OpenStreetMap Research Articles

Semantic Segmentation Uncertainty Assessment of Different U-net Architectures for Extracting Building Footprints

Abstract. Automatic extraction of building footprints from aerial and space imageries has been found ever increasing importance in urban planning, disaster management, and environmental monitoring. However, achieving accurate building footprint extraction poses significant challenges due to diverse building characteristics and their similarities to their background elements. While conventional methods in building footprint extraction have mainly relied on image processing techniques, recent advancements in deep learning, particularly semantic segmentation algorithms like U-Net, have shown promise in addressing these challenges through machine learning. This study explores different depths of the U-Net model for building footprint extraction, aiming to identify the optimum architecture while investigating the semantic uncertainty of the building footprint extraction. Utilizing aerial imagery from cities including Berlin, Paris, Chicago, and Zurich, collected from Google Maps and OpenStreetMap (OSM) data, five U-Net models have been compared with varying depths. In addition, the impact of dataset sizes and learning rates on model performance has been investigated. Results confirmed that the U-Net-32-1024 model achieves the highest intersection over union (IoU), Accuracy, and F1-score. Moreover, increasing the training dataset size leads to significant improvements in model performance with IoU, Accuracy and F1-score reaching their values of 73.73%, 88.65% and 88.53%. However, challenges remain in accurately delineating buildings in dense urban areas. Nonetheless, our findings demonstrated the effectiveness of U-Net models in building footprint extraction.

Multi-Modal Contextualization of Trajectory Data for Advanced Analysis

SummaryRising amounts of generated geospatial data, either trajectory-like tracking data, raster-like imagery, or vector-like mappings as in OpenStreetMap (OSM), grow the need for multi-modal algorithmic analysis. Existing machine-learning-based algorithms contradictly mainly focus on image and textual input representations and cannot deal with other modes of geospatial data. Therefore, we propose a novel method to contextualize vector-like trajectory data with surrounding data to create easy-to-be-analyzed image-like representations. Our approach includes the proposition of a chase-cam-like scanline over space according to the trajectory’s speed and possibly smoothed orientation. Thereby, surrounding pixels in the vicinity of the trajectory points are accumulated along the scanline and are combined into a visual representation of the trajectory. To show the potential effects of our work, we predict traffic regulations for trajectory sections in the vehicle speed dataset based on our proposed trajectory-based sampling of orthophotos in the same region. This proposes a new way of using multi-modal data sources (trajectories and airborne imagery) to extract road metadata.

Achieving Nepal's clean cooking ambitions: an open source and geospatial cost–benefit analysis

Cooking with traditional fuels can lead to severe health issues caused by household air pollution, and can also affect gender equality and drive environmental degradation. In Nepal, despite government efforts to promote electric cooking, more than half of the population still uses traditional fuels, with electric cooking adoption remaining below 1%. Several of the barriers to and enablers of clean cooking vary geographically; however, few studies have considered spatial explicit information in planning national-scale transitions to clean cooking. In this study we provide a spatially explicit roadmap to estimate the required investments and benefits gained from the transition across Nepal. This study uses geospatial modelling methods to evaluate strategies to achieve the Government of Nepal's vision for a national-scale transition to clean cooking. We integrate the open-source clean cooking geospatial assessment tool OnStove and a spatial multicriteria analysis model. With OnStove, we evaluate which cooking technologies and fuels maximise the net benefits of a clean-cooking transition across each km2 of the region. With the multicriteria analysis, we weigh stakeholder preferences and prioritise areas of action where policy should be implemented. We used the most up-to-date geospatial data to the year 2023, such as the High Resolution Settlement Layer, Open Street Maps' road networks, the Global Human Settlement Layer, NASA/USGS forest cover maps, and Facebook's Relative Wealth Index, among others. We also relied on data from the Nepal Oil Corporation, the Nepal Electricity Agency, the Central Bureau of Statistic's 2021 national census, and the Alternative Energy Promotion Center. We evaluate four scenarios capturing advances on clean cooking policy up to the year 2022, current market inefficiencies, and the potential effects of new policies for clean-cooking transition in Nepal. Our results show that transitional and clean cooking technologies provide higher net benefits than traditional options everywhere across Nepal in all scenarios. Our net-benefit analysis shows that around 9563 deaths could be averted yearly if benefits and externalities were perceived and valued correctly. Furthermore, substantial benefits could be achieved in regard to greenhouse gas emissions avoidance, time saved, and health-cost reductions. Our results also show that the current subsidy strategy from the Government of Nepal is well aligned with the benefits achieved under a cost-benefit analysis. In this context, electric cooking can bring the highest benefits to the largest part of the population. The analysis showed how high subsidies for liquefied petroleum gas in Nepal can present trade-offs with energy security and independence, and how this could be avoided by transferring part of the subsidy to cover differentiated electric cooking tariffs. Accounting for stakeholder preferences and sociodemographic and geographical differences to prioritise areas of focus can balance affordability constraints and target the most vulnerable people first, thus achieving integrated and inclusive planning. Using spatially explicit modelling approaches to evaluate strategies for a clean cooking transition can provide more nuanced results that have not been possible before. This approach can enable data-driven and integrated planning to help to understand which locations of a study area should be prioritised for policy application. Integrated planning can help to reduce affordability constraints on the population and design strategies for a sustainable and inclusive transition. These strategies allow financial institutions, donors, impact investors, development organisations, and government agencies to use their resources, funds, and assistance to create a large impact. Clean Cooking Alliance.

Leveraging Open-Source Geographic Databases to Enhance the Representation of Landscape Heterogeneity in Ecological Models.

Wildlife abundance and movement are strongly impacted by landscape heterogeneity, especially in cities which are among the world's most heterogeneous landscapes. Nonetheless, current global land cover maps, which are used as a basis for large-scale spatial ecological modeling, represent urban areas as a single, homogeneous, class. This often requires urban ecologists to rely on geographic resources from local governments, which are not comparable between cities and are not available in underserved countries, limiting the spatial scale at which urban conservation issues can be tackled. The recent expansion of community-based geographic databases, for example, OpenStreetMap (OSM), represents an opportunity for ecologists to generate large-scale maps geared toward their specific research needs. However, computational differences in language and format, and the high diversity of information within, limit the access to these data. We provide a framework, using R, to extract geographic features from the OSM database, classify, and integrate them into global land cover maps. The framework includes an exhaustive list of OSM features describing urban and peri-urban landscapes and is validated by quantifying the completeness of the OSM features characterized, and the accuracy of its final output in 34 cities in North America. We portray its application as the basis for generating landscape variables for ecological analysis by using the OSM-enhanced map to generate an urbanization index, and subsequently analyze the spatial occupancy of six mammals throughout Chicago, Illinois, USA. The OSM features characterized had high completeness values for impervious land cover classes (50%-100%). The final output, the OSM-enhance map, provided an 89% accurate representation of the landscape at 30m resolution. The OSM-derived urbanization index outperformed other global spatial data layers in the spatial occupancy analysis and concurred with previously seen local response trends, whereby lagomorphs and squirrels responded positively to urbanization, while skunks, raccoons, opossums, and deer responded negatively. This study provides a roadmap for ecologists to leverage the fine resolution of open-source geographic databases and apply it to spatial modeling by generating research-specific landscape variables. As our occupancy results show, using context-specific maps can improve modeling outputs and reduce uncertainty, especially when trying to understand anthropogenic impacts on wildlife populations.

What amenities drive footfall in UK town centres? A machine learning approach using OpenStreetMap data

In the United Kingdom, town centres face significant economic and social challenges, with amenities playing a crucial role in their vitality. However, no existing study has thoroughly investigated the relationship between amenities and footfall, a key measure of place vitality. This research addresses this gap by examining which amenities drive footfall in UK town centres. The study employs the random forest modelling, to analyse data from OpenStreetMap (OSM) and footfall data from 960 counters across the United Kingdom. Our findings reveal that OSM data can effectively predict footfall, highlighting the importance of diverse amenities. Key amenities identified include hotels, pedestrian ways, and retail establishments. Furthermore, the study identifies critical inflection points where the presence of certain amenities significantly boosts urban vitality. These insights offer valuable guidance for urban planning and development, suggesting that a mix of diverse amenities at appropriate levels can enhance the attractiveness and vitality of town centres.

Exploring the Coordination of Park Green Spaces and Urban Functional Areas through Multi-Source Data: A Spatial Analysis in Fuzhou, China

The coordinated development of park green spaces (PGS)with urban functional areas (UFA) has a direct impact on the operational efficiency of cities and the quality of life of residents. Therefore, an in-depth exploration of the coupling patterns and influencing factors between PGS and UFA is fundamental for efficient collaboration and the creation of high-quality living environments. This study focuses on the street units of Fuzhou’s central urban area, utilizing multi-source data such as land use, points of interest (POI), and OpenStreetMap (OSM) methods, including kernel density analysis, standard deviational ellipse, coupling coordination degree model, and geographical detectors, are employed to systematically analyze the spatial distribution patterns of PGS and UFA, as well as their coupling coordination relationships. The findings reveal that (1) both PGS and various UFA have higher densities in the city center, with a concentric decrease towards the periphery. PGS are primarily concentrated in the city center, exhibiting a monocentric distribution, while UFA display planar, polycentric, or axial distribution patterns. (2) The spatial distribution centers of both PGS and UFA are skewed towards the southwest of the city center, with PGS being relatively evenly distributed and showing minimal deviation from UFA. (3) The dominant type of coupling coordination between PGS and various UFA is “Close to dissonance”, displaying a spatial pattern of “high in the center, low on the east-west and north-south wings”. Socioeconomic factors are the primary driving force influencing the coupling coordination degree, while population and transportation conditions are secondary factors. This research provides a scientific basis for urban planning and assists planners in more precisely coordinating the development of parks, green spaces, and various functional spaces in urban spatial layouts, thereby promoting sustainable urban development.

Spatial Evaluation and Modelling of Fire Stations Layout to Access Forest Fires by Roads (Case Study: Krasnoyarsk Region, Russia)

Regional forest fire protection services on the ground usually have a fire station infrastructure with firefighting vehicles capable of moving by public and forest roads. The location of fire stations is a subject of evaluation on the regional scale and a matter of constant research interest. Infrastructure and transport accessibility, as well as the spatial location of fire stations worldwide and in Russia, were discussed. Location-Allocation ArcGIS tool and the access routes database for Krasnoyarsk region (archived data of 2002-2022 forest fires detected by MODIS containing 60637 records) were the base of methodology to evaluate fire station layout. The settlement dataset from Open Street Map (OSM) was used to analyze new locations as candidates for a fire station. Standard Deviational Ellipse ArcGIS tool was applied to define an optimal area for the current fire station from which routes to the nearest fires are built. OSM settlements inside of 1-sd area of the ellipse were used to generate the candidate list of settlements to find new locations instead of the current fire station. Results have been evaluated for 3 groups of access routes: 3 hours and less, more than 3 hours, and access routes of any duration according to the Russian forestry rules. The proposed fire station layout has improved forest fire accessibility with OSM candidates for 39 stations; 20 of 59 remain spatially unchanged. Total regional forest fire accessibility changed from the current to the proposed layout in absolute values from 47331 to 48905 fires. Analysis of 39 relocated stations showed that the new fire station layout is more optimal than the current one because it provides access to an additional 20 % of forest fires with a decrease in average weighted time to reach them by 30 %. The described methodology could make an emergency response during a fire-hazardous period more effective.

Global Localization using OpenStreetMap and Elevation Offsets

Localization is a critical component in autonomous vehicle navigation stacks. While GNSS-only localization cannot be fully reliable and available all the time, localization based on 3D high-definition (HD) maps have to be robust to world changes, which is still a challenging issue. Added to that, in general, HD maps are expensive and difficult to construct and maintain.In this paper, we propose a particle filter-based 2D global pose estimation method that can use the crowdsourced OpenStreetMap (OSM) API, a digital surface map, or both. The main contributions of the proposed approach are: that it is lightweight, does not require the vehicle to map the environment, does not require a GPU (can be used with low-power computing resources), is agnostic to the odometry source, and achieved relatively low position and orientation errors for this localization modality using the KITTI dataset sequences. The proposed method's implementation is open source and is available with the experimental results on our GitHub page.

A comprehensive assessment approach for multiscale regional economic development: Fusion modeling of nighttime lights and OpenStreetMap data

Assessing regional economic development is key for advancing towards the Sustainable Development Goals and ensuring sustainable societal progress. Traditional evaluation methods focus on basic economic metrics like population and capital, which may not fully reflect the complexities of economic activities. Nighttime light (NTL) has been validated as an alternative indicator for regional economic development, yet limitations persist in its evaluation. This study integrates OpenStreetMap (OSM) data and NTL data, providing a novel data integration approach for evaluating economic development. The study uses mainland China as a case, applying Ordinary Least Squares (OLS) and Geographically Weighted Regression (GWR) to evaluate OSM and NTL data across provincial, municipal, and county levels. It compares OSM, NTL, and their combined use, providing key empirical insights for enhancing data fusion models. The study results reveal: (1) NTL data is more accurate for provincial-level economic activity, while OSM data excels at the county level. (2) GWR demonstrates superior capability over OLS in revealing the spatial dynamics of economic development across scales. (3) Through the integration of both datasets, it is observed that, compared to single-data modeling, the performance is enhanced at the city scale and county scale. The study demonstrates that combining OSM and NTL data effectively assesses economic development in both developed and underdeveloped areas at provincial, municipal, and county levels. The study offers a straightforward and efficient approach to data integration. The findings offer new research perspectives and scientific support for sustainable regional economic growth, particularly valuable in data-scarce, underdeveloped areas.

Comparing mapped park and greenspace boundaries in Philadelphia: implications for exposure assessment in health studies

An important consideration in studies of the relationship between greenspace exposure and health is the use of mapped data to assign geographic exposures to participants. Previous studies have used validated data from municipal park departments to describe the boundaries of public greenspaces. However, this approach assumes that these data accurately describe park boundaries, that formal parks fully capture the park and greenspace exposure of residents, and (for studies that use personal GPS traces to assign participant exposures) that time spent within these boundaries represents time spent in greenspace. These assumptions are tested using a comparison and ground-truthing of four sources of mapped park and greenspace data in Philadelphia, Pennsylvania: PAD-US-AR, Philadelphia Parks and Recreation, the Delaware Valley Regional Planning Commission, and Open Street Maps. We find several important differences and tradeoffs in these data: the incorporation of highways and building lots within park boundaries, the inclusion or exclusion of formal park spaces (federal, state, and nonprofit), the exclusion of informal parks and greenspaces, and inconsistent boundaries for a linear park. Health researchers may wish to consider these issues when conducting studies using boundary data to assign park exposure.

Enriching building function classification using Large Language Model embeddings of OpenStreetMap Tags

AbstractAutomated methods for building function classification are essential due to restricted access to official building use data. Existing approaches utilize traditional Natural Language Processing (NLP) techniques to analyze textual data representing human activities, but they struggle with the ambiguity of semantic contexts. In contrast, Large Language Models (LLMs) excel at capturing the broader context of language. This study presents a method that uses LLMs to interpret OpenStreetMap (OSM) tags, combining them with physical and spatial metrics to classify urban building functions. We employed an XGBoost model trained on 32 features from six city datasets to classify urban building functions, demonstrating varying F1 scores from 67.80% in Madrid to 91.59% in Liberec. Integrating LLM embeddings enhanced the model's performance by an average of 12.5% across all cities compared to models using only physical and spatial metrics. Moreover, integrating LLM embeddings improved the model's performance by 6.2% over models that incorporate OSM tags as one-hot encodings, and when predicting based solely on OSM tags, the LLM approach outperforms traditional NLP methods in 5 out of 6 cities. These results suggest that deep contextual understanding, as captured by LLM embeddings more effectively than traditional NLP approaches, is beneficial for classification. Finally, a Pearson correlation coefficient of approximately -0.858 between population density and F1-scores suggests that denser areas present greater classification challenges. Moving forward, we recommend investigation into discrepancies in model performance across and within cities, aiming to identify generalized models.

Towards an open pipeline for the detection of critical infrastructure from satellite imagery—a case study on electrical substations in The Netherlands

Abstract Critical infrastructure (CI) are at risk of failure due to the increased frequency and magnitude of climate extremes related to climate change. It is thus essential to include them in a risk management framework to identify risk hotspots, develop risk management policies and support adaptation strategies to enhance their resilience. However, the lack of information on the exposure of CI to natural hazards prevents their incorporation in large-scale risk assessments. This study sets out to improve the representation of CI for risk assessment studies by building a neural network model to detect CI assets from optical remote sensing imagery. We present a pipeline that extracts CI from OpenStreetMap (OSM), processes the imagery and assets’ masks, and trains a Mask R-CNN model that allows for instance segmentation of CI at the asset level. This study provides an overview of the pipeline and tests it with the detection of electrical substations assets in the Netherlands. Several experiments are presented for different under-sampling percentages of the majority class (25 %, 50 % and 100 %) and hyperparameters settings (batch size and learning rate). The highest scoring experiment achieved an Average Precision at an Intersection over Union of 50 % of 30.93 and a tile F-score of 89.88 %. This allows us to confirm the feasibility of the method and invite disaster risk researchers to use this pipeline for other infrastructure types. We conclude by exploring the different avenues to improve the pipeline by addressing the class imbalance, Transfer Learning and Explainable Artificial Intelligence.

Risk of Tropical Cyclones and Floods to Power Grids in Southeast and East Asia

Power grids play a critical role in modern society, serving as the lifeline of a well-functioning economy. This article presents a first large-scale study on the risk estimation of tropical cyclone (TC)-induced winds and coastal floods, which can widely impact power grids in Southeast and East Asia. Our comprehensive risk model incorporates detailed infrastructure data from OpenStreetMap (OSM) and government power grid maps, along with global hazard maps and vulnerability curves. The results reveal that the estimated expected annual damages from TCs and coastal floods to OSM-mapped assets account for approximately 0.07% (0.00–0.38%) and 0.02% (0.00–0.02%) of the total GDP of the study area, respectively. We analyzed the main sources of uncertainty in the risk model and emphasized the importance of understanding asset vulnerability. These results highlight the urgent need to strengthen power infrastructure to withstand the impacts of natural hazards, and the significance of reliable risk information for improving power grid design and planning. Focusing on developing more region-specific infrastructure data and vulnerability curves will improve the accuracy of risk estimation and provide valuable insights not only for the electricity sector but also for customers of other infrastructure systems that heavily rely on a stable supply of electricity.

A Comparative Analysis of Data Source’s Impact on Renewable Energy Scenario Assessment—The Example of Ground-Mounted Photovoltaics in Germany

The German government aims to convert its energy system to renewable energy by 2045. This requires a comprehensive understanding of land eligibility for renewables, particularly land-intensive ground-mounted photovoltaics (GM-PV). Federal states must set aside at least 2% of their land for renewable energy. This target value was derived using a top-down energy demand approach. Georeferenced land use data can be used to make bottom-up estimates. This study investigates how the choice of data source influences the bottom-up evaluation of land eligibility for GM-PV installations in Germany. This study evaluates the quality of data sources and their applicability for GM-PV scenario assessment by comparing the official data source Basis-DLM as the reference with the open-access data sources OpenStreetMap (OSM), Corine Land Cover (CLC), and Copernicus Emergency Management Service (CEMS). The intersection over union (IoU) and Matthews correlation coefficient (MCC) methods were used to analyse the differences in land use and eligibility due to the quality of the data sources and to compare their accuracy. The study’s results show the crucial role of data source selection in estimating the potential for GM-PV in Germany. The results indicate that open-access data overestimate land eligibility by 4.0% to 4.5% compared to the official Basis-DLM data. Spatial similarities and discrepancies between the OSM, CEMS CLC, and Basis-DLM land uses were identified. The CLC data exhibit higher consistency with Basis-DLM. These findings emphasise the importance of selecting the appropriate data source depending on the purpose and the use of official data sources for accurate and spatially differentiated decision-making and project planning at different scales. Open-access data sources can be applied for initial orientation and large-scale rough assessment as they balance data accuracy and accessibility.

Opportunity Analysis of Phosphorus Recovery from Municipal Wastewater for Cropland Based on the Simulated Vehicle Transport Distance in the Yangtze River Delta, China.

With the rapid depletion of phosphate rocks and increasing agricultural demand, establishing a phosphorus (P) flow "loop" rather than a one-way trajectory between cropland and urban areas was imperative. Recovering P from municipal wastewater stood as a viable strategy to mitigate reliance on traditional P-containing chemical fertilizer. This study analyzed the intricate relationships between the potentials of P recovery from municipal wastewater and the P demand of croplands in the populated Yangtze River Delta (YRD), China. An indicator of the P vehicle transport distance was constructed and calculated to estimate the potential to recover and reuse P in agriculture, applying the simulated annealing (SA) algorithm and road networks obtained from OpenStreetMap (OSM). The results indicated that, on a regional scale, recovered P from municipal wastewater could fulfill 14.0% of the cropland P demands in the YRD, with a median P vehicle transport distance of 3.1 km/Mg of P. Notably, the P vehicle transport distance varied largely depending upon the cropland distributions, road density, and P recovery potential from municipal wastewater. The novel methodology developed here determined the optimal transportation routes for P recovery from wastewater treatment plants (WWTPs) to cropland, which played a crucial role in refining the wastewater management strategies aligned with the United Nations Sustainable Development Goals.

The synergistic effect of multiple design factors on building energy consumption of office blocks: A case study of Wuhan, China

Design factors such as block morphology, building form and building envelope performance are key parameters affecting building energy consumption of urban blocks. However, the synergistic effect of multi-design factors on building energy consumption has not been studied in detail. This paper aims to investigate the synergistic effect of multi-design factors on building energy consumption of office blocks in Wuhan, China. This study employs field survey, satellite map and open street map to extract the typical building forms and construct parametric models of office blocks. Then, 81 representative scenarios considering the synergy of multiple design factors in office blocks are built. Then, based on the Rhino & Grasshopper parametric platform, a building energy assessment tool that considers the synergistic effect of multiple design factors is developed to simulate and record the building energy consumption of each scenarios. Finally, the synergistic effect of multi-design parameters on building energy consumption of office blocks is quantified using correlation and multiple linear regression methods. The findings reveal that the synergistic effect of multi-design factors on building energy consumption is 18.53 %. Building energy consumption for high-rise pavilion typology is saved by 9.64 % than multi-storey courtyard. The key design parameter combinations affecting building energy consumption in office block are building shape factor, solar heat gain coefficient, wall K-value, building width and window-wall ratio of west and east. This study contributes to a deeper understanding of the synergistic effects of multiple design factors on building energy consumption in office blocks and presents a scalable model that can be applied globally to promote sustainable urban development.

ROAD EXTRACTION FROM SATELLITE IMAGERY USING DEEP LEARNING VOL - I

Road extraction involves the intricate process of generating road maps automatically through deep learning algorithms. This task, particularly from satellite imagery, presents significant challenges due to various factors like occlusions, shadows, noise, and fluctuating illumination conditions. As a result, achieving complete and accurate road extraction is daunting without relying on manual annotations or imperfect road maps for guidance. One potential strategy to enhance road extraction accuracy is by incorporating partial road maps as supplementary data. These partial maps, sourced from platforms like OpenStreetMap or Google Maps, may not offer complete or pristine representations of roads but can still provide valuable additional information. By integrating these partial maps with satellite images, we can exploit their complementary nature to mitigate uncertainty in the extraction process. It's important to note that while road extraction may be relatively straightforward in some regions, such as rural areas, it becomes significantly more complex in urban or underdeveloped areas. These environments present unique challenges that require sophisticated algorithms and approaches to accurately extract roads from satellite imagery. Key Words: Road Extraction, Satellite Imagery, Google Maps, Open Street Map, Auxiliary information, Disaster management, Occlusions, Illumination, Annotation, Shadow.

Clustering data analytics of urban land use for change detection

In this study, the author proposes and details a workflow for the spatial-temporal demarcation of urban areal features in 8 cities of Tamilnadu, India. During the inception phase, functional requirements and non-functional parameters are analyzed and designed, within a suitable pixel area and object-oriented derived paradigm. Land use categories are defined from OpenStreetMap (OSM) related works with the scope of conducting climate change, using multispectral sensors onboard Landsat series. Furthermore, we augment the bands dataset with Spatially Invariant Feature Transform (SIFT), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Leaf Area Index (LAI), and Texture base indices, as a means of spatially integrating auto-covariance to stationarity patterns. In doing so, change detection can be pursuit by scaling up the segmentation of regional/zonal boundaries in a multi-dimensional environment, with the aid of Wide Area Networks (WAN) cluster computers such as the BEOWULF/Google Earth Engine clusters. GeoAnalytical measures are analyzed in the design of local and zonal spatial models (GRID, RASTER, DEM, IMAGE COLLECTION). Finally, multi variate geostatistical works are ensued for precision and recall in predictive data analytics. The author proposes reusing machine learning tools (filtering by attribute-based indexing in PaaS clouds) for pattern recognition and visualization of features and feature collection.

Euclide, the crow, the wolf and the pedestrian: distance metrics for linguistic typology.

It is common for people working on linguistic geography, language contact and typology to make use of some type of distance metric between lects. However, most work so far has either used Euclidean distances, or geodesic distance, both of which do not represent the real separation between communities very accurately. This paper presents two datasets: one on walking distances and one on topographic distances between over 8700 lects across all macro-areas. We calculated walking distances using Open Street Maps data, and topographic distances using digital elevation data. We evaluate these distance metrics on three case studies and show that from the four distances, the topographic and geodesic distances showed the most consistent performance across datasets, and would be likely to be reasonable first choices. At the same time, in most cases, the Euclidean distances were not much worse than the other distances, and might be a good enough approximation in cases for which performance is critical, or the dataset cover very large areas, and the point-location information is not very precise.

The impact of urban configuration types on urban heat islands, air pollution, CO2 emissions, and mortality in Europe: a data science approach

The world is becoming increasingly urbanised. As cities around the world continue to grow, it is important for urban planners and policy makers to understand how different urban configuration patterns affect the environment and human health. However, previous studies have provided mixed findings. We aimed to identify European urban configuration types, on the basis of the local climate zones categories and street design variables from Open Street Map, and evaluate their association with motorised traffic flows, surface urban heat island (SUHI) intensities, tropospheric NO2, CO2 per person emissions, and age-standardised mortality. We considered 946 European cities from 31 countries for the analysis defined in the 2018 Urban Audit database, of which 919 European cities were analysed. Data were collected at a 250 m × 250 m grid cell resolution. We divided all cities into five concentric rings based on the Burgess concentric urban planning model and calculated the mean values of all variables for each ring. First, to identify distinct urban configuration types, we applied the Uniform Manifold Approximation and Projection for Dimension Reduction method, followed by the k-means clustering algorithm. Next, statistical differences in exposures (including SUHI) and mortality between the resulting urban configuration types were evaluated using a Kruskal-Wallis test followed by a post-hoc Dunn's test. We identified four distinct urban configuration types characterising European cities: compact high density (n=246), open low-rise medium density (n=245), open low-rise low density (n=261), and green low density (n=167). Compact high density cities were a small size, had high population densities, and a low availability of natural areas. In contrast, green low density cities were a large size, had low population densities, and a high availability of natural areas and cycleways. The open low-rise medium and low density cities were a small to medium size with medium to low population densities and low to moderate availability of green areas. Motorised traffic flows and NO2 exposure were significantly higher in compact high density and open low-rise medium density cities when compared with green low density and open low-rise low density cities. Additionally, green low density cities had a significantly lower SUHI effect compared with all other urban configuration types. Per person CO2 emissions were significantly lower in compact high density cities compared with green low density cities. Lastly, green low density cities had significantly lower mortality rates when compared with all other urban configuration types. Our findings indicate that, although the compact city model is more sustainable, European compact cities still face challenges related to poor environmental quality and health. Our results have notable implications for urban and transport planning policies in Europe and contribute to the ongoing discussion on which city models can bring the greatest benefits for the environment, climate, and health. Spanish Ministry of Science and Innovation, State Research Agency, Generalitat de Catalunya, Centro de Investigación Biomédica en red Epidemiología y Salud Pública, and Urban Burden of Disease Estimation for Policy Making as a Horizon Europe project.