Massive-scale unlabelled field and labelled synthetic seismic data sets of global shelf-edge clinothems

SUMMARY Seismic stratigraphic interpretation of shelf-edge clinothems is essential for revealing tectonic evolution, paleoclimate change, depositional dynamic conditions and hydrocarbon generation and accumulation during basin filling. However, traditional interpretation methods remain labour-intensive, time-consuming and highly subjective. Although AI-based method offer a potential solution for automating this task, its development has been limited by the scarcity of comprehensive and representative benchmark data sets for shelf-edge clinothems. This limitation primarily arises from limited field data availability, the scarcity of reliable geological labels and the structural complexity and strong variability of clinothem-dominated systems. To address this gap, we develop a hybrid benchmark data set through two complementary strategies of field data curation and geological and geophysical forward modelling, ultimately generating 3000 unlabelled field and 4000 labelled synthetic seismic data, respectively. We further evaluate several representative baseline deep learning models on these data sets, and the accurate results demonstrate that the curated data set provides an effective and representative basis for model training, quantitative assessment and practical application. Finally, we have publicly released this hybrid benchmark data set (https://doi.org/10.5281/zenodo.20769762) to facilitate the development, validation and assessment of deep learning methods for automated seismic stratigraphic interpretation.