Recovering the parameters underlying the Lorenz-96 chaotic dynamics
This work addresses uncertainty in climate projections for climate scientists, but it is incremental as it applies existing deep learning methods to a known chaotic model.
The study tackled the problem of uncertain climate sensitivity due to subjective parameterization in climate models by using deep network algorithms to infer parameters in a data-driven way, achieving performance comparisons in recovering parameters from the Lorenz-96 model.
Climate projections suffer from uncertain equilibrium climate sensitivity. The reason behind this uncertainty is the resolution of global climate models, which is too coarse to resolve key processes such as clouds and convection. These processes are approximated using heuristics in a process called parameterization. The selection of these parameters can be subjective, leading to significant uncertainties in the way clouds are represented in global climate models. Here, we explore three deep network algorithms to infer these parameters in an objective and data-driven way. We compare the performance of a fully-connected network, a one-dimensional and, a two-dimensional convolutional networks to recover the underlying parameters of the Lorenz-96 model, a non-linear dynamical system that has similar behavior to the climate system.