Your Mission The Institute of Solar Research is committed to advancing the application of solar energy. Reliable information on solar resources is essential. The Institute's Energy Meteorology Group collects meteorological data and identifies parameters essential for the design, operation and qualification of solar power plants. Clouds are the main cause of shortwave solar irradiance variability, which affects the performance of solar power plants and electricity grids. The Institute of Solar Research is one of the leading groups in the development of short-term solar irradiance forecasts. The automatic detection and classification of clouds based on high-resolution sky images is one of the most important steps in the generation of such forecasts. The use of deep learning (DL) in computer vision has led to massive advances in this area. However, due to the high variability and complexity of the conditions, there is still a need for improvement, especially under multi-layer cloud conditions. One challenge in training such models is the lack of sufficient reference data. The tedious task of manually labeling images is very time consuming and error prone. Objective of the Master's Thesis: The aim of this thesis is to create and evaluate a large reference dataset for deep learning cloud detection and classification models. The dataset will be created by combining synthetic data with weakly labeled and labeled data. The benefits of optical flow techniques for further data augmentation will be evaluated, especially under complex multi-layer conditions. In order to achieve this goal, the following tasks will be carried out: Conduct a literature review on image segmentation/classification, data augmentation, synthetic image data, weakly labeled data, semi-supervised learning, and other relevant topics Develop a GUI for manual evaluation and labeling of sky images Create and evaluate synthetic sky images (e.g. using Blender) Implement data augmentation techniques based on optical flow and/or weakly labeled techniques Train DL models (e.g. CNN) for cloud detection and classification Benchmark results of cloud detection and classification models with already existing models Summarize the results and findings in a well-structured Master's thesis Organizational Notes: Location: Almería, Spain Minimum Period: 6 months (extendable) Ongoing university studies in computer science, mathematics, physics, or engineering (Diplom/Master, Uni/FH)Background in machine learningStrong programming skills in Python (experience in Pytorch desired)Familiarity with software versioning tools (git/gitlab) advantageousExperience with Blender advantageousProficient in oral and written EnglishGerman and/or Spanish language skills are beneficial (not required) Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development. Our unique infrastructure offers you a working environment in which you have unparalleled scope to develop your creative ideas and accomplish your professional objectives. Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (f/m/x). Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.
