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.
Related
- A general lightweight global modeling framework for three-dimensional seismic exploration
- GeoAgent: Contract-Constrained LLM Agents for Seismic Data Processing
- A cloud-native framework for seismic waveform data quality assessment: Performance evaluation under equivalent resource constraints
- Impact of proposed wind turbines on seismic monitoring stations at the Xiaolangdi Reservoir
- Seismic imaging of the crust and upper mantle beneath Taiwan using full-waveform inversion of teleseismic body waves
BibTeX
@misc{liu2026spbench,
title = {{SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing}},
author = {Qi Liu and Tianxiang Gao and Zhitong Cheng and Chen Zhang and Peng Hu and Wei Gao and Jianwei Ma},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.28925},
eprint = {2609.28925},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.28925},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing
AU - Qi Liu
AU - Tianxiang Gao
AU - Zhitong Cheng
AU - Chen Zhang
AU - Peng Hu
AU - Wei Gao
AU - Jianwei Ma
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.28925
UR - https://arxiv.org/abs/2609.28925
AB - 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.
ER -