跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.21769 · v1

Learning Calibrated and Samplable Predictive Distributions of Surface-Ocean $Δp$CO$_2$ Using Tabular Diffusion Models

首次提交 2026-11-17 03:03
版本更新 2026-11-17 03:03
雷达观测 2026-11-18 19:44
arXiv ↗PDF ↗

摘要

The ocean absorbs almost 30% of anthropogenic CO2_2 emissions, but quantifying this sink requires estimating surface-ocean CO2_2 from observations that are sparse in space and time. Most existing machine-learning estimates of this field are deterministic, giving a single value per grid point, with uncertainty approximated post hoc via residuals, ensembles, or prescribed distributions. We instead learn a conditional predictive distribution for each observation: using Treeffuser, a conditional diffusion model with gradient-boosted-tree score functions, we estimate the full predictive distribution of ΔpΔpCO2_2 (the sea-air ppCO2_2 difference) from 13 environmental, spatial, and temporal predictors. On a held-out SOCAT test set, Treeffuser attains the lowest continuous ranked probability score among the uncertainty-quantification methods evaluated (8.229 μμatm) and the coverage closest to the nominal 68% / 95% levels (0.686 / 0.930), while retaining point-prediction skill comparable to a deterministic XGBoost baseline (RMSE 18.4 vs. 17.7 μμatm; R2R^2 0.77 vs. 0.79). These results show that conditional diffusion can provide well-calibrated, observation-level uncertainties while largely preserving point-prediction skill. Because Treeffuser is generative, its samples can support probabilistic analyses of ΔpΔpCO2_2; extending this to spatially coherent field reconstruction will require modeling dependence across grid cells and evaluation on spatially held-out data.

作者备注:40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: Representations for the Physical Sciences

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

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 · 2026-11-17 03:03 · 最新观测版本

Learning Calibrated and Samplable Predictive Distributions of Surface-Ocean $Δp$CO$_2$ Using Tabular Diffusion Models

The ocean absorbs almost 30% of anthropogenic CO2_2 emissions, but quantifying this sink requires estimating surface-ocean CO2_2 from observations that are sparse in space and time. Most existing machine-learning estimates of this field are deterministic, giving a single value per grid point, with uncertainty approximated post hoc via residuals, ensembles, or prescribed distributions. We instead learn a conditional predictive distribution for each observation: using Treeffuser, a conditional diffusion model with gradient-boosted-tree score functions, we estimate the full predictive distribution of ΔpΔpCO2_2 (the sea-air ppCO2_2 difference) from 13 environmental, spatial, and temporal predictors. On a held-out SOCAT test set, Treeffuser attains the lowest continuous ranked probability score among the uncertainty-quantification methods evaluated (8.229 μμatm) and the coverage closest to the nominal 68% / 95% levels (0.686 / 0.930), while retaining point-prediction skill comparable to a deterministic XGBoost baseline (RMSE 18.4 vs. 17.7 μμatm; R2R^2 0.77 vs. 0.79). These results show that conditional diffusion can provide well-calibrated, observation-level uncertainties while largely preserving point-prediction skill. Because Treeffuser is generative, its samples can support probabilistic analyses of ΔpΔpCO2_2; extending this to spatially coherent field reconstruction will require modeling dependence across grid cells and evaluation on spatially held-out data.

查看此版本解读 →查看此版本原文 ↗