Software

See the table below for our open-source software offerings.

For the most current listing of NLR-developed open-source software, see U.S. Department of Energy Office of Scientific and Technical Information's DOE CODE database.

Commercial Licensing

Explore more than 250 copyrighted software tools available for licensing via the Department of Energy's Lab Partnering Service.

GANISP: GAN-assisted Importance Splitting

Nov 14, 2021, 17:00 PM

Genealogical importance splitting marches toward a rare event by iteratively selecting and replicating realizations that are headed toward a rare event. The replication step is made difficult when applied to deterministic systems as the initial conditions of the offspring realizations need to be adjusted. Typically, a random perturbation is applied to the offspring. For some cases, this cloning technique may not be adequate and prevent variance reduction in the probability estimate. A GAN-based replication process is proposed to address this limitation. The perturbations applied to the clones are physically consistent instead of being randomly chosen. The proposed method allows reducing the variance in the probability estimation.

Title : GANISP: GAN-assisted Importance Splitting

Url : https://github.com/NREL/GANISP

Software Id : 67088

Categories :

Computational Science
Python
Software Categories