{
  "id": 272812,
  "title": "[Paper] Black Hole Gravitational Wave Signals... Using Deep Learning",
  "url": "/competitions/g2net-gravitational-wave-detection/discussion/272812",
  "author_name": "",
  "post_date": "2021-09-17T12:59:50.866137400Z",
  "votes": 32,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Dear all,</p>\n<p>I have noticed that the prestigious journal <em>Physical Review D</em> has just published a paper that may make interesting reading:</p>\n<ul>\n<li><a href=\"https://doi.org/10.1103/PhysRevD.104.064046\" target=\"_blank\">\"<em>Extraction of binary black hole gravitational wave signals from detector data using deep learning</em>\", Phys. Rev. D <strong>104</strong>, 064046</a></li>\n</ul>\n<p>It is behind a paywall, put the pre-print is freely available on arXiv</p>\n<ul>\n<li><a href=\"https://arxiv.org/pdf/2105.03073v3.pdf\" target=\"_blank\">Chayan Chatterjee, Linqing Wen, Foivos Diakogiannis, Kevin Vinsen \"<em>Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning</em>\", arXiv:2105.03073v3\n</a></li>\n</ul>\n<p>where, amongst other details, they provide the architecture of the CNN-LSTM denoising autoencoder model that was used, along with a custom loss function.</p>\n<p>All the best,<br>\ncarl</p>",
  "messages": [
    {
      "id": "1515770",
      "postDate": "09/17/2021 12:59:50",
      "content": "<p>Dear all,</p>\n<p>I have noticed that the prestigious journal <em>Physical Review D</em> has just published a paper that may make interesting reading:</p>\n<ul>\n<li><a href=\"https://doi.org/10.1103/PhysRevD.104.064046\" target=\"_blank\">\"<em>Extraction of binary black hole gravitational wave signals from detector data using deep learning</em>\", Phys. Rev. D <strong>104</strong>, 064046</a></li>\n</ul>\n<p>It is behind a paywall, put the pre-print is freely available on arXiv</p>\n<ul>\n<li><a href=\"https://arxiv.org/pdf/2105.03073v3.pdf\" target=\"_blank\">Chayan Chatterjee, Linqing Wen, Foivos Diakogiannis, Kevin Vinsen \"<em>Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning</em>\", arXiv:2105.03073v3\n</a></li>\n</ul>\n<p>where, amongst other details, they provide the architecture of the CNN-LSTM denoising autoencoder model that was used, along with a custom loss function.</p>\n<p>All the best,<br>\ncarl</p>",
      "rawMarkdown": "Dear all,\n\nI have noticed that the prestigious journal *Physical Review D* has just published a paper that may make interesting reading:\n\n* [\"*Extraction of binary black hole gravitational wave signals from detector data using deep learning*\", Phys. Rev. D **104**, 064046](https://doi.org/10.1103/PhysRevD.104.064046)\n\nIt is behind a paywall, put the pre-print is freely available on arXiv\n\n* [Chayan Chatterjee, Linqing Wen, Foivos Diakogiannis, Kevin Vinsen \"*Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning*\", arXiv:2105.03073v3\n](https://arxiv.org/pdf/2105.03073v3.pdf)\n\nwhere, amongst other details, they provide the architecture of the CNN-LSTM denoising autoencoder model that was used, along with a custom loss function.\n\nAll the best,\ncarl",
      "votes": null
    },
    {
      "id": "1517000",
      "postDate": "09/19/2021 04:48:35",
      "content": "<p>Thank you for sharing!</p>",
      "rawMarkdown": "Thank you for sharing!",
      "votes": null
    },
    {
      "id": "1517475",
      "postDate": "09/19/2021 16:18:10",
      "content": "<p>Thank you for sharing</p>",
      "rawMarkdown": "Thank you for sharing",
      "votes": null
    },
    {
      "id": "1517898",
      "postDate": "09/20/2021 07:17:38",
      "content": "<p>This is really impressive, thanks for the sharing. <br>\nI have a little question regarding the journal, with an impact factor of 5.3, is that a good one in this field? I'm used to biomedical and medicine stuff where the impact factor varies a lot.  </p>",
      "rawMarkdown": "This is really impressive, thanks for the sharing. \nI have a little question regarding the journal, with an impact factor of 5.3, is that a good one in this field? I'm used to biomedical and medicine stuff where the impact factor varies a lot.",
      "votes": null
    },
    {
      "id": "1517912",
      "postDate": "09/20/2021 07:55:16",
      "content": "<p>Dear <a href=\"https://www.kaggle.com/matthirou\" target=\"_blank\">@matthirou</a> </p>\n<p>I no longer work in academia so I  do not have access to the Thomson Reuters Journal Citation Reports, however I would not be at all surprised if all of the subsections of the <em>Physical Review</em> are Q1 in their respective areas.</p>\n<p>That said, focusing on impact factors is not necessarily a good thing; many years ago I added my name to  <a href=\"https://sfdora.org/read/\" target=\"_blank\">The Declaration on Research Assessment (DORA)</a> which \"<em>…recognizes the need to improve the ways in which the outputs of scholarly research are evaluated.</em>\".</p>\n<p>Specifically:</p>\n<blockquote>\n  <p>\"<em>The Journal Impact Factor is frequently used as the primary parameter with which to compare the scientific output of individuals and institutions. The Journal Impact Factor… …was originally created as a tool to help librarians identify journals to purchase, not as a measure of the scientific quality of research in an article.</em>\"</p>\n</blockquote>\n<p>All the best,<br>\ncarl</p>",
      "rawMarkdown": "Dear @matthirou \n\nI no longer work in academia so I  do not have access to the Thomson Reuters Journal Citation Reports, however I would not be at all surprised if all of the subsections of the *Physical Review* are Q1 in their respective areas.\n\nThat said, focusing on impact factors is not necessarily a good thing; many years ago I added my name to  [The Declaration on Research Assessment (DORA)](https://sfdora.org/read/) which \"*...recognizes the need to improve the ways in which the outputs of scholarly research are evaluated.*\".\n\nSpecifically:\n\n> \"*The Journal Impact Factor is frequently used as the primary parameter with which to compare the scientific output of individuals and institutions. The Journal Impact Factor... ...was originally created as a tool to help librarians identify journals to purchase, not as a measure of the scientific quality of research in an article.*\"\n\nAll the best,\ncarl",
      "votes": null
    },
    {
      "id": "1559727",
      "postDate": "10/27/2021 07:09:45",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "rawMarkdown": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1517000,
      "author_name": "yudaiyamaguchi",
      "author_url": "",
      "post_date": "09/19/2021 04:48:35",
      "content": "<p>Thank you for sharing!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1517475,
      "author_name": "womingqiu98",
      "author_url": "",
      "post_date": "09/19/2021 16:18:10",
      "content": "<p>Thank you for sharing</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1517898,
      "author_name": "matthirou",
      "author_url": "",
      "post_date": "09/20/2021 07:17:38",
      "content": "<p>This is really impressive, thanks for the sharing. <br>\nI have a little question regarding the journal, with an impact factor of 5.3, is that a good one in this field? I'm used to biomedical and medicine stuff where the impact factor varies a lot.  </p>",
      "votes": null,
      "replies": [
        {
          "id": 1517912,
          "author_name": "carlmcbrideellis",
          "author_url": "",
          "post_date": "09/20/2021 07:55:16",
          "content": "<p>Dear <a href=\"https://www.kaggle.com/matthirou\" target=\"_blank\">@matthirou</a> </p>\n<p>I no longer work in academia so I  do not have access to the Thomson Reuters Journal Citation Reports, however I would not be at all surprised if all of the subsections of the <em>Physical Review</em> are Q1 in their respective areas.</p>\n<p>That said, focusing on impact factors is not necessarily a good thing; many years ago I added my name to  <a href=\"https://sfdora.org/read/\" target=\"_blank\">The Declaration on Research Assessment (DORA)</a> which \"<em>…recognizes the need to improve the ways in which the outputs of scholarly research are evaluated.</em>\".</p>\n<p>Specifically:</p>\n<blockquote>\n  <p>\"<em>The Journal Impact Factor is frequently used as the primary parameter with which to compare the scientific output of individuals and institutions. The Journal Impact Factor… …was originally created as a tool to help librarians identify journals to purchase, not as a measure of the scientific quality of research in an article.</em>\"</p>\n</blockquote>\n<p>All the best,<br>\ncarl</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 1559727,
      "author_name": "zerafachris",
      "author_url": "",
      "post_date": "10/27/2021 07:09:45",
      "content": "<p>Hey All,</p>\n<p>Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey <a href=\"https://forms.gle/QP9L16niPexozyhu5\" target=\"_blank\">https://forms.gle/QP9L16niPexozyhu5</a>.</p>\n<p>Thank you all,</p>\n<p>Regards,<br>\nChris</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1515770": "Dear all,\n\nI have noticed that the prestigious journal *Physical Review D* has just published a paper that may make interesting reading:\n\n* [\"*Extraction of binary black hole gravitational wave signals from detector data using deep learning*\", Phys. Rev. D **104**, 064046](https://doi.org/10.1103/PhysRevD.104.064046)\n\nIt is behind a paywall, put the pre-print is freely available on arXiv\n\n* [Chayan Chatterjee, Linqing Wen, Foivos Diakogiannis, Kevin Vinsen \"*Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning*\", arXiv:2105.03073v3\n](https://arxiv.org/pdf/2105.03073v3.pdf)\n\nwhere, amongst other details, they provide the architecture of the CNN-LSTM denoising autoencoder model that was used, along with a custom loss function.\n\nAll the best,\ncarl",
    "1517000": "Thank you for sharing!",
    "1517475": "Thank you for sharing",
    "1517898": "This is really impressive, thanks for the sharing. \nI have a little question regarding the journal, with an impact factor of 5.3, is that a good one in this field? I'm used to biomedical and medicine stuff where the impact factor varies a lot.",
    "1517912": "Dear @matthirou \n\nI no longer work in academia so I  do not have access to the Thomson Reuters Journal Citation Reports, however I would not be at all surprised if all of the subsections of the *Physical Review* are Q1 in their respective areas.\n\nThat said, focusing on impact factors is not necessarily a good thing; many years ago I added my name to  [The Declaration on Research Assessment (DORA)](https://sfdora.org/read/) which \"*...recognizes the need to improve the ways in which the outputs of scholarly research are evaluated.*\".\n\nSpecifically:\n\n> \"*The Journal Impact Factor is frequently used as the primary parameter with which to compare the scientific output of individuals and institutions. The Journal Impact Factor... ...was originally created as a tool to help librarians identify journals to purchase, not as a measure of the scientific quality of research in an article.*\"\n\nAll the best,\ncarl",
    "1559727": "Hey All,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris"
  },
  "source": "meta"
}