# The NCS-Model: A seismic foundation model trained on the Norwegian repository of public data

Source: [The NCS-Model: A seismic foundation model trained on the Norwegian repository of public data](<https://www.sota2.com/research/paper/69c36c4e0636e5bf4afc6797>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-28T05:00:12.409Z

Authors: Alba Ordonez, Theodor Johannes Line Forgaard, David Wade, Aina Juell Bugge, Hakon Nese, Anders Ueland Waldeland

Published: 2026-03-24T13:54:12.000Z

## Abstract

We present the NCS-models, a family of seismic foundation models pretrained on a large share of full-stack seismic cubes from the Norwegian Continental Shelf (NCS) available through the public DISKOS database. The model weights are open-sourced for the wider geoscience community. Foundation models trained with large-scale self-supervision are emerging as a promising basis for automatic seismic interpretation. However, most existing seismic models rely on limited or proprietary datasets, and it remains unclear how well natural-image foundation models transfer to seismic data. Our goals are to develop basin-scale seismic foundation models, provide practical recipes for scalable 3D training, and quantify the effects of basin-targeted pretraining and token dimensionality on downstream interpretation performance. Using masked autoencoders with Vision Transformer backbones, we pretrain models on a DISKOS-derived corpus of 3D time- and depth-migrated seismic volumes. The NCS-model variants use 2D, 2.5D multi-view, and 3D tokenization within a matched training setup. Transfer is evaluated on interpretation benchmarks using frozen backbones and a simple k-nearest neighbor classifier. Baselines include an ImageNet-pretrained MAE, a frontier vision foundation model, and a globally pretrained seismic model. Natural-image pretrained models do not reliably transfer, reflecting the large domain gap between natural images and seismic data. Seismic pretraining is necessary for robust transfer, and large-scale basin-targeted pretraining yields further gains over a smaller globally pretrained seismic baseline. The NCS-models achieve the best overall performance without fine-tuning, while 2.5D tokenization offers the strongest accuracy-efficiency tradeoff and the embeddings support similarity search for interactive interpretation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.23211>)

[PDF](<https://arxiv.org/pdf/2603.23211.pdf>)
