发表机构
Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对尾迹规避的卫星验证难题，构建小型扩散模型检测尾迹，发现输入分辨率、数据增强至关重要，而预训练有害，为相关任务提供经验。
AI 中文摘要
尾迹是飞机留下的薄冰云。它们造成了航空变暖的很大一部分，而重新规划少数产生尾迹的航班可以避免其中大部分变暖。然而，只有卫星能够确认尾迹从未形成，避免尾迹才算数，而这一检查很困难：尾迹只有一到两个像素宽，仅覆盖0.18%的像素，并且与自然卷云非常相似。我们构建了一个小型扩散模型（8.4M参数，在一张GPU上训练）来检测尾迹，并进行了一项受控研究以找出哪些组件起作用。该模型达到了0.476的PR-AUC，而DeepLabV3+基线为0.414，改编的MedSegDiff为0.119。将CNN的输入分辨率加倍使其达到同等水平（0.499，p=0.07）。有三个经验适用于尾迹之外。首先，在设计新架构之前检查输入分辨率。其次，简单的翻转和旋转使准确率提高一倍以上，并且比我们测量的任何架构选择都更重要。第三，在尾迹形状上预训练模型是有害的：模型学会了细条纹出现在任何地方，并将它们画在空场景上。精确率降至1%，而基于召回率的指标仍将退化模型评为优秀，且没有阈值或引导启发式方法能修复这一失败。
英文摘要
Contrails are the thin ice clouds that aircraft leave behind. They cause a large share of aviation's warming, and rerouting the few flights that produce them could avoid much of it. However, an avoided contrail only counts if a satellite can confirm that it never formed, and this check is hard: contrails are one to two pixels wide, cover only 0.18% of pixels, and look very similar to natural cirrus. We build a small diffusion model (8.4M parameters, trained on one GPU) that detects them, and we run a controlled study to find out which components matter. The model reaches 0.476 PR-AUC, compared with 0.414 for a DeepLabV3+ baseline and 0.119 for an adapted MedSegDiff. Doubling the input resolution of the CNN brings it to parity (0.499, p=0.07). Three lessons apply beyond contrails. First, check the input resolution before designing a new architecture. Second, simple flips and rotations more than double accuracy and matter more than any architectural choice we measured. Third, pretraining the model on contrail shapes is harmful: the model learns that thin strokes appear everywhere and paints them onto empty scenes. Precision collapses to 1% while recall-based metrics still rate the degraded model as excellent, and no threshold or guidance heuristic repairs this failure.
CommentsAccepted into Tackling Climate Change with Machine Learning: workshop at NeurIPS 2026
