I like studying and using Machine Learning to tackle challenges faced by our society and human beings. My background is in Applied Mathematics, however underpinned by a core multidisciplinary engineering curriculum. I have a keen interest in kernel methods, bayesian statistics and put a particular emphasis on research open access and reproducibility. My latest focus has been on using deep generative models to enhance and fuse remote-sensing imagery products in order to overcome limited access to high spatial and temporal resolution earth observations. I have also worked on data-space regularization strategies for neural networks in computer vision.
Can observations be combined to better understand aerosol-cloud relationships?
Obtaining better measurements of the state of the atmosphere
