multi-scale simplification of a cityscape, show the effectiveness of our approach.