Dec 6, 2021
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Speaker · 0 followers
Traditional seismic inversion (SI) maps the hundreds of terabytes of raw-field data to subsurface properties in gigabytes. This inversion process is expensive, requiring over a year of human and computational effort. Recently, data-driven approaches equipped with Deep learning (DL) are envisioned to improve the efficiency of SI. However, these improvements are restricted to data with highly reduced scale and complexity. To the best of our knowledge, this is the first successful demonstration of DL approach on SI for real, large-scale and complicated raw field data. We solve the scalability of SI by proposing a new auxiliary learning paradigm for SI (Aux-SI). In this paradigm, we break the SI into local inversion tasks, which predicts each small chunk of subsurface properties using surrounding seismic data. Aux-SI combines these local predictions to obtain the entire subsurface model. However, even this local inversion is challenging due to: (1) high-dimensional, spatially irregular multi-modal seismic data, (2) there is no concrete spatial mapping (or alignment) between subsurface properties and raw data. To handle these challenges, we propose an all-MLP architecture, "Multi-modal Information Unscrambler (MMI-Unscrambler), that unscrambles seismic information by ingesting all available multi-modal data. In the experiment, we show that MMI-Unscrambler outperforms both SOTA U-Net and Transformer models on simulation data. We also scale MMI-Unscrambler to raw-field nav-merge data on Gulf-of-Mexico to obtain a geologically sound velocity model with an SSIM score of 0.8.Traditional seismic inversion (SI) maps the hundreds of terabytes of raw-field data to subsurface properties in gigabytes. This inversion process is expensive, requiring over a year of human and computational effort. Recently, data-driven approaches equipped with Deep learning (DL) are envisioned to improve the efficiency of SI. However, these improvements are restricted to data with highly reduced scale and complexity. To the best of our knowledge, this is the first successful demonstration of…
Account · 1.9k followers
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Hugo Soulat, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Eric Hambro, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Zijian Kang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Amir Hertz, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%