AI Enhancement to Resolve the Planetary Boundary Layer in AIRS/AMSU Retrievals

Currently, the planetary boundary layer (PBL) is challenging to assess in PBL remote sensing retrievals from space. To address this, we have developed a new 3D deep neural network (DNN) which enhances detail and reduces noise in 3D granules of temperature and humidity retrieved from hyperspectral infrared and microwave sounders. We show that this approach improves accuracy and detail including key features such as capping inversions at the top of the PBL over land, resulting in improved accuracy in estimations of PBL height.