Simultaneous Automatic Picking and Manual Picking Refinement for First-Break

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-12
• Main Authors: Bai, Haowen, Zhao, Zixiang, Zhang, Jiangshe, Cui, Yukun, Zhang, Chunxia, Guo, Zhenbo, Wang, Yongjun
• Format: Article
• Language: English
• Subjects: Adaptability; Algorithms; Annotations; Automation; Data acquisition; Datasets; Deep learning; First-break picking; Geophysics; Labeling; Labelling; Labels; Machine learning; Manuals; microseismic signal; Neural networks; Noise measurement; noisy label learning; outlier sample; Probabilistic logic; Probabilistic models; Resource exploration; Seismic data; Signal processing algorithms; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3400977

First-break picking is a pivotal procedure in processing microseismic data for geophysics and resource exploration. Recent advancements in deep learning have catalyzed the evolution of automated methods for identifying first-break. Nevertheless, the complexity of seismic data acquisition and the requirement for detailed, expert-driven labeling often result in outliers and potential mislabeling within manually labeled datasets. These issues can negatively affect the training of neural networks, necessitating algorithms that handle outliers or mislabeled data effectively. We introduce the simultaneous picking and refinement (SPR) algorithm, designed to handle datasets plagued by outlier samples or even noisy labels. Unlike conventional approaches that regard manual picks as ground truth, our method treats the true first-break as a latent variable within a probabilistic model that includes a first-break labeling prior. SPR aims to uncover this variable, enabling dynamic adjustments and improved accuracy across the dataset. This strategy mitigates the impact of outliers or inaccuracies in manual labels. Intra-site picking experiments and cross-site generalization experiments on publicly available data confirm our method's performance in identifying first-break and its generalization across different sites. Additionally, our investigations into noisy signals and labels underscore SPR's resilience to both types of noise and its capability to refine misaligned manual annotations. Moreover, the flexibility of SPR, not being limited to any single network architecture, enhances its adaptability across various deep learning-based picking methods. Focusing on learning from data that may contain outliers or partial inaccuracies, SPR provides a robust solution to some of the principal obstacles in automatic first-break picking.