{"id":19315902,"url":"https://github.com/liweitianux/paper-eor-detection","last_synced_at":"2026-02-27T10:41:56.813Z","repository":{"id":74978391,"uuid":"187335595","full_name":"liweitianux/paper-eor-detection","owner":"liweitianux","description":"[MNRAS] Separating the EoR Signal with a Convolutional Denoising Autoencoder: A Deep-learning-based Method","archived":false,"fork":false,"pushed_at":"2019-05-18T08:52:00.000Z","size":3500,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-11-06T18:02:56.880Z","etag":null,"topics":["autoencoder","deep-learning","eor-detection","mnras","paper","phd"],"latest_commit_sha":null,"homepage":null,"language":"TeX","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/liweitianux.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2019-05-18T08:51:24.000Z","updated_at":"2020-06-15T07:56:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"601e97d0-2e2c-4e44-99df-b69eb4e13b56","html_url":"https://github.com/liweitianux/paper-eor-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/liweitianux/paper-eor-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/liweitianux%2Fpaper-eor-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/liweitianux%2Fpaper-eor-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/liweitianux%2Fpaper-eor-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/liweitianux%2Fpaper-eor-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/liweitianux","download_url":"https://codeload.github.com/liweitianux/paper-eor-detection/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/liweitianux%2Fpaper-eor-detection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29892055,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-27T09:48:51.284Z","status":"ssl_error","status_checked_at":"2026-02-27T09:48:43.992Z","response_time":57,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["autoencoder","deep-learning","eor-detection","mnras","paper","phd"],"created_at":"2024-11-10T01:08:53.609Z","updated_at":"2026-02-27T10:41:56.767Z","avatar_url":"https://github.com/liweitianux.png","language":"TeX","funding_links":[],"categories":[],"sub_categories":[],"readme":"MNRAS Paper\n-----------\n\n**Title**:\nSeparating the EoR Signal with a Convolutional Denoising Autoencoder:\nA Deep-learning-based Method\n\n**Authors**:\nWeitian Li,\nHaiguang Xu,\nZhixian Ma,\nRuimin Zhu,\nDan Hu,\nZhenghao Zhu,\nJunhua Gu,\nChenxi Shan,\nJie Zhu,\nXiang-Ping Wu\n\n**Journal**:\n[MNRAS, 2019, 485, 2628](https://dx.doi.org/10.1093/mnras/stz582)\n\n**arXiv**:\n[1902.09278](https://arxiv.org/abs/1902.09278)\n\n**ADS**:\n[2019MNRAS.485.2628L](http://adsabs.harvard.edu/abs/2019MNRAS.485.2628L)\n\n**Code**:\nhttps://github.com/liweitianux/cdae-eor\n\n**Abstract**:\nWhen applying the foreground removal methods to uncover the faint cosmological\nsignal from the epoch of reionization (EoR), the foreground spectra are assumed\nto be smooth.\nHowever, this assumption can be seriously violated in practice since the\nunresolved or mis-subtracted foreground sources, which are further complicated\nby the frequency-dependent beam effects of interferometers, will generate\nsignificant fluctuations along the frequency dimension.\nTo address this issue, we propose a novel deep-learning-based method that uses\na 9-layer convolutional denoising autoencoder (CDAE) to separate the EoR\nsignal.\nAfter being trained on the SKA images simulated with realistic beam effects,\nthe CDAE achieves excellent performance as the mean correlation coefficient (ρ̄)\nbetween the reconstructed and input EoR signals reaches 0.929 ± 0.045.\nIn comparison, the two representative traditional methods, namely the\npolynomial fitting method and the continuous wavelet transform method, both\nhave outstanding difficulties in uncovering the EoR signal, yielding only\nρ̄[poly] = 0.296 ± 0.121 and ρ̄[cwt] = 0.198 ± 0.160, respectively.\nWe conclude that, by hierarchically learning sophisticated features through\nmultiple convolutional layers, the CDAE is a powerful tool that can be used to\novercome the complicated frequency-dependent beam effects and accurately\nseparate the EoR signal, which exhibits the great potential of\ndeep-learning-based methods in future EoR experiments.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliweitianux%2Fpaper-eor-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fliweitianux%2Fpaper-eor-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliweitianux%2Fpaper-eor-detection/lists"}