HDS-LEE Seminar Series - Ribana Roscher
We cordially invite you to the “HDS-LEE Seminar Series”, where data science experts from the application areas Life, Earth and Energy present the current state of their research to interested researchers. The goal is that the doctoral researches get to know the experts in the individual fields and have the opportunity to interact and discuss with them. It is organized by HDS-LEE.
Talk title: Generating the Unseen and Explaining the Seen - On the use of explainable machine learning for the agricultural and environmental sciences
Speaker: Prof. Ribana Roscher
Deep generative models and explainable machine learning are two emerging areas of data science that we can use to address current challenges in agricultural and environmental sciences. Deep generative models are neural networks capable of learning the complex underlying data distribution. They can be used for a variety of applications, such as the forecasting of the future appearance of objects. Explainable machine learning, which analyzes the decision-making process of machine learning methods in more detail, is used whenever an explanation for the result is required in addition to the result. This can be done for various reasons, e.g., to increase confidence in the outcome or to derive new scientific knowledge that can be inferred from patterns in the decision process of the machine learning model. This talk addresses methods from both areas and provides examples of their application in agricultural and environmental sciences.