Researchers have applied a deep neural network (DNN) to significantly improve seismic interference attenuation in a large-scale marine seismic survey in Angola's Camie Field. This DNN-based workflow, trained using a supervised learning framework with manually generated training data, demonstrated superior accuracy in removing seismic interference compared to conventional geophysical algorithms. The project, covering over 345 km², highlighted the DNN's effectiveness in achieving higher SI removal accuracy with less signal leakage and more complete noise elimination, suggesting potential for deep learning in other seismic denoising applications. AI
IMPACT Demonstrates the practical application of deep learning for complex data processing challenges, potentially improving efficiency and accuracy in geoscience.
RANK_REASON The item is a research paper detailing the application of a deep learning model to a specific scientific problem. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Daily Papers →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
