We are a group of computer scientists with ten years of experience developing data analytics methods in interdisciplinary research projects.
Our data analytics methods support users’ in conducting the essential data analytics steps 1) to identify appropriate data for the scientific scenario at hand, 2) to understand data’s properties, 3) to extract relevant information from the data, and 4) to interpret and explain the extracted information.
What is the data science project’s research question? The scientific question is to extract relevant information from classifiers (which we assume to be black boxes) that support scientists a) to interpret the classification results and b) to understand the internal mechanics of the classification process.
What data will be worked on? The proposed project will closely collaborate with the AI4Flood project (https://www.helmholtz.ai/themenmenue/our-model/funding-lines/project-call-2019/index.html). Therefore, the project will extend our current XAI approach to neural network classifiers trained to detect flood events.
What tasks will this project involve? The project involves developing ideas on what information needs to be extracted and how to extract and depict the information to our collaborators in the AI4Flood project.
What makes this project interesting to work on? The project’s research and development efforts contribute to a better understanding of the driving factors in flood detection. The developed XAI methods will support our collaborators to understand flood events better. The project will also contribute to building trust in the used classification methods, which is critical in establishing early warning systems that will save people’s lives.
What is the expected outcome? Contribution to research paper
What infrastructure, programs and tools will be used? Can they be used remotely? The candidates need a personal computer and network connections. We used the open-source programming language “python” to implement an initial XAI prototype. We expect the candidates to have a significant background in the “python” language to integrate new ideas into the existing prototype. We use git to organize our research and development activities.
What skills are necessary for this project? Data analytics / statistics, Data mining / Machine learning
Is the data open source? Yes
Interested candidates should be at Phd level . Mike Sips is looking for 1 visiting scientist , working on the project together with the team.