LTrace partner with industry leaders for offering our solutions as plugins for Petrel and OpendTect using the latest NVIDIA GPU Technologies.
Bayesian Linear Inversion (BLI)
LTrace Bayesian Linear Inversion provides a deterministic elastic seismic inversion using the linearized Bayesian methodology for estimating velocities or impedances and density. We use angle stacked seismic data – such as near, mid and far – along with low frequency models to quickly perform the inversion. The results are comparable to a constrained sparse spike inversion but are obtained 6x to 10x faster. The software implements an approximation on the horizontal continuity model, allowing the user to impose lateral correlation on the results with a low overhead.
A suggested workflow is to perform quality control (QC) comparing the inversion results with well log data. The QC implementation enables the user to change the parameters and quickly run the inversion on a limited area, automatically updating the QC window with the new results. After defining the optimal parameters, the user can perform the inversion on the full volume.
The software uses the latest Graphics Processing Unit (GPU) technologies to accelerate the inversion processing. If the user has an NVIDIA® GPU, the inversion will be automatically processed using it. Using GPUs provides a performance gain over CPUs of 4 to 7 times in our benchmarks, depending on the model of the GPU and the vertical gate selected at the inversion.
- Deterministic elastic inversion for estimating Velocities or Impedances and Density.
- Runs 6x to 10x faster than a Constrained Sparse Spike inversion.
- Horizontal correlation.
- Quality Control (QC) for comparing the inversion results with well log data and iterative parameters adjustment.
- Accelerated by CUDA on NVIDIA® GPUs.
LTrace Geophysical Solutions is part of the NVIDIA Inception Program for exceptional technology startups who are revolutionizing their industries with advances in artificial intelligence (AI) and data science.
LTrace uses NVIDIA GPUs in seismic inversion and deep learning methods for characterization of the reservoir with quality, better performance and interactivity. We have also developed techniques that use deep learning for Digital Rock Analysis to predict pretophysical properties and lithofacies from CT and micro-CT rock data.
NVIDIA has been instrumental in the resurgence of neural networks in machine learning over the last several years. The rise of GPU-accelerated neural network training has allowed for major advances in the field of deep learning and NVIDIA’s GPU lines, Deep Learning SDK, and investment in AI startups have all undoubtedly played an immense role in that.
More about NVIDIA Inception Program at: