Offset gathers and trace index maps support iterative convolution to predict and remove surface-related multiples from seismic data.
Statistical correction of local traveltime operators reconstructs wavefronts and clarifies subsurface structures from sparse seismic data.
Discontinuity and layering data are filtered and analyzed to predict fracture spacing, guide geomodeling, and target drilling.
Full-resolution seismic dips guide decimated horizon surfaces, reducing processing volume while preserving RGT image accuracy.
This case maps surface hazards and artifacts from post-stack seismic cubes, reducing manual QC and avoiding inversion steps.
Training on 5D seismic data enables rapid 3D velocity models for seismic imaging and reservoir interpretation.
A 3D complex wavelet transform and sparse dictionary approximation attenuate coherent noise while improving seismic image quality.
Temporal gating reduces seismic imaging noise and cuts computational demands.
Update synthetic horizons faster by applying stored distance ratios to changed horizons.
Multibeam water-column features, waveform matching, and soft classification improve mapping of mixed deep-sea sediments.
Reconstruct low-frequency seismic data to improve formation images and velocity models.
This case partitions drilling acoustic spectra into energy bands, reducing noise and uncertainty for more precise lithology identification.
A trained model selects seismic reflectors and iteratively refines velocity models to align depth values with well data.
Statistical pilot waveforms train a machine-learning model to denoise seismic data and improve imaging precision and resolution.
Neural networks predict Green's functions to accelerate complex seismic imaging.
A cost and matching matrix guides iterative gradient updates, reducing initial-model precision demands in seismic velocity inversion.
Nonlinear amplitude transforms improve seismic velocity modeling in complex subsurface regions.
Calibrate paleogeographic surfaces with seismic attributes to reduce model uncertainty.
Bayesian neural networks improve seismic fault detection by quantifying uncertainty, helping guide drilling locations and well selection.
Iterative impulse removal cuts ALFT costs while preserving seismic image quality.
This case uses PP-target events and objective-function optimization to estimate PS-receiver statics for accurate seismic imaging.
Clustered seismic data accelerates velocity prediction while preserving imaging detail.
This case merges spectrally shaped FWI and migrated volumes to broaden seismic bandwidth for cleaner reservoir characterization.
This case uses an eikonal solver and travel-time inversion to refine near-surface velocity models for well location.
Automated neural-network analysis of seismic attributes identifies faulted areas and generates polygons faster and more accurately.