LoRA Adaptation Strength in Aurora-WRF: Trade-offs in Regional Heavy-Rainfall Forecasting

Excerpt

arXiv:2610.03747v1 Announce Type: cross Abstract: We investigate how parameter-efficient adaptation of an atmospheric foundation model affects downstream regional precipitation in a controlled Aurora-WRF coupling experiment over the Beijing-Tianjin-Hebei region. A single-step, precipitation-weighted LoRA adaptation of AuroraPretrained is trained on May-September 2020-2021 and selected using 2022 validation data. Five inference-time adaptation strengths are coupled to an unchanged 9-km WRF config