IPLab LLC is a software development company, resident of Skolkovo Innovation Center in Moscow, Russia, focusing on development of software products for prediction of oil and gas formations productivity parameters.
IPLab software is based on:
- Deep neural networks based on innovative methods of hybrid training (genetic algorithms and gradient methods).
- Seismic inversion applying full, angle and azimuth stacks.
- Fracture analysis based on seismic data set.
We use modern innovative machine learning algorithms for data processing and interpretation of complex data of different scale and with different accuracy (well test, seismic, ground studies, aerospace data). Development of technologies based on these algorithms involves the use of large amounts of input data in order to build reliable forecasts reservoir productivity for conventional and unconventional hydrocarbon deposits.
As the basic algorithm for production prediction, neural network with hybrid training approch is used. It will provide a high degree of freedom nonlinear prediction operator. Training of neural networks and their stabilization is based on a combination of genetic algorithms, gradient methods and regularization.
In addition, we applied our ideas on seismic inversion based on 'direct' inversion constructions in the frequency domain for full, angular and azimuthal stacks.
In order to detect the fracture zones and hidden faults on the 3D seismic data we make use of innovative artificial intelligence algorithms.