发表机构
Institute of Geophysics, China Earthquake Administration; Laboratory of Seismology and Physics of Earth’s Interior, School of Earth and Space Sciences, University of Science and Technology of China; Institute of Advanced Technology, University of Science and Technology of China; University of Chinese Academy of Sciences（中国地震局地球物理研究所; 中国科学技术大学地球和空间科学学院地球内部地震学与物理实验室; 中国科学技术大学先进技术研究院; 中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究利用图像形态学作为结构先验，结合物理观测推断地球属性，在未见模型上降低投影误差四倍，并区分了可复用形态与跨属性耦合的贡献。
AI 中文摘要
结构学习与物理属性推断可以借鉴不同的知识来源。我们利用33,140张自然图像、卫星图像和纹理图像学习形态学，无需地质训练模型，然后从物理观测中推断地球属性。相同的冻结权重将128个坐标映射到每个$256\ imes256$的压缩波速度、剪切波速度或密度场。固定的适配器赋予物理意义；观测特定的似然函数确定新的后验，无需重新训练。在256个未见过的地球模型中，图像坐标将投影误差相对于维度匹配的余弦基降低了四倍。匹配的反演对于测试的弯曲速度目标更倾向于图像坐标，而对于测试的断层目标则更倾向于光滑径向基。一个简化的2.5维应用，沿南加州一条120.9公里剖面有915个实测观测值，约束了速度-密度对比。相对于预训练的图像先验，分组走时和重力误差分别下降了43%和44%，尽管匹配的光滑径向基预测更好。直接的分层瑞利波更新在五个站点将盲相速度误差降低了28%，而仅P波和重力共享则使其恶化，这区分了可复用的形态学与有益的跨属性耦合。这些结果建立了一种实用的分离：图像提供结构替代方案，而异质物理观测决定其实验特定的后验概率。
英文摘要
Structural learning and physical-property inference can draw on different sources of knowledge. We learn morphology from 33,140 natural, satellite, and texture images, without geological training models, then infer Earth properties from physical observations. Identical frozen weights map 128 coordinates into each $256\times256$ compressional-velocity, shear-velocity, or density field. Fixed adapters assign physical meaning; observation-specific likelihoods determine new posteriors without retraining. Across 256 unseen Earth models, image coordinates reduce projection error fourfold relative to a dimension-matched cosine basis. Matched inversions favor image coordinates for the tested curved-velocity targets and a smooth radial basis for the tested faulted targets. A simplified 2.5-dimensional application with 915 measured observations along one 120.9-km southern-California profile constrains a velocity--density contrast. Grouped arrival-time and gravity errors fall by 43% and 44% relative to the pretrained image prior, although the matched smooth radial basis predicts better. Direct layered-Rayleigh updating reduces blind phase-velocity error by 28% at five sites, whereas P-and-gravity-only sharing worsens it, distinguishing reusable morphology from beneficial cross-property coupling. These results establish a practical separation: images supply structural alternatives, and heterogeneous physical observations determine their experiment-specific posterior probabilities.
Comments45 pages, including supplementary material
