{"id":23500445,"url":"https://github.com/gully/blase","last_synced_at":"2025-07-29T16:42:39.632Z","repository":{"id":37806336,"uuid":"314040627","full_name":"gully/blase","owner":"gully","description":"Interpretable Machine Learning for astronomical spectroscopy in PyTorch and JAX","archived":false,"fork":false,"pushed_at":"2025-05-13T16:51:14.000Z","size":77889,"stargazers_count":27,"open_issues_count":17,"forks_count":8,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-05-13T17:57:21.943Z","etag":null,"topics":["astronomy","interpretable-machine-learning","machine-learning","spectroscopy"],"latest_commit_sha":null,"homepage":"https://blase.readthedocs.io","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gully.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2020-11-18T19:45:00.000Z","updated_at":"2025-05-13T16:51:31.000Z","dependencies_parsed_at":"2025-04-15T18:53:23.956Z","dependency_job_id":null,"html_url":"https://github.com/gully/blase","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/gully/blase","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2Fblase","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2Fblase/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2Fblase/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2Fblase/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gully","download_url":"https://codeload.github.com/gully/blase/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2Fblase/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267718782,"owners_count":24133464,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-29T02:00:12.549Z","response_time":2574,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["astronomy","interpretable-machine-learning","machine-learning","spectroscopy"],"created_at":"2024-12-25T06:44:20.101Z","updated_at":"2025-07-29T16:42:39.593Z","avatar_url":"https://github.com/gully.png","language":"Jupyter Notebook","readme":"# blasé\n\nInterpretable Machine Learning for high-resolution astronomical spectroscopy.\n\n\u003ca href=\"https://blase.readthedocs.io/en/latest/\"\u003e\u003cimg src=\"https://img.shields.io/badge/Read-the%20docs-blue\"\u003e\u003c/a\u003e\n\u003ca href=\"https://ui.adsabs.harvard.edu/abs/2022ApJ...941..200G/abstract\"\u003e\u003cimg src=\"https://img.shields.io/badge/Paper-Gully--Santiago \u0026 Morley (2022)-green\"\u003e\u003c/a\u003e\n\n## _Handles stellar and telluric lines simultaneously_\n\nWe can combine stellar, [telluric](https://en.wikipedia.org/wiki/Telluric_contamination), and instrumental models into a unified forward model of your entire high-bandwidth, high-resolution spectrum. We can obtain best-in-class models of Earth's atmosphere, line-by-line, automatically, for free (or cheap).\n\n## _Massively scalable_\n\nBy using autodiff, we can fit over 10,000 spectral lines simultaneously. This enormous amount of flexibility is unavailable in conventional frameworks that do not have [autodiff](https://en.wikipedia.org/wiki/Automatic_differentiation).  \n![optimize lines](https://user-images.githubusercontent.com/860227/284969022-bfa7d8ad-889b-49c4-93e1-62f6a61c518f.gif)  \n^ We do this for 10,000 lines simultaneously.\n\n## _Rooted in physics_\n\nWe first clone a precomputed synthetic spectrum, such as PHOENIX, and then **transfer learn** with data. By regularizing to the cloned model, we get the best of both worlds: data driven when the Signal-to-Noise ratio is high, and model-driven when we lack data to say otherwise.\n\n## _Blazing fast with GPUs_\n\nWe achieve $\u003e60 \\times$ speedups with NVIDIA GPUs, so training takes minutes instead of hours.\n\n## Get started\n\nVisit our [step-by-step tutorials](https://blase.readthedocs.io/en/latest/tutorials/index.html) or [installation](https://blase.readthedocs.io/en/latest/install.html) pages to get started. We also have [deep dives](https://blase.readthedocs.io/en/latest/deep_dives/index.html#), or you can [read the paper](https://ui.adsabs.harvard.edu/abs/2022ApJ...941..200G/abstract). Have a question or a research project in mind? Open [an Issue](https://github.com/gully/blase/issues) or [email gully](https://gully.github.io/).\n\nCopyright 2020, 2021, 2022, 2023 The Authors\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgully%2Fblase","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgully%2Fblase","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgully%2Fblase/lists"}