用深度分割网络提升地震速度反演精度，效果优于传统方法。
Seismic Velocity Inversion from Multi-Source Shot Gathers Using Deep Segmentation Networks: Benchmarking U-Net Variants and SeismoLabV3+
- 采用U-Net、U-Net++和DeepLabV3+等网络结构进行速度场预测
- SeismoLabV3+在测试集上达到0.031246的MAPE，表现最佳
- 专为地震数据优化的模型设计适合地质勘探领域应用
地震速度反演是地球物理勘探中的关键任务，用于从地震波数据重建地下结构，对高分辨率成像与解释至关重要。传统基于物理的全波形反演（FWI）方法计算成本高、对初始值敏感，且受限于地震数据带宽。近年来，深度学习方法将速度反演视为密集预测任务，实现数据驱动求解。本研究基于ThinkOnward 2025 Speed & Structure数据集，对三种先进编码器-解码器架构——U-Net、U-Net++和DeepLabV3+，以及改进版DeepLabV3+ SeismoLabV3+（采用ResNeXt50 32x4d主干网络并添加任务特定优化）进行了基准测试。实验结果显示，SeismoLabV3+表现最优，在内部验证集上MAPE为0.03025，在隐藏测试集上为0.031246（由官方排行榜评分）。结果表明，深度分割网络适用于地震速度反演，且针对任务的架构优化显著提升性能。
原文摘要 · Abstract (English)
Seismic velocity inversion is a key task in geophysical exploration, enabling the reconstruction of subsurface structures from seismic wave data. It is critical for high-resolution seismic imaging and interpretation. Traditional physics-driven methods, such as Full Waveform Inversion (FWI), are computationally demanding, sensitive to initialization, and limited by the bandwidth of seismic data. Recent advances in deep learning have led to data-driven approaches that treat velocity inversion as a dense prediction task. This research benchmarks three advanced encoder-decoder architectures -- U-Net, U-Net++, and DeepLabV3+ -- together with SeismoLabV3+, an optimized variant of DeepLabV3+ with a ResNeXt50 32x4d backbone and task-specific modifications -- for seismic velocity inversion using the ThinkOnward 2025 Speed \& Structure dataset, which consists of five-channel seismic shot gathers paired with high-resolution velocity maps. Experimental results show that SeismoLabV3+ achieves the best performance, with MAPE values of 0.03025 on the internal validation split and 0.031246 on the hidden test set as scored via the official ThinkOnward leaderboard. These findings demonstrate the suitability of deep segmentation networks for seismic velocity inversion and underscore the value of tailored architectural refinements in advancing geophysical AI models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。