条件扩散模型指导 CMIP6 温度预估，中位偏差减半
Guiding future global temperature distributions with simulations and observations
做气候风险分析的朋友可以看看：用扩散模型一次训练十七个 CMIP6 模型，采样时靠 guidance 把偏差中位数砍半，还修正了极端高温覆盖三倍高估的问题。比传统偏差校正强在保留模型间差异的同时逼近观测，搞气候 ML 的人值得跑一下代码。
一篇 arXiv 论文训练了单个条件扩散模型，基于十七个 CMIP6 模型与 ERA5 再分析数据，按模型身份、日期和 CO2 等效浓度生成空间连贯的逐日温度场。
采样时通过扩散引导（diffusion guidance）将各模拟气候模型的分布拉向观测，引导强度由保留模拟未来的 perfect-model 实验选定。在十七个合成目标上，引导使逐日温度第 1 和第 99 百分位的中位偏差减半以上，三种排放情景下全球年均温度 RMSE 降低 32-57%。
该框架纠正了 CMIP6 对极端高温覆盖范围约三倍的历史高估，并给出 SSP3-7.0 情景下 2080 年代典型日近半数全球陆地受并发极端事件影响的预估。
高效采样无需额外气候模拟即可生成大集合，逐日场概率评分上超过既有偏差校正方法。
Guiding future global temperature distributions with simulations and observations
Assessing climate risks requires projections of daily temperature distributions, including rare and spatially widespread extremes. Climate simulations are costly and biased, while correcting them toward observations risks suppressing inter-model differences. We train a single machine-learning emulator, a conditional diffusion model, on seventeen CMIP6 models and ERA5 reanalysis to generate spatially coherent daily temperature fields conditioned on model identity, date, and CO2-equivalent concentration. At sampling time, diffusion guidance reduces model biases by steering each emulated climate-model distribution toward observations, with its strength selected through perfect-model experiments using withheld simulated futures. Observational influence decreases with projection horizon and forcing. Across seventeen synthetic targets, guidance more than halves median biases in the 1st and 99th percentiles of daily temperature, improves probabilistic scores and reliability, and reduces median annual global-mean temperature RMSE by 32-57% across three emission scenarios. In a detailed benchmark, guidance also outperforms established bias corrections on daily-field probabilistic scores. Efficient sampling generates large ensembles without further climate simulations. For example, our framework corrects CMIP6's roughly threefold historical overestimate of extreme-heat coverage, yet projects that concurrent extremes will affect nearly half of global land on a typical day in the 2080s under SSP3-7.0.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：diffusion model、CMIP6、ERA5、气候变化，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Francesco Immorlano, Elijah Tavares, Felix Draxler, Juan Nathaniel, Violette Launeau, Duncan Watson-Parris, Padhraic Smyth, Pierre Gentine, Stephan Mandt），经 AITOP 多维评分管线结构化提炼。