GROUND ROLL ATTENUATION USING UNSUPERVISED DEEP LEARNING

• Main Authors: MOLDOVEANU, Nicolae, MANIAR, Hiren, DI, Haibin, ABUBAKAR, Aria
• Format: Patent
• Language: English; French; German
• Published: 20.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; DETECTING MASSES OR OBJECTS; EARTH DRILLING; EARTH DRILLING, e.g. DEEP DRILLING; FIXED CONSTRUCTIONS; GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; MEASURING; MINING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR ASLURRY OF MINERALS FROM WELLS; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING

A machine-implemented method, at least one non-transitory computer-readable medium storing instructions, and a computing system are provided for attenuating noise. A computing system receives a seismic image and generates a first image using a first neural network configured to identify low-frequency ground roll in a seismic image, and a second image using a second neural network configured to identify reflections in the seismic image. A combined image is generated by combining the first image and the second image. The first neural network and the second neural network are adjusted to reduce a difference between the combined image and the seismic image using frequency constraint to guide separation of the seismic image into the first image and the second image.