Abstract
You've found the official code repository for the paper "SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems," presented at the Foundation Models for Science: Progress, Opportunities, and Challenges workshop at NeurIPS 2024. Our paper conjectures that interfaces (both text templates as well as conversational) makes interacting with simulation surrogate models for complex systems more intuitive and accessible for both non-experts and experts. "System captions", or SysCaps, are text-based descriptions of systems based on information contained in simulation metadata. Our paper's goal is to train multimodal regression models that take text inputs (SysCaps) and timeseries inputs (exogenous system conditions such as hourly weather) and regress timeseries simulation outputs (e.g. hourly building energy consumption). The experiments in our paper with building and wind farm simulators, which can be reproduced using this codebase, aim to help us understand whether a) accurate regression in this setting is possible and b) if so, how well can we do it.
Paper: https://arxiv.org/abs/2405.19653
- Developers:
-
Emami, Patrick [1] ; Sinha, Saumya [1] ; Nguyen, Truc [1] ; Li, Zhaonan [1]
- National Renewable Energy Laboratory (NREL), Golden, CO (United States)
- Release Date:
- 2024-07-31
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Programming Languages:
-
Python
Jupyter Notebook
Shell
- Licenses:
-
BSD 3-clause "New" or "Revised" License
- Sponsoring Org.:
-
USDOE Laboratory Directed Research and Development (LDRD) ProgramPrimary Award/Contract Number:AC36-08GO28308
- Code ID:
- 147675
- Site Accession Number:
- NREL SWR-24-97
- Research Org.:
- National Renewable Energy Laboratory (NREL), Golden, CO (United States)
- Country of Origin:
- United States
Citation Formats
Emami, Patrick, Sinha, Saumya, Nguyen, Truc, and Li, Zhaonan.
SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97].
Computer Software.
https://github.com/NREL/SysCaps.
USDOE Laboratory Directed Research and Development (LDRD) Program.
31 Jul. 2024.
Web.
doi:10.11578/dc.20241118.2.
Emami, Patrick, Sinha, Saumya, Nguyen, Truc, & Li, Zhaonan.
(2024, July 31).
SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97].
[Computer software].
https://github.com/NREL/SysCaps.
https://doi.org/10.11578/dc.20241118.2.
Emami, Patrick, Sinha, Saumya, Nguyen, Truc, and Li, Zhaonan.
"SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97]." Computer software.
July 31, 2024.
https://github.com/NREL/SysCaps.
https://doi.org/10.11578/dc.20241118.2.
@misc{
doecode_147675,
title = {SysCaps (Language Interfaces for Simulation Surrogates of Complex Systems) [SWR-24-97]},
author = {Emami, Patrick and Sinha, Saumya and Nguyen, Truc and Li, Zhaonan},
abstractNote = {You've found the official code repository for the paper "SysCaps: Language Interfaces for Simulation Surrogates of Complex Systems," presented at the Foundation Models for Science: Progress, Opportunities, and Challenges workshop at NeurIPS 2024. Our paper conjectures that interfaces (both text templates as well as conversational) makes interacting with simulation surrogate models for complex systems more intuitive and accessible for both non-experts and experts. "System captions", or SysCaps, are text-based descriptions of systems based on information contained in simulation metadata. Our paper's goal is to train multimodal regression models that take text inputs (SysCaps) and timeseries inputs (exogenous system conditions such as hourly weather) and regress timeseries simulation outputs (e.g. hourly building energy consumption). The experiments in our paper with building and wind farm simulators, which can be reproduced using this codebase, aim to help us understand whether a) accurate regression in this setting is possible and b) if so, how well can we do it.
Paper: https://arxiv.org/abs/2405.19653},
doi = {10.11578/dc.20241118.2},
url = {https://doi.org/10.11578/dc.20241118.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20241118.2}},
year = {2024},
month = {jul}
}