Schlumberger Technology Corporation

Services Petroliers Schlumberger

Geoquest Systems B.v.

Haibin Di

Aria Abubakar

Hiren Maniar

Cen Li

Nicolae Moldoveanu

Xiaoli Chen

Leigh Truelove

Zhun Li

Sunil Manikani

Wenyi Hu

Stewart Smith

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.

Ground roll attenuation using unsupervised deep learning

A method includes receiving a seismic survey that includes a plurality of seismic slices. The method also includes converting the seismic slices into an embedding. The embedding includes one or more vectors. Each of the vectors includes more than 3 dimensions. The method also includes generating a plot based at least partially upon the embedding.

Quantifying diversity in seismic datasets

Systems, computer-readable media, and methods are provided. Blended baseline data is generated by numerically blending unblended baseline data according to a simultaneous shooting schedule scheme. Pseudo-deblended baseline seismic data is generated by applying a pseudo-deblending procedure to the blended baseline data. Machine learning labels are generated from common gathers of the pseudo-deblended baseline data and the unblended baseline data. A neural network is trained using the labels, the common gathers of the pseudo-deblended baseline data, and the unblended baseline data to produce common gathers of deblended baseline seismic data from the common gathers of the pseudo-deblended baseline seismic data.

Simultaneous shooting time-lapse seismic data deblending for CO2 monitoring and time lapse simultaneous shooting scheme recommender

A method for seismic processing includes extracting, using a first machine learning model, one or more seismic features from seismic data representing a subsurface domain, receiving one or more well logs representing one or more subsurface properties in the subsurface domain, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain at a location that does not correspond to an existing well based on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data.

Subsurface property estimation in a seismic survey area with sparse well logs

A computer-implemented method includes receiving a test seismic dataset associated with a known truth interpretation, receiving one or more hard constraints, training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints, determining an error value based on the training the machine learning system, adjusting the error value based on one or more soft constraints, updating the training of the machine learning system based on the adjusted error value, receiving a second seismic dataset after the updating the training; applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset, generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset, and outputting the seismic image.

Growing community of inventors

Houston, TX, United States of America

Haibin Di