2 results
Search Results
Now showing 1 - 2 of 2
- ItemLearning from urban form to predict building heights(San Francisco, California, US : PLOS, 2020) Milojevic-DupontI, Nikola; Hans, Nicolai; Kaack, Lynn H.; Zumwald, Marius; Andrieux, François; de Barros Soares, Daniel; Lohrey, Steffen; PichlerI, Peter-Paul; Creutzig, FelixUnderstanding 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.
- ItemHave wind turbines in Germany generated electricity as would be expected from the prevailing wind conditions in 2000-2014?(San Francisco, Ca. : PLOS, 2019) Germer, Sonja; Kleidon, AxelThe planning of the energy transition from fossil fuels to renewables requires estimates for how much electricity wind turbines can generate from the prevailing atmospheric conditions. Here, we estimate monthly ideal wind energy generation from datasets of wind speeds, air density and installed wind turbines in Germany and compare these to reported actual yields. Both yields were used in a statistical model to identify and quantify factors that reduced actual compared to ideal yields. The installed capacity within the region had no significant influence. Turbine age and park size resulted in significant yield reductions. Predicted yields increased from 9.1 TWh/a in 2000 to 58.9 TWh/a in 2014 resulting from an increase in installed capacity from 5.7 GW to 37.6 GW, which agrees very well with reported estimates for Germany. The age effect, which includes turbine aging and possibly other external effects, lowered yields from 3.6 to 6.7% from 2000 to 2014. The effect of park size decreased annual yields by 1.9% throughout this period. However, actual monthly yields represent on average only 73.7% of the ideal yields, with unknown causes. We conclude that the combination of ideal yields predicted from wind conditions with observed yields is suitable to derive realistic estimates of wind energy generation as well as realistic resource potentials. © 2019 Germer, Kleidon. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.