05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
Search Results
Item Open Access Deep learning based prediction and visual analytics for temporal environmental data(2022) Harbola, Shubhi; Coors, Volker (Prof. Dr.)The objective of this thesis is to focus on developing Machine Learning methods and their visualisation for environmental data. The presented approaches primarily focus on devising an accurate Machine Learning framework that supports the user in understanding and comparing the model accuracy in relation to essential aspects of the respective parameter selection, trends, time frame, and correlating together with considered meteorological and pollution parameters. Later, this thesis develops approaches for the interactive visualisation of environmental data that are wrapped over the time series prediction as an application. Moreover, these approaches provide an interactive application that supports: 1. a Visual Analytics platform to interact with the sensors data and enhance the representation of the environmental data visually by identifying patterns that mostly go unnoticed in large temporal datasets, 2. a seasonality deduction platform presenting analyses of the results that clearly demonstrate the relationship between these parameters in a combined temporal activities frame, and 3. air quality analyses that successfully discovers spatio-temporal relationships among complex air quality data interactively in different time frames by harnessing the user’s knowledge of factors influencing the past, present, and future behaviour with Machine Learning models' aid. Some of the above pieces of work contribute to the field of Explainable Artificial Intelligence which is an area concerned with the development of methods that help understand, explain and interpret Machine Learning algorithms. In summary, this thesis describes Machine Learning prediction algorithms together with several visualisation approaches for visually analysing the temporal relationships among complex environmental data in different time frames interactively in a robust web platform. The developed interactive visualisation system for environmental data assimilates visual prediction, sensors’ spatial locations, measurements of the parameters, detailed patterns analyses, and change in conditions over time. This provides a new combined approach to the existing visual analytics research. The algorithms developed in this thesis can be used to infer spatio-temporal environmental data, enabling the interactive exploration processes, thus helping manage the cities smartly.Item Open Access Pure tin halide perovskite solar cells : focusing on preparation and strategies(2022) Liu, Hairui; Zhang, Zuhong; Zuo, Weiwei; Roy, Rajarshi; Li, Meng; Byranvand, Mahdi Malekshahi; Saliba, MichaelMetal halide perovskite solar cells (PSCs) have emerged as an important direction for photovoltaic research. Although the power conversion efficiency (PCE) of lead‐based PSCs has reached 25.7%, still the toxicity of Pb remains one main obstacle for commercial adoption. Thus, to address this issue, Pb‐free perovskites have been proposed. Among them, tin‐based perovskites have emerged as promising candidates. Unfortunately, the fast oxidation of Sn2+ to Sn4+ leads to low stability and efficiency. Many strategies have been implemented to address these challenges in Sn‐based PSCs. This work introduces stability and efficiency improvement strategies for pure Sn‐based PSCs by optimization of the crystal structure, processing and interfaces as well as, implementation of low‐dimension structures. Finally, new perspectives for further developing Sn‐based PSCs are provided.Item Open Access How much photovoltaic efficiency is enough?(2022) Werner, Jürgen H.At present, the purchasing prices for silicon-based photovoltaic modules with 20% efficiency and more are between 20 and 40 EURct/Wp. These numbers correspond to 40 to 80 EUR/m2 and are in the same range as the mounting costs (material prices plus salaries) of such modules. Installers and operators of photovoltaic systems carefully balance the module and mounting costs when deciding among modules of different efficiencies. This contribution emulates the installer’s decision via a simple, analytical module mounting decision (Mo2De) model. A priori, the model, and the resulting conclusions are completely independent of the photovoltaically active material inside the modules. De facto, however, based on the present state (cost, efficiency, reliability, bankability, etc.) of modules fabricated from (single) crystalline Si cells, conclusions on other photovoltaic materials might also be drawn: On the one hand, the model suggests that lower-efficiency modules with efficiencies below 20% will be driven out of the market. Keeping in mind their installation costs, installers will ask for large discounts for lower-efficiency modules. Technologies based on organic semiconductors, CdTe, CIGS, and even multicrystalline Si, might not survive in the utility market, or in industrial and residential applications. Moreover, this 20% mark will soon reach 23%, and finally will stop at around 25% for the very best, large-area (square meter sized) commercial modules based on single crystalline silicon only. On the other hand, it also seems difficult for future higher-efficiency modules based on tandem/triple cells to compete with standard Si-based reference modules. Compared to their expected higher efficiency, the production costs of tandem/triple cell modules and, therefore, also their required markup in sales, might be too high. Depending on the mounting cost, the Mo2De-model predicts acceptable markup values of 1 EURct/Wp (for low mounting costs of around 10 EUR/m2) to 11 EURct/Wp (for high mounting costs of 100 EUR/m2) if the module efficiency increases from 23% to 30%. Therefore, a 23% to 24% module efficiency, which is possible with silicon cells alone, might be enough for many terrestrial photovoltaic applications.