Predicting building types using OpenStreetMap

Atwal, Kuldip Singh; Anderson, Taylor; Pfoser, Dieter; Züfle, Andreas

doi:10.1038/s41598-022-24263-w

Cited by 30 publications

(8 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each POI data includes six attributes, namely "ID", "Code", "Type", "Name", "Longitude", and "Latitude". Following the POI classification standards established by OpenStreetMap [64][65][66] , the original POI data are classified into six categories: "Money", "Accommodation", "Public", "Catering", "Shopping", and "Traffic". The reclassification of POI data is shown in Table 2.…”

Section: Comparison With Traditional Methodsmentioning

confidence: 99%

Accurate Identification of Micro-scale Urban Functional Zones from the Perspective of Dialectical Materialism

Zhang

2023

Preprint

View full text Add to dashboard Cite

With the advancement of global urbanization, accurate identification of urban functional zones has become a crucial task for the high-quality development of cities. Traditional methods that rely on POI data are insufficient to accurately identify micro-scale urban functional zones. Thus, this study proposes a novel method for identifying urban functional zones based on VOI (Volume of Interest) data and applies it to a small region in Hong Kong for comparative research. Subsequently, the identification accuracy of the two methods is assessed using a confusion matrix and the Kappa Coefficient. The results show that the VOI data contains richer and more comprehensive urban spatial information compared to POI data, enabling a superior representation of connections and influences among different zones within cities. The study can be applied to analyse micro-scale urban functional zones in other cities, providing a new perspective for the in-depth research.

show abstract

Section: Comparison With Traditional Methodsmentioning

confidence: 99%

Accurate Identification of Micro-scale Urban Functional Zones from the Perspective of Dialectical Materialism

Zhang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The lack of reliable building occupancy type has led several researchers to explore using machine learning to predict this value. For instance, [1] achieved 98% accuracy in the binary classification task of predicting residential vs. non-residential occupancy type. To achieve this, the authors used other features within the OSM dataset to train a decision tree.…”

Section: Related Work and The Need For Machine Learningmentioning

confidence: 99%

Enhancing Flood Risk Assessment Through Machine Learning and Open Data

Narock¹,

Johnson²,

Rad³

2023

Preprint

View full text Add to dashboard Cite

Urban flooding causes billions of dollars in damages annually, with severe flood events becoming more frequent and destructive as our climate changes. While extreme weather is a primary driver of flooding, its consequences depend on the interconnectedness of urban systems - referred to as the Urban Multiplex, which includes the power grid, transportation network, natural surface water and groundwater systems, sewerage and drinking water systems, intertwined with the socioeconomic and public health sectors. One component of this multiplex - a reliable buildinginventory - is critical for assessing the number of people affected by flooding, the propagation of shocks throughout the economy, and for forecasting detailed socioeconomic risk from flooding. Yet, a major discrepancy exists in the way data about buildings are collected across the U.S. There is no harmonization in what data are recorded by city, county, or state governments, let alone at the national scale. We demonstrate how existing open source datasetscan be spatially integrated and subsequently used as training for machine learning models. These machine learning models can then predict building occupancy type, a currently lacking component of flood risk assessment. Multiplemachine learning algorithms are compared and an application to the 100-year flood in North Carolina is provided. Results indicate that a 100-year flood will disproportionately impact Mecklenburg, Wake, Dare, and Brunswick counties.

show abstract

“…To explore a technical path to adaptive to multiple cities research, this research combines the open-source data with the Envi-met tool to simplify the research workload. In this research, open-source data include open street map data and open-source meteorological data [15]. Open street map is non-profit data, which is built by public feedback.…”

Section: Introductionmentioning

confidence: 99%

Exploring the Effect of Aspect Ratio (H/W) on Thermal Environment in Multiple Climate Zones with Open-Source Data

Rao,

Zheng,

2024

Buildings

View full text Add to dashboard Cite

For a country with multiple climate zones, analyzing the impacts of urban design in different climate zones is a prerequisite to climate adaptation policies. However, countries advanced in climate adaptation strategies are mostly located in a single climate zone, leading to a lack of research on climate adaptation policies for multiple climate countries. As China is launching the urban zoning management policy, this research takes China as an example to explore a technique to quickly distinguish the impact of urban design in multiple climate zones by combing the open-source data with the Envi-met tool, where the open-source data indicate the data that can be obtained from public platforms such as the internet and Envi-met is a microclimate simulation tool. First, the open street map tool, one of the open-source data, was used to abstract the typical models of each climate city. Then, open-source meteorological data were employed as the boundary conditions for Envi-met simulation. Lastly, after the Envi-met simulation, the impacts of aspect ratio (H/W) on multiple climate indicators in seven climate cities were analyzed with the meteorological interpolation method. The analytical results show that H/W has a stronger ability to regulate the thermal comfort of high latitude cities. In Guangzhou and Changsha, the maximum differences of PET caused by H/W are only 0.61 °C (Changsha) and 0.63 °C (Guangzhou). H/W has the strongest regulating effect on the thermal comfort in Harbin, with the highest value of 8.62 °C. The regulating effects of H/W on outdoor PET in other 4 cities are 4.37 °C in Urumqi, 3.29 °C in Xining, 1.29 °C in Xi’an, and 0.76 °C in Kunming. In addition, H/W mainly affects PET by modifying the radiant temperature. Compared with mean radiant temperature, the effects of H/W on air temperature, relative humidity, and wind speed are negligible. Longitude regulates the occurrence time of the coldest and hottest thermal environments. Among the seven climate zones in China, the difference in appearance time between the coldest and hottest reaches up to 2 h. For the implementation of urban zoning management policy, in China, high latitude cities are encouraged to high H/W to create a comfortable city. Cities whose latitude is less than 30° may not consider the impacts of H/W on thermal comfort. This method of combining open-source data with Envi-met can serve as a reference for other countries that span multiple climate zones. In addition, these results provide a decision-making basis for the management of H/W in different climate cities of China.

show abstract

Predicting building types using OpenStreetMap

Cited by 30 publications

References 48 publications

Accurate Identification of Micro-scale Urban Functional Zones from the Perspective of Dialectical Materialism

Accurate Identification of Micro-scale Urban Functional Zones from the Perspective of Dialectical Materialism

Enhancing Flood Risk Assessment Through Machine Learning and Open Data

Exploring the Effect of Aspect Ratio (H/W) on Thermal Environment in Multiple Climate Zones with Open-Source Data

Contact Info

Product

Resources

About