LiuFeng2317/OpenSWI

OpenSWI是一个全面的1D数据集，专门用于表面波频散曲线反演。该数据集包含从各种地质模型中获得的合成数据以及来自实际观测的数据，为评估和增强深度学习模型的一般化能力提供了宝贵的资源。数据集包括OpenSWI-Shallow，OpenSWI-Deep和OpenSWI-Real三部分，分别对应浅层和深层地质研究。OpenSWI-Shallow包含约2200万个1D速度剖面，每个剖面都配有相应的瑞利波频散曲线，适用于浅层地质结构的反演任务。OpenSWI-Deep包含约126万个1D速度剖面，适用于深层地质研究，包括全球和区域3D地质模型。OpenSWI-Real包含来自美国长滩和中国地震学参考模型项目的观测数据，用于评估模型性能。

OpenSWI is a comprehensive 1D dataset designed for surface-wave dispersion curve inversion. It includes synthetic data from various geological models and real-world observational data, providing a valuable resource for evaluating and enhancing the generalization capabilities of deep learning models. The dataset is divided into three main parts: OpenSWI-Shallow, OpenSWI-Deep, and OpenSWI-Real, catering to shallow and deep geological studies. OpenSWI-Shallow comprises approximately 22 million 1D velocity profiles, each paired with corresponding Rayleigh wave dispersion curves, suitable for shallow geological inversion tasks. OpenSWI-Deep includes about 1.26 million 1D velocity profiles derived from high-resolution 3D geological models, ideal for deep geological studies. OpenSWI-Real features observational data from Long Beach, USA, and the China Seismological Reference Model Project, providing real-world data for evaluating model performance.