Artificial intelligence enhanced litter pollution mapping: Integrating citizen science with geospatial and social data

Validation of a bathymetric monitoring method for the coastal zone using multimodal geospatial data fusion from unmanned measurement platforms

Vertical 15-minute city: Modeling urban density and functional mix with multi-source geospatial data

Remote sensing science is expected to produce spatio-temporal indicators to help societies to address major global challenges. In this regard, we have implemented the CHOVE-CHUVA web platform to monitor socio-environmental dynamics in the Brazilian Amazon state of Mato Grosso. Result of a long-term collaboration between research labs, local NGOs, and administrations, this Space for Climate Observatory initiative relies on two major pillars: (1) visualizing and computing spatio-temporal indices derived from Earth Observation data and (2) collecting citizen information as part of collaborative science. A major asset of the platform is to gather, visualize, and process data covering a wide range of themes such as land status, land use, climate, natural vegetation, agriculture, and hydrology. The collaborative information refers to land use types that are still unusual in Mato Grosso, i.e., forest restoration and low-carbon agricultural practices. The implementation of the platform was based on a French open source geospatial data infrastructure named PRODIGE. Prospects for enhancing the platform include integrating new thematic information, making better use of raw Earth Observation data, improving interactions with end-users to better capture their interpretation of socio-environmental dynamics, and improving the platform's efficiency to update data and process large study areas.

Abstract With the progression of climate change, Central Europe faces an increasing risk of extreme weather events, particularly floods and wildfires. One of the latest events took place in June 2024, when continuous rainfall in southern Germany caused water levels to rise. This paper presents the German Aerospace Center’s (DLR) operational response to the flood incident, focusing on the integration of Earth observation data and the dissemination of information via a web-based platform. DLR combined high-resolution aerial imagery, very high-resolution radar and optical satellite imagery, and utilized flood extent masks derived from Copernicus Sentinel-1 and -2 data to support the flood response. The collected datasets were refined with ancillary geospatial layers such as building footprints and infrastructure data, before being integrated into a web-based viewer. The viewer allowed a dynamic visualization and data exploration by public authorities and disaster response organizations, facilitating efficient coordination and decision-making. The first information layers were published within hours of acquisition, and the web-based viewer was accessed more than 800 times during the first week. User feedback from emergency stakeholders highlighted the platform’s usability, relevance, and value in crisis coordination. While certain limitations were identified such as the reliance on internet access and challenges in urban radar interpretation, the workflow proved highly effective. This case study demonstrates how a national EO agency can leverage integrated geospatial data, automation, and dissemination tools to support rapid flood response. The approach presented in this paper provides a framework that can potentially be replicated in other countries and disaster scenarios.

Climate change is significantly affecting biodiversity, and organisms that depend on external temperature – such as ectotherms – are particularly vulnerable to these effects. Microhabitats provide refuge for species, thereby reducing exposure to thermal and hydric stress under climate change. Using a mechanistic modelling approach, we assessed how microhabitat variability and physiological traits influence activity behaviour, time spent in preferred temperature, shade selection, and water loss under different climate change scenarios on two green lizard species. We classified study area microhabitats using high‐resolution geospatial data and applied biophysical models to simulate organismal responses under current and future climate change scenarios (+2°C and +4°C). We first calibrated microhabitat‐specific microclimate models using field data and adjusting key parameters that determine surface energy balance and soil heat transfer, including surface roughness height, substrate longwave emissivity, and soil density. We then performed steady‐state ectotherm models and extracted physiological responses such as foraging and basking times, times spent in preferred temperature, selected shade, and water loss under current and projected climate scenarios. Our results revealed differences between species in terms of thermoregulatory and water‐loss dynamics: Timon lepidus showed higher foraging and basking activity, particularly in open rocky microhabitats. In contrast, Lacerta schreiberi relied more on shaded vegetated microhabitats and exhibited higher size‐corrected evaporative water loss. Foraging activity in T. lepidus increased in low‐slope areas, whereas L. schreiberi foraged more in steeper microhabitats, where both species also selected greater shade. Activity increased on south/west slopes, while shade selection was greater on north/west slopes. Activity periods may increase under warming conditions, but this may come at the cost of higher selected shade and water loss. These results go beyond recognizing the buffering role of microhabitats in climate change, by linking fine‐scale thermal and hydric variation to physiological strategies of lizard species. By integrating microclimate and ectotherm models, our work illustrates how species‐specific traits interact with microhabitat heterogeneity to shape differential vulnerability under warming conditions.

Abstract. The map, as a way of representing geospatial data, is designed to reflect important information about the Earth as deeply and accurately as possible. To meet this requirement, maps are produced in different scales and different types, depending on the task being solved. Created by highly educated specialists, the map contains not only raw geospatial data, but also some high-level knowledge accumulated by people during the exploration of the Earth. The introduction of deep learning into the data analysis process has allowed the development of neural network models that can solve complex aerial image processing tasks, such as semantic image segmentation, object detection and recognition, and retrieving of semantic relations between objects in a scene. These advances created the background for moving to image (scene) understanding as a higher level of image analysis. The current study addresses to a problem of multi-scale scene graph generation from aerial images, similarly to creating maps of different scales.

Abstract. The concept of smart cities aims to create more efficient, sustainable and liveable urban environments by integrating information and communication technologies. In recent years, the integration of artificial intelligence (AI) with geospatial data, known as geospatial artificial intelligence (GeoAI), has emerged as a pivotal catalyst for smart city initiatives. GeoAI has become as a transformative force in the context of smart cities, revolutionising the analysis, design and management of urban environments. By integrating AI and geographic information systems (GIS), it processes and analyses spatial data, informing decisions in various domains such as urban planning, public health, transportation management, and environmental monitoring. This study presents a systematic review of GEOAI applications in the smart cities concept between 2019 and 2024, focusing on the following topics: (1) smart transportation systems, (2) 3D building models and indoor navigation, (3) open data platforms and urban analytics, and (4) web-based interactive data visualisation.

Rapid urban expansion has transformed rural land use, generating multiple sustainability challenges, including environmental pollution, habitat degradation, and crises of community identity. However, existing studies lack a quantitative framework that captures the multidimensional coupling among economic vitality, ecological integrity, and social wellbeing during urban–rural transitions, limiting guidance for integrating urban and rural landscapes. To respond to this issue, this study introduces an integrated Urban-Rural Sustainability Index (URSI) that encompasses economic, ecological, and social dimensions. Additionally, it develops a methodological framework that combines a Random Effects Model (REM), an Extreme Gradient Boosting (XGBoost) model, and Shapley Additive Explanations (SHAP) to identify both linear and non-linear relationships, interaction effects, and threshold conditions, while ensuring predictive accuracy and interpretability. Using geospatial data from Suzhou, China, this study systematically examines the spatial-temporal dynamics of urban-rural integration and associated sustainable outcomes between 2012 and 2024. Three key findings were revealed: (1) Urban-Rural Sustainability Index (URSI)-based conflict exhibits significant spatial clustering, evolving from a monocentric hotspot into a polycentric, multi-nodal pattern as urban expansion proceeds; (2) REM results reveal heterogeneous effects across land use types: built-up area is positively associated with conflict, whereas farmland, water, and forest are negatively associated, indicating a buffering role of ecological and agricultural stocks; (3) XGBoost–SHAP analysis enhances these findings by identifying segmented effects and indicative operating ranges, including an inflection around a built-up area about 60%, diminishing marginal mitigation from water coverage around 15%, and conflict alleviation when contiguous farmland is maintained near 20%. Building upon these empirical insights, this study proposes targeted strategies to enhance urban-rural sustainability, including spatially differentiated land-use management, prioritising blue-green infrastructure in urban planning and balancing sustainability pressures within urban areas. The proposed framework and analytical methodology provide a transferable foundation for future research and practical urban-rural sustainability planning across diverse geographical contexts.

Assessment of Coastal Erosion Vulnerability Using Aerial Sensing and Geospatial Data

ABSTRACT This paper aims to conduct a systematic literature review (SLR) on geospatial data governance in ASEAN with a focus on policy, security and compliance challenges. The SLR method was based on the PRISMA protocol, which involves a systematic search strategy in the Scopus, Web of Science, Google Scholar and Semantic Scholar databases for the period 2020–2025. A total of 25 valid articles were selected after going through a screening process. The results of the study showed four main themes, namely the existing policy of geospatial data governance in ASEAN, followed by challenges to security and sovereignty of the data, next is the weak enforcement leads to poor compliance and finally limitations in technology and organisational capacity in implementing policies. The finding highlights that despite various efforts at the national level for geospatial data sharing such as MyGeoportal in Malaysia, Land Administration Domain Model (LADM) in the Philippines, One Map Policy in Indonesia and OneMap in Singapore, the absence of a regional governance framework makes the issue of data integration, compliance and security increasingly critical. This article contributes to the existing literature by addressing gaps in the ASEAN context, strengthening the theoretical understanding of geospatial data governance and offering practical insights for policymakers, communities and industry stakeholders. Accordingly, this review paper not only synthesises existing evidence but also proposes directions for the development of a future framework aimed at enhancing and reinforcing ASEAN compliance and risk management practices related to geospatial data governance.

Crowdsourced geospatial platforms constitute complex socio-technical systems in which data quality and reliability emerge from collective user behavior rather than centralized control. This study proposes a system-oriented, unsupervised machine learning framework to assess the reliability of crowdsourced building data using only intrinsic indicators. The framework is demonstrated through a large-scale analysis of OpenStreetMap building polygons in Tehran. Six intrinsic indicators—reflecting contributor activity, temporal dynamics, semantic instability, and geometric evolution—were normalized using fuzzy membership functions and objectively weighted based on their discriminative influence within a K-means clustering process. Five reliability classes were identified, ranging from very low to very high reliability. The resulting classification exhibited strong internal validity (average silhouette coefficient = 0.58) and pronounced spatial coherence (Global Moran’s I = 0.85, p < 0.001). This approach eliminates dependence on authoritative reference datasets, enabling scalable, reproducible, and feature-level reliability assessment in open geospatial systems. The framework provides a transferable methodological foundation for trust-aware analysis and decision-making in participatory and data-intensive systems.

Abstract. Landscape restoration in semi-arid environments demands not only effective interventions but also communicative approaches that make complexity legible and foster ecological literacy. Immersive technologies such as Virtual Reality (VR) transform geospatial data into navigable environments, making processes tangible and transferable experiences. This study translates a remote restoration site in the Murcia region of Spain, characterized by limited accessibility and harsh conditions, into an immersive Virtual Reality geovisualization. A UAV structure-from-motion survey produced a high-resolution textured model that was geospatially situated with BlenderGIS (ESRI imagery over a 30 m digital elevation model) and then reconstructed in Twinmotion under a calibrated HDRI skydome. The scene is engineered for room-scale use with teleport-only locomotion and a uniform down-scale that enables hand-scale inspection of swales, ponds, ground cover, tree rows, and micro-topography. Three access points organize short narrated sequences that guide users from landscape overview to near-field readings, converting mesh into meaning. A pilot on Meta Quest 3 yielded encouraging signals: high presence and perceived realism, low discomfort, positive self-reported competence, and intent to re-engage. The pilot also surfaced technical priorities, including tighter blending between the VR layers, and bias-aware context. The contribution is a reproducible workflow that combines geospatial context and proxemic design to support spatial reasoning, knowledge transfer, and public communication. Strategically, the module offers a path toward a participatory, education-ready XR tool for regenerative practice, and a future platform for stakeholders, to support cognitive spatial reasoning and field-digital decision-making.

Flood disasters pose persistent socio-economic and environmental challenges, particularly in tropical regions such as Sumatra, Indonesia. Traditional hydrological and GIS-based approaches often struggle to capture complex interactions among terrain, rainfall, land use, and human activities. This review critically examines recent applications of Geospatial Artificial Intelligence (GeoAI) for flood disaster mapping, focusing on machine learning models, geospatial data sources, and computational workflows. Analysis of selected studies highlights that satellite imagery and digital elevation models remain dominant data inputs, while Random Forest, Support Vector Machines, Convolutional Neural Networks, and hybrid models are most frequently applied. Workflow patterns reveal recurring stages of data preprocessing, model training, and post-processing, yet gaps persist in model explainability, feature selection, and generalization across regions. The study underscores the importance of integrating multi-source data, standardizing workflows, and fostering interdisciplinary collaboration to enhance operational flood risk management. Findings provide a foundation for advancing GeoAI research and translating methodological innovations into practical flood preparedness and mitigation strategies.

The main objective of this research is to conduct an urban flood-risk assessment approach for South Jakarta, Indonesia. Flood susceptibility was modelled using the frequency ratio (FR) method and validated with the receiver operating characteristic–area under the curve (ROC–AUC). Vulnerability was assessed using the analytic hierarchy process (AHP) across four domains: physical, economic, environmental and social. We used high-resolution spatial data (1:25 000) and a historical flood inventory to produce rapid, urban-scale risk information where conventional datasets are limited. The susceptibility map shows three classes: low, medium and high; the combined risk map indicates that most of the study area is at medium risk (108.64 km2, or 74.550%), low (37.08 km2 or 25.447%) and high (0.004 km2 or 0.003%). Vulnerability analysis identifies residential areas, critical infrastructure and key service zones as the most exposed elements. Susceptibility, vulnerability and risk are the three essential parameters incorporated into the spatial planning analysis to ensure comprehensive evaluation. The findings identify protection zones with particular risk levels, which require targeted mitigation strategies for any future development initiatives. Furthermore, this study highlights that the integration of FR, ROC–AUC and AHP provides reliable and operational flood-risk assessments that can be effectively incorporated into spatial planning and development policies in data-constrained urban settings. Contribution: This study presents an innovative and practical framework for urban flood-risk assessment, combining FR, ROC–AUC and AHP to evaluate flood susceptibility and vulnerability in South Jakarta, Indonesia. Leveraging high-resolution geospatial data at a detailed 1:25 000 scale, it addresses critical data gaps and equips policymakers with actionable tools to integrate risk sensitive strategies into urban spatial planning for further mitigation. The findings, revealing 74.55% of the area at medium flood risk, set a benchmark for advancing disaster resilience and sustainable urban development, offering valuable applications for other rapidly urbanising, data-constrained regions globally.

Human–Wildlife Conflict (HWC) is an increasing challenge in rapidly changing landscapes, where agricultural expansion, settlement growth, and infrastructure development intersect with critical wildlife corridors. Addressing these conflicts requires spatially explicit methods that can evaluate trade-offs among competing land uses. This study demonstrates the application of the open-source Land Use Conflict Identification Strategy (Open-LUCIS), a suitability-based framework that integrates open geospatial data, domain knowledge, and goal-driven land-use modeling. Using Pandamatenga in Botswana’s Chobe District as a case study, we identified areas of potential conflict among agriculture, human settlement, and wildlife conservation. High-conflict zones were concentrated where commercial farms overlap with transboundary wildlife corridors, highlighting the tension between agricultural development and conservation. A sensitivity analysis indicated that existing land use, road accessibility, and development constraints strongly influence conflict dynamics. The application demonstrates a clear pathway for using open-source tools to support HWC studies. By relying on open data and reproducible methods, Open-LUCIS offers a cost-effective and accessible alternative to proprietary software, with direct implications for advancing sustainable land development in regions with limited resources. Given that the dynamics observed in Chobe reflect pressures common across many parts of Africa and beyond, the framework is broadly applicable as a transferable approach for managing land-use conflicts in many rapidly developing, ecologically sensitive frontiers worldwide.

Human-Wildlife Conflict (HWC) is an increasing challenge in rapidly changing landscapes, where agricultural expansion, settlement growth, and infrastructure development intersect with critical wildlife corridors. Addressing these conflicts requires spatially explicit methods that can evaluate trade-offs among competing land uses. This study demonstrates the application of the open-source Land Use Conflict Identification Strategy (Open-LUCIS), a suitability-based framework that integrates open geospatial data, domain knowledge, and goal-driven land-use modeling. Using Pandamatenga in Botswana's Chobe District as a case study, we identified areas of potential conflict among agriculture, human settlement, and wildlife conservation. High-conflict zones were concentrated where commercial farms overlap with transboundary wildlife corridors, highlighting the tension between agricultural development and conservation. A sensitivity analysis indicated that existing land use, road accessibility, and development constraints strongly influence conflict dynamics. The application demonstrates a clear pathway for using open-source tools to support HWC studies. By relying on open data and reproducible methods, Open-LUCIS offers a cost-effective and accessible alternative to proprietary software, with direct implications for advancing sustainable land development in regions with limited resources. Given that the dynamics observed in Chobe reflect pressures common across many parts of Africa and beyond, the framework is broadly applicable as a transferable approach for managing land-use conflicts in many rapidly developing, ecologically sensitive frontiers worldwide.

Abstract Geospatial data are often spatially varying but measured sparsely in a two-dimensional (2D) plane. Therefore, spatial interpolation methods, such as Kriging, are frequently used to estimate values at locations without measurement and quantify the associated uncertainty. However, Kriging generally requires extensive measurements to effectively divide non-stationary geospatial data into a deterministic trend and stationary residuals (i.e., detrending) and to estimate semi-variogram parameters from the detrended residuals (i.e., semi-variogram fitting). When measurements are limited, a scenario often encountered in practice, detrending might be challenging, and the estimated semi-variogram parameters inevitably contain statistical uncertainty. The statistical uncertainty may significantly affect the subsequent Kriging interpolation, but it is often ignored in practical applications of Kriging. This study develops a 2D Kriging method (SR-Kriging) that is featured by a sparse representation of covariance function from a Bayesian perspective and explicitly models both spatial variability and statistical uncertainty for interpolation of 2D geospatial data directly from sparse measurements. The proposed method requires neither detrending nor semi-variogram fitting. Both simulated and real data are used to illustrate and validate the proposed method. Results demonstrate that the proposed method directly interpolates 2D geospatial data from limited measurements, with quantified interpolation uncertainty, and explicitly accounts for statistical uncertainty. Ignorance of statistical uncertainty may lead to an underestimation of Kriging interpolation uncertainty.

Pneumonia remains a leading cause of morbidity and hospitalization in sub-Saharan Africa, yet the contributions of long-term environmental and infrastructural factors to its spatial distribution are poorly understood. Kinshasa, a rapidly expanding African megacity, experiences high levels of air pollution, substantial vegetation loss, and marked urban inequalities, potentially exacerbating respiratory vulnerability. We conducted a retrospective ecological spatial study using 484,954 pneumonia hospital admissions recorded across 35 health zones in Kinshasa between 2018 and 2022. Long-term exposure to ambient air pollution (PM₂.₅, NO₂, CO), vegetation cover (NDVI), major road density, climatic indicators, and healthcare infrastructure were assessed via satellite-derived and geospatial data. Bayesian BYM2 negative binomial models were fitted to estimate age-stratified relative risks (RRs), accounting for spatial dependence and overdispersion. Sensitivity analyses were used to evaluate model robustness. Pneumonia incidence showed pronounced spatial heterogeneity, with persistent high-risk zones concentrated in central and northern districts. Children under five years of age accounted for 41% of the cases and presented a substantially higher cumulative incidence than older individuals did. After adjustment for spatial effects and multicollinearity, no air pollutant demonstrated a consistent positive association with pneumonia risk. In contrast, vegetation cover was a robust protective factor across all age groups (RR range: 0.58-0.85). Higher major road density was also associated with reduced risk, likely reflecting improved accessibility and urban infrastructure. Areas combining low vegetation, high climatic stress, and limited infrastructure experienced the highest pneumonia burden. Pneumonia risk in Kinshasa is driven primarily by environmental and infrastructural inequalities rather than by the isolated effects of individual air pollutants. Strengthening urban green infrastructure, reducing environmental stressors, and improving equitable access to healthcare should be central to pneumonia prevention strategies in rapidly urbanizing African cities.

This study aims to demonstrate the contribution of census data combined with Geographic Information System (GIS) techniques to local development planning in Mali, with a particular focus on spatial accessibility to health infrastructure in a rural context. A cross-sectional study design was adopted, integrating spatial and statistical analyses of census and geospatial data. The study was conducted in the rural commune of Kroukoto, located in the cercle of Kéniéba, Kayes Region, south-western Mali, covering approximately 250 km² with an estimated population of about 12,000 inhabitants. Georeferenced census data were integrated with spatial layers representing settlements, road networks, health centers, and educational facilities within a GIS environment. Distance-based accessibility modeling was applied using commonly adopted rural planning thresholds, including 5 km for access to health centers. The results indicate that approximately 65% of the population lives within 5 km of an existing community health center, while 35% remains beyond this threshold, mainly in peripheral and poorly connected areas. Spatial analysis further shows that the existing health facility serves 4,671 people across 1 village and 43 hamlets, whereas the proposed second health center would serve 5,089 people in 5 villages and 44 hamlets, with 2,331 people benefiting from overlapping service areas. These findings reveal significant spatial disparities in service accessibility linked to settlement dispersion and road connectivity. The integration of census data with GIS provides an effective decision-support tool for identifying underserved areas, improving resource allocation, and strengthening evidence-based territorial planning in rural Mali.