---
code_id: 147675
site_ownership_code: "NREL"
open_source: true
repository_link: "https://github.com/NREL/SysCaps"
project_type: "OS"
software_type: "S"
official_use_only: {}
developers:
- email: ""
  orcid: ""
  first_name: "Patrick"
  last_name: "Emami"
  middle_name: ""
  affiliations:
  - "National Renewable Energy Laboratory (NREL), Golden, CO (United States)"
- email: ""
  orcid: ""
  first_name: "Saumya"
  last_name: "Sinha"
  middle_name: ""
  affiliations:
  - "National Renewable Energy Laboratory (NREL), Golden, CO (United States)"
- email: ""
  orcid: ""
  first_name: "Truc"
  last_name: "Nguyen"
  middle_name: ""
  affiliations:
  - "National Renewable Energy Laboratory (NREL), Golden, CO (United States)"
- email: ""
  orcid: ""
  first_name: "Zhaonan"
  last_name: "Li"
  middle_name: ""
  affiliations:
  - "National Renewable Energy Laboratory (NREL), Golden, CO (United States)"
contributors: []
sponsoring_organizations:
- organization_name: "USDOE Laboratory Directed Research and Development (LDRD) Program"
  funding_identifiers: []
  primary_award: "AC36-08GO28308"
  DOE: true
contributing_organizations: []
research_organizations:
- organization_name: "National Renewable Energy Laboratory (NREL), Golden, CO (United\
    \ States)"
  DOE: true
related_identifiers: []
award_dois: []
release_date: "2024-07-31"
software_title: "SysCaps (Language Interfaces for Simulation Surrogates of Complex\
  \ Systems) [SWR-24-97]"
acronym: "SysCaps"
doi: "https://doi.org/10.11578/dc.20241118.2"
description: "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.\n\nPaper: https://arxiv.org/abs/2405.19653"
programming_languages:
- "Python"
- "Jupyter Notebook"
- "Shell"
documentation_url: "https://arxiv.org/abs/2405.19653"
country_of_origin: "United States"
project_keywords: []
licenses:
- "BSD 3-clause \"New\" or \"Revised\" License"
recipient_org: "NREL Technology Transfer Office"
site_accession_number: "NREL SWR-24-97"
date_record_added: "2024-11-18"
date_record_updated: "2024-11-18"
is_file_certified: false
last_editor: "angela.hupp@nrel.gov"
is_limited: false
links:
- rel: "citation"
  href: "https://www.osti.gov/doecode/biblio/147675"