Suchergebnisse

Understanding the patterns of urban temperature a high spatial and temporal resolution is of large importance for urban heat adaptation and mitigation. Machine learning offers promising tools for high-resolution modeling of urban heat, but it requires large amounts of data. Measurements from official weather stations are too sparse but could be complemented by crowd-sensed measurements from citizen weather stations (CWS). Here we present an approach to model urban temperature using the quantile regression forest algorithm and CWS, open government and remote sensing data. The analysis is based on data from 691 sensors in the city of Zurich (Switzerland) during a heat wave using data from for 25-30th June 2019. We trained the model using hourly data from for 25-29th June (n = 71,837) and evaluate the model using data from June 30th (n = 14,105). Based on the model, spatiotemporal temperature maps of 10 × 10 m resolution were produced. We demonstrate that our approach can accurately map urban heat at high spatial and temporal resolution without additional measurement infrastructure. We furthermore critically discuss and spatially map estimated prediction and extrapolation uncertainty. Our approach is able to inform highly localized urban policy and decision-making. ; ISSN:2212-0955

Abstract. Extreme temperatures have reached unprecedented levels in many regions of the globe due to climate change, and a further increase is expected. Besides other consequences, high temperatures increase the mortality risk and severely affect the labour productivity of workers. We perform a high-resolution spatial analysis to assess the impacts of heat on mortality and labour productivity in Switzerland and project their development under different Representative Concentration Pathway (RCP) scenarios, considering that no socio-economic changes take place. The model is based on the risk framework of the Intergovernmental Panel on Climate Change (IPCC), which combines the three risk components: hazard, exposure, and vulnerability. We model the two impact categories in the same spatially explicit framework, and we integrate uncertainties into the analysis by a Monte Carlo simulation. We model first that about 658 deaths are associated with heat exposure currently each year in Switzerland. Second, the economic costs caused by losses in labour productivity amount to around CHF 665 million (approx. USD 700 million) per year. Should we remain on an RCP8.5 emissions pathway, these values may double (for mortality) or even triple (for labour productivity) by the end of the century. Under an RCP2.6 scenario impacts are expected to slightly increase and peak around mid-century, when climate is assumed to stop warming. Even though uncertainties in the model are large, the underlying trend in impacts is unequivocal. The results of the study are valuable information for political discussions and allow for a better understanding of the cost of inaction.

Extreme temperatures have reached unprecedented levels in many regions of the globe due to climate change anda further increase is expected. Besides other consequences, high temperatures increase the mortality risk and severely affectthe labour productivity of workers. We perform a high-resolution spatial analysis to assess the impacts of heat on mortality and labour productivity in Switzerland and project their development under different Representative Concentration Pathway (RCP) scenarios, considering that no socio-economic changes takes place. The model is based on the risk framework of the Intergovernmental Panel on Climate Change (IPCC), which combines the three risk components: Hazard , Exposure , and Vulnerability . We model the two impact categories in the same spatially explicit framework and we integrate uncertainties into the analysis through a Monte Carlo simulation. We model, that first, about 670 people die today per year because of heat in Switzerland. Second, the economic costs caused by losses in labour productivity amount to around CHF 413 million (approx. $ 465 million) per year. Should we remain on an RCP8.5 emissions pathway, these values may double (for mortality) or even triple (for labour productivity) by the end of the century. Under an RCP2.6 scenario impacts are expected to slightly increaseand peak around mid-century, when climate is assumed to stop warming. Even though uncertainties in the model are large, theunderlying trend in impacts is unequivocal. The results of the study are valuable information for political discussions and allowfor a better understanding of the cost of inaction.

Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change. ; ISSN:1932-6203

Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change.

Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change. ; TU Berlin, Open-Access-Mittel - 2020