In this work, we evaluate the efficiency of a deep-convolutional neural network (CNN) to reconstruct missing data in chlorophyll-a satellite images. The missing area are mainly due to the presence of cloud above the ocean. The CNN-based methodology is compared with a sate-of-art krigging algorithm.

The rate of mass loss from the Greenland Ice Sheet (GrIS) has tripled over the last 20 years, reflecting strong climate warming over the region. Here I will present a review of some of the Greenland mass-balance evaluations that I have been involved with over the last 15 years. We will also review other recent estimates of GrIS mass change, including some very recent observational updates from satellite data, noting the impacts on global sea-level rise.

Stochastic parameterizations have been successfully used to represent the uncertainty associated with the parameterization of unresolved scale processes for ensemble forecasting and data assimilation systems. In order to accurately describe the uncertainty associated with numerical predictions, these parameterizations have to be optimized. We will introduce a novel technique based on hierarchical ensemble Kalman filters for the optimization of stochastic parameterizations for data assimilation applications.

The Madden--Julian oscillation (MJO), a planetary--scale eastward propagating coherent structure with periods of 30--60 days, is a prominent manifestation of intraseasonal variability in the tropical atmosphere.
It is widely presumed that small--scale moist cumulus convection is a critical part of its dynamics.
However, the recent results from high--resolution modeling as well as data analysis suggest that the MJO may be understood by dry dynamics to a leading--order approximation.