首页|New Findings from University of Oklahoma Describe Advances in Machine Learning ( Uncertainty Assessment in Unsupervised Machine Learning Methods For Deepwater Ch annel Seismic Facies Using Outcrop-derived 3D Models And Synthetic Seismic Data)
New Findings from University of Oklahoma Describe Advances in Machine Learning ( Uncertainty Assessment in Unsupervised Machine Learning Methods For Deepwater Ch annel Seismic Facies Using Outcrop-derived 3D Models And Synthetic Seismic Data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News - A new study on artificial intelligence is now available. According to news originating from Norman, Oklahoma, by NewsR x correspondents, research stated, “Unsupervised machine learning (ML) technique s have been widely applied to analyze seismic reflection data, including the ide ntification of seismic facies and structural features.” The news editors obtained a quote from the research from University of Oklahoma: “However, interpreting the resulting clusters often relies on geoscientists’ ex pertise, necessitating a robustness assessment of these methods. To evaluate the ir reliability, synthetic data generated from an actual outcrop model were emplo yed to demonstrate how two unsupervised methods, Self-Organizing Maps (SOM) and Generative Topographic Maps (GTM), cluster deepwater channel-related seismic fac ies and then measure the associated error. Six seismic attributes, comprising RM S amplitude, instantaneous envelope, peak magnitude, and spectral decomposition frequencies at 20, 40, and 55 Hz, served as input variables. Geobodies were assi gned to each cluster formed, and error in facies clustering was quantified by co mparing the actual 3D model with the facies grouped by machine learning methods on a voxel-by-voxel basis. This allowed for error quantification and the computa tion of metrics such as F1 score and accuracy through correlation matrices. Key findings revealed that (1) GTM and SOM exhibited similar performance, with a clu stering configuration of 81 for GTM slightly outperforming others.”
University of OklahomaNormanOklahomaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMach ine Learning
NETL
NSTL
