Abstract
A software package that contains three inverse design blackbox problems to investigate the efficiency and accuracy of inverse design machine learning models. The software contains highly accurate forward machine learning models that can be used to assess the inverse predictions. The package also contains separate test data for each problem. The inverse design problems that are in the package are: airfoil inverse design, scalar boundary reconstruction and photonic surfaces inverse design.
- Developers:
-
Grbcic, Luka [1]
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Release Date:
- 2025-05-15
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Licenses:
-
BSD 3-clause "New" or "Revised" License
- Sponsoring Org.:
-
USDOEPrimary Award/Contract Number:AC02-05CH11231
- Code ID:
- 160805
- Site Accession Number:
- 2025-088
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Country of Origin:
- United States
Citation Formats
Grbcic, Luka.
InverseBench: Inverse design benchmark suite that contains inverse problems from science and engineering (InverseBench) v0.0.1.
Computer Software.
https://github.com/lukagrbcic/InverseBench.
USDOE.
15 May. 2025.
Web.
doi:10.11578/dc.20250814.4.
Grbcic, Luka.
(2025, May 15).
InverseBench: Inverse design benchmark suite that contains inverse problems from science and engineering (InverseBench) v0.0.1.
[Computer software].
https://github.com/lukagrbcic/InverseBench.
https://doi.org/10.11578/dc.20250814.4.
Grbcic, Luka.
"InverseBench: Inverse design benchmark suite that contains inverse problems from science and engineering (InverseBench) v0.0.1." Computer software.
May 15, 2025.
https://github.com/lukagrbcic/InverseBench.
https://doi.org/10.11578/dc.20250814.4.
@misc{
doecode_160805,
title = {InverseBench: Inverse design benchmark suite that contains inverse problems from science and engineering (InverseBench) v0.0.1},
author = {Grbcic, Luka},
abstractNote = {A software package that contains three inverse design blackbox problems to investigate the efficiency and accuracy of inverse design machine learning models. The software contains highly accurate forward machine learning models that can be used to assess the inverse predictions. The package also contains separate test data for each problem. The inverse design problems that are in the package are: airfoil inverse design, scalar boundary reconstruction and photonic surfaces inverse design.},
doi = {10.11578/dc.20250814.4},
url = {https://doi.org/10.11578/dc.20250814.4},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20250814.4}},
year = {2025},
month = {may}
}