13 Zentrale Universitätseinrichtungen

Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/14

Browse

Filters

2020 - 20222

Settings

Institute: search.filters.UBSInstitut.Höchstleistungsrechenzentrum Stuttgart (HLRS)Subject: search.filters.subject.710

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Urban digital twins for smart cities and citizens : the case study of Herrenberg, Germany
    (2020) Dembski, Fabian; Wössner, Uwe; Letzgus, Mike; Ruddat, Michael; Yamu, Claudia
    Cities are complex systems connected to economic, ecological, and demographic conditions and change. They are also characterized by diverging perceptions and interests of citizens and stakeholders. Thus, in the arena of urban planning, we are in need of approaches that are able to cope not only with urban complexity but also allow for participatory and collaborative processes to empower citizens. This to create democratic cities. Connected to the field of smart cities and citizens, we present in this paper, the prototype of an urban digital twin for the 30,000-people town of Herrenberg in Germany. Urban digital twins are sophisticated data models allowing for collaborative processes. The herein presented prototype comprises (1) a 3D model of the built environment, (2) a street network model using the theory and method of space syntax, (3) an urban mobility simulation, (4) a wind flow simulation, and (5) a number of empirical quantitative and qualitative data using volunteered geographic information (VGI). In addition, the urban digital twin was implemented in a visualization platform for virtual reality and was presented to the general public during diverse public participatory processes, as well as in the framework of the “Morgenstadt Werkstatt” (Tomorrow’s Cities Workshop). The results of a survey indicated that this method and technology could significantly aid in participatory and collaborative processes. Further understanding of how urban digital twins support urban planners, urban designers, and the general public as a collaboration and communication tool and for decision support allows us to be more intentional when creating smart cities and sustainable cities with the help of digital twins. We conclude the paper with a discussion of the presented results and further research directions.
  • Thumbnail Image
    ItemOpen Access
    Soya yield prediction on a within-field scale using machine learning models trained on Sentinel-2 and soil data
    (2022) Pejak, Branislav; Lugonja, Predrag; Antić, Aleksandar; Panić, Marko; Pandžić, Miloš; Alexakis, Emmanouil; Mavrepis, Philip; Zhou, Naweiluo; Marko, Oskar; Crnojević, Vladimir
    Agriculture is the backbone and the main sector of the industry for many countries in the world. Assessing crop yields is key to optimising on-field decisions and defining sustainable agricultural strategies. Remote sensing applications have greatly enhanced our ability to monitor and manage farming operation. The main objective of this research was to evaluate machine learning system for within-field soya yield prediction trained on Sentinel-2 multispectral images and soil parameters. Multispectral images used in the study came from ESA’s Sentinel-2 satellites. A total of 3 cloud-free Sentinel-2 multispectral images per year from specific periods of vegetation were used to obtain the time-series necessary for crop yield prediction. Yield monitor data were collected in three crop seasons (2018, 2019 and 2020) from a number of farms located in Upper Austria. The ground-truth database consisted of information about the location of the fields and crop yield monitor data on 411 ha of farmland. A novel method, namely the Polygon-Pixel Interpolation, for optimal fitting yield monitor data with satellite images is introduced. Several machine learning algorithms, such as Multiple Linear Regression, Support Vector Machine, eXtreme Gradient Boosting, Stochastic Gradient Descent and Random Forest, were compared for their performance in soya yield prediction. Among the tested machine learning algorithms, Stochastic Gradient Descent regression model performed better than the others, with a mean absolute error of 4.36 kg/pixel (0.436 t/ha) and a correlation coefficient of 0.83%.