How can we harness powerful data-driven techniques to compare 4D seismic data and simulation models?
Check the latest result of our Artificial Intelligence Lab. ( Recod.ai ) at the Instituto de Computação – Unicamp Universidade Estadual de Campinas in partnership with the UNISIM / CEPETRO – Centro de Estudos de Petróleo .
We propose a novel approach leveraging three-way deep neural networks trained using a reference image (4D seismic data) with two simulation model candidates. It learns to find the simulation models that best characterize the reference. Our method is underpinned by more than a thousand pairs of simulation models and reference maps evaluated by human specialists for training.
The new method achieves more than 90% accuracy when comparing 4D seismic data with simulation data and represents an important push forward in the Oil & Gas industry.
[Check the paper] https://lnkd.in/g8bxBf5