Bridging quantum information theory and atmospheric science, we develop a hybrid quantum-classical architecture that accelerates deep neural network training on high-dimensional climate grids. By deploying tensor network states on superconducting quantum processors, we demonstrate polynomial speedups over classical meteorological forecasting.
The full manuscript includes introduction, methodology, results, discussion, conclusion, figures, tables, and complete bibliography with all 2 references.
↓ Download Full PDF (88-106)