As a Senior Scientist for Machine Learning at Fraunhofer IEE and as the head of the BMBF-funded junior research group RL4CES at the University of Kassel, I am dedicated to the task of using machine learning to optimize processes in the energy sector. My academic career, shaped by a degree in computer science with a focus on theoretical computer science and a doctorate in machine learning, forms the foundation for my specialization in innovative learning methods such as self-supervised learning and few-shot learning.
As the project leader of this ambitious initiative, I aim to redefine the approval process for wind farms by developing an AI-powered system. This system is designed to enable the automated identification of species potentially at risk from wind turbines. By leveraging advanced deep learning techniques, complemented by an intuitive interface made comprehensible through Explainable AI methods, we are making a significant contribution to accelerating the transition to renewable energy.
Gaining a degree in physics, I initially focussed on the search for extra-solar planets until my professional focus led me back to our planet and specifically to the integration of renewable energies into our energy system.
What particularly fascinates me about the DBD project is that it focuses on the connection between sustainable energy production and species conservation and utilizes innovative deep learning approaches. I am particularly motivated by the areas of few shot learning and self supervised learning, as they support the development of efficient and low-resource models. They also enable increasing independence from elaborately annotated data, which is often challenging and time-consuming to obtain. As the protection of our natural environment and its biodiversity is close to my heart, I am delighted to be able to participate in this project.
I hold a doctorate in machine learning. In DBD, I work on generative models and methods for audio and image classification. One aspect that particularly fascinates me is linking different modalities such as audio and image data. I also always find it exciting to discover the solutions and results machine learning methods come up with based on their training data and optimization goals. The world of birds offers some particularly interesting special cases and problems.
With solid mathematical competencies gained from my master's degree at the University of Augsburg, I am currently working on my PhD in the exciting field of trustworthy artificial intelligence. In our DeepBirdDetect project, I focus on the interpretability of deep learning models for bird detection. My goal is to make the complex decision-making processes of these models comprehensible and transparent for us humans. I find it particularly inspiring that our research does not only provide theoretical insights, but also creates practical solutions in the areas of animal welfare and the energy transition.
How can computers learn to recognize birds by their calls? As a postdoc at Chemnitz University of Technology and the K. Lisa Yang Centre for Conservation Bioacoustics, I am trying to find an answer to this question. My research mainly focuses on the recognition and classification of bird calls using machine learning. Automated monitoring of bird vocal activity and species diversity can be an important tool for ornithologists, conservation biologists and birdwatchers for long-term monitoring of critical environmental niches.
With a background in computer vision and deep learning, I mainly focus on developing new methods for processing large data collections of environmental sounds. Since 2022, I also lead the AI junior research group "BirdNET+". Our team continues the work on a bird call recognition system. Our goal is to support experts and citizen scientists in their work to monitor and protect our birds by developing a wide range of applications such as smartphone apps, public demonstrators, web interfaces and robust analysis frameworks.
I completed my master's degree in applied computer science at Chemnitz University of Technology. Since my thesis was supervised by Stefan Kahl, I was already in contact with BirdNET at that time. After graduating in 2021, I initially worked as a software developer for two years until Stefan offered me the opportunity to work on DeepBirdDetect. For me, the most fascinating part of the project is using AI for preserving nature and protecting species.
I completed my master's degree in applied computer science at the Chair of Media Informatics at Chemnitz University of Technology and am currently a PhD student in the field of artificial intelligence, specifically in bioacoustics. My current work focusses on the further development of the BirdNET project into BirdNET+. This initiative aims to improve the acoustic monitoring of bird species. Since joining the project, I have gained fascinating insights into the communication patterns of birds. It is particularly inspiring to see how AI technologies can help to develop effective strategies for environmental protection.
After my master's degree, I started my PhD in natural language processing. My work focussed on transformer models and active learning via self-supervised learning. I switched to the DeepBirdDetect project to apply the researched methods to a practical and challenging problem. My goal is to have a real impact on climate change and nature conservation with my research.
In my research group, I develop approaches and methods that enable technical systems to make intelligent decisions autonomously. My research focusses on dealing with unknown situations and providing performance in highly disturbed conditions. We also work intensively on self-learning processes in order to continuously develop technical systems during operation. In the DeepBirdDetect project, we are able to further develop and utilize these approaches in a practical manner.
I have been a doctoral student in the Intelligent Systems group at Kiel University since March 2023 and I am supervised by Prof Dr Sven Tomforde. Previously, I completed my master's degree in computer science with the thesis "Autonomous ship collision avoidance trained on observational data". In the DeepBirdDetect project, I can combine my interest in birdlife with machine learning techniques. My research focus is in the area of self-supervised learning and few-shot learning.
I am a research assistant at CAU in the Intelligent Systems Group under Professor Sven Tomforde supervision. With a master’s degree in electrical engineering and 2years experience in the industry as an electrical engineer, I am passionate about the applied sciences and the impact of scientific research on real world challenges especially those related to environmental protection. My research focuses on intelligent decision making in the DBD project using ML techniques.
I studied computer science and psychology at the Humboldt-University of Berlin. I have been working as a research associate at the Museum für Naturkunde since 2012. The Animal Sound Archive located there has offered me the ideal opportunity to work intensively on various methods of acoustic pattern recognition for the identification of birds and other animal species in audio recordings. Through regular participation in programming competitions for automated species recognition (e.g. BirdCLEF and DCASE), I have been able to further expand my experience in this field over the years. I am very much looking forward to contributing my knowledge to the DBD project and helping to develop new AI models for environmental monitoring and as a useful tool for nature and species conservation.
EN 
DE