SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing

Abstract

Exploration seismic processing underpins subsurface imaging and resource exploration, but learning-based methods remain difficult to compare across studies. Our survey of 368 papers finds widespread reliance on private or difficult-to-reproduce datasets, with only 25 providing public code. This obscures whether reported gains arise from model design or experimental settings. We introduce the Seismic Processing Benchmark (SPBench), covering six tasks: random noise attenuation, trace interpolation, ground-roll suppression, multiple suppression, deblending, and first-arrival picking. We reproduce 24 supervised methods on 10 datasets under 43 standardized settings and release datasets, implementations, configurations, evaluation scripts, and results. To complement global scores and per-trace pick errors, we introduce signal-component-resolved evaluation (SCoRE) for reconstruction and a reference-free ridge-curvature score (RC_norm) for first-arrival picking. Our analyses show that synthetic rankings do not reliably predict field rankings, with task-dependent agreement when models train within each setting. As degradation strengthens, rankings reorder more under coherent ground roll than under random-like interference. The ridge score agrees with MAE-based model rankings in the evaluated settings, with a mean Kendall correlation of 0.881 across three field surveys, while SCoRE reveals frequency- and energy-dependent differences hidden by global scores. SPBench provides a reproducible basis for comparing learning-based seismic processing methods and characterizes how their relative advantages vary across data settings, degradation strengths, and evaluation criteria.