Showing physics.ao-phShow all
2 papers · 1 filter
physics.ao-ph2026
One2N: Recursive refinement breaks the resolution barrier for Earth-system AI
Yanyan Tan, Xiangjun Tian, Can Wang +14
Earth-system AI models approach kilometre-scale resolution, but halving grid spacing quadruples the grid-point count and end-to-end training cost. We introduce One2N, a recursive i…
physics.ao-ph2022
Handling errors in four-dimensional variational data assimilation by balancing the degrees of freedom and the model constraints: A new approach
Xiangjun Tian, Hongqin Zhang, Zhe Jin +5
For many years, strongly and weakly constrained approaches were the only options to deal with errors in four-dimensional variational data assimilation (4DVar), with the aim of bala…