@misc{Duering,
  type      = {Master Thesis},
  author    = {D{\"u}ring, Serjoscha},
  title     = {Between plan and reality: tracing the development dynamics of the Lanzhou New Area - a computational approach},
  doi       = {10.25643/bauhaus-universitaet.4000},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20191108-40002},
  school      = {Bauhaus-Universit{\"a}t Weimar},
  pages     = {78},
  abstract  = {Contemporary planning practice is often criticized as too design-driven with a lack of both quantitative evaluation criteria and employment of models that anticipate the self-organizational forces shaping cities, resulting in significant gaps between plan and reality. This study aims to introduce a modular toolbox prototype for spatial-analysis in data-poor environments. It is proposed to integrate designing, evaluation, and monitoring of urban development into one framework, thus supporting data-driven, on-demand urban design, and planning processes. The proposed framework's value will exemplarily be tested, focussing on the analysis and simulation of spatiotemporal growth trajectories taking the Lanzhou New Area as a case-study - a large scale new town project that struggles to attract residents and businesses. Conducted analysis suggests that more attention should be given to spatiotemporal development paths to ensure that cities work more efficiently throughout any stage of development. Finally, early hints on general design strategies to achieve this goal are discussed with the assistance of the proposed toolbox.},
  subject      = {Stadtplanung},
  language  = {en}
}
@article{DehghaniSalehiMosavietal.,
  author    = {Dehghani, Majid and Salehi, Somayeh and Mosavi, Amir and Nabipour, Narjes and Shamshirband, Shahaboddin and Ghamisi, Pedram},
  title     = {Spatial Analysis of Seasonal Precipitation over Iran: Co-Variation with Climate Indices},
  series = {ISPRS, International Journal of Geo-Information},
  volume    = {2020},
  journal   = {ISPRS, International Journal of Geo-Information},
  number    = {Volume 9, Issue 2, 73},
  publisher = {MDPI},
  doi       = {10.3390/ijgi9020073},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20200128-40740},
  pages     = {23},
  abstract  = {Temporary changes in precipitation may lead to sustained and severe drought or massive floods in different parts of the world. Knowing the variation in precipitation can effectively help the water resources decision-makers in water resources management. Large-scale circulation drivers have a considerable impact on precipitation in different parts of the world. In this research, the impact of El Ni{\~n}o-Southern Oscillation (ENSO), Pacific Decadal Oscillation (PDO), and North Atlantic Oscillation (NAO) on seasonal precipitation over Iran was investigated. For this purpose, 103 synoptic stations with at least 30 years of data were utilized. The Spearman correlation coefficient between the indices in the previous 12 months with seasonal precipitation was calculated, and the meaningful correlations were extracted. Then, the month in which each of these indices has the highest correlation with seasonal precipitation was determined. Finally, the overall amount of increase or decrease in seasonal precipitation due to each of these indices was calculated. Results indicate the Southern Oscillation Index (SOI), NAO, and PDO have the most impact on seasonal precipitation, respectively. Additionally, these indices have the highest impact on the precipitation in winter, autumn, spring, and summer, respectively. SOI has a diverse impact on winter precipitation compared to the PDO and NAO, while in the other seasons, each index has its special impact on seasonal precipitation. Generally, all indices in different phases may decrease the seasonal precipitation up to 100\%. However, the seasonal precipitation may increase more than 100\% in different seasons due to the impact of these indices. The results of this study can be used effectively in water resources management and especially in dam operation.},
  subject      = {Maschinelles Lernen},
  language  = {en}
}