In my research I work with probabilistic machine learning methods for modeling data with spatial and temporal dependencies. I am motivated by applications of machine learning to earth system modeling, such as weather forecasting and climate modeling. Part of my research is in core machine learning method development, where unique challenges from earth science act as an underlying motivation. These challenges include irregular observations, high-dimensional data, complex temporal dynamics and the need for accurate uncertainty estimates. I also enjoy developing methods specifically for earth science applications, tailoring the machine learning methods using domain knowledge to solve relevant problems in new ways.