Masterarbeit (w/m/d): Messung Solarstrahlung mittels HDR-Bilder & Deep Learning

About

The Institute for Solar Research develops innovative technologies for the use of solar energy, focusing on electricity generation and the provision of heat and fuels. The primary goal is to contribute to the energy and heat transition and to a reduction in fossil fuels using solar energy.

What to expect

In the Solar Energy Meteorology working group, methods are developed to derive measurements and short-term forecasts of solar radiation from the image information of cloud cameras, thereby supporting the efficient and grid-friendly operation of photovoltaic power plants.

In this thesis, a method for determining solar diffuse radiation is to be further developed, which uses the image of a cloud camera and the measurement of a pyranometer (global radiation) as input data. The measurement uses a radiometric camera model and a multimodal machine learning model based on image and tabular data. Currently, low dynamic range images are to be replaced by High Dynamic Range (HDR) images, which are generated from exposure series. It is expected that this will allow the area around the sun to be captured better, leading to more accurate and, in particular, more robust measurements overall.

You will work in a diverse and motivated team on energy transition issues, actively contribute to climate protection, and gain practical experience – in machine learning, software development, automated testing, version control, and modern image processing. As a special feature, a workplace in Almería, one of the sunniest locations in Europe, awaits you.

Your tasks

• Introduction to data-driven and, to a lesser extent, physical approaches relevant to the task
• Ensuring the valid function of the updated physical model component for the use of HDR images through suitable tests
• Preparation of multimodal datasets of camera images, pyranometer measurements, and derived tabular data
• Implementation of an updated deep learning model architecture
• Development and implementation of an updated training strategy with a focus on maximum transferability between locations and different camera hardware
• In-depth validation and evaluation of the further developed method compared to a previous approach
• Documentation of the methodology and results in a well-structured master's thesis

What you bring

• You are studying for a Master's degree in Computer Science, Physics, Mathematics, Engineering, or a related field and have good academic performance.
• Experience in Python and basic knowledge in the field of Machine Learning
• Ability to work independently and at the same time work in a team
• Strong self-motivation
• Previous experience in data analysis, computer vision, and Git version control is desirable
• Previous experience in radiometry, digital photography, image processing is desirable
• Good English skills, both written and spoken

We look forward to getting to know you!

Questions about this position (Reference number 4267) can be answered by:

Dr. Stefan Wilbert Tel.: +49 2203 601 4619