← 研踪 PaperTrailarXiv:2610.39777 · v1
Surface Conditioning for Zero-Shot Multivariate Correction in a Marine Biogeochemistry Emulator
首次提交 2026-10-29 18:29
版本更新 2026-10-29 18:29
雷达观测 2026-10-30 13:28
摘要
Bias correction in process-based models usually means iterative data assimilation with explicit covariance modelling. We propose a lightweight alternative based on a neural emulator of marine biogeochemistry (BGC), showing that the conditioning pathway of its autoencoder can serve as an observation injection point. The decoder is conditioned on surface variables via Feature-wise Linear Modulation (FiLM), originally designed to incorporate physical boundary forcings. We extend these inputs to include surface chlorophyll-a and replace the simulated field with satellite observations at inference time. The surface substitution propagates through the water column, improving agreement with depth-resolved observations at all depths, and spreads to other output variables in a pattern consistent with expected trophic relationships.
期刊信息：NeurIPS workshop Sim2sci 2026, Dec 2026, Paris, France
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-29 18:29 · 最新观测版本
Surface Conditioning for Zero-Shot Multivariate Correction in a Marine Biogeochemistry Emulator
Bias correction in process-based models usually means iterative data assimilation with explicit covariance modelling. We propose a lightweight alternative based on a neural emulator of marine biogeochemistry (BGC), showing that the conditioning pathway of its autoencoder can serve as an observation injection point. The decoder is conditioned on surface variables via Feature-wise Linear Modulation (FiLM), originally designed to incorporate physical boundary forcings. We extend these inputs to include surface chlorophyll-a and replace the simulated field with satellite observations at inference time. The surface substitution propagates through the water column, improving agreement with depth-resolved observations at all depths, and spreads to other output variables in a pattern consistent with expected trophic relationships.
查看此版本解读 →查看此版本原文 ↗