{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "ai-oct-fourcastnet-family",
    "title": "FourCastNet high-resolution weather forecasting and distributed training",
    "summary": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead.",
    "boundary": "Two 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.",
    "area": "AI weather forecasting",
    "topic": "Artificial intelligence",
    "year": 2022,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "ai-oct-fourcastnet-family",
    "target": {
      "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
      "version": 1,
      "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
    },
    "humans": [
      "Jaideep Pathak",
      "Shashank Subramanian",
      "Peter Harrington",
      "Sanjeev Raja",
      "Ashesh Chattopadhyay",
      "Morteza Mardani",
      "Thorsten Kurth",
      "David Hall",
      "Zongyi Li",
      "Kamyar Azizzadenesheli",
      "Pedram Hassanzadeh",
      "Karthik Kashinath",
      "Animashree Anandkumar",
      "Andrea Miele"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "src-ai-oct-2202-11214v1-primary",
        "title": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
        "url": "https://arxiv.org/pdf/2202.11214v1"
      },
      {
        "id": "src-ai-oct-2208-05419v1-primary",
        "title": "FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators",
        "url": "https://arxiv.org/pdf/2208.05419v1"
      }
    ],
    "points": "155000",
    "published_grade": {
      "id": "ai-oct-fourcastnet-family",
      "entry_id": "ai-oct-fourcastnet-family",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
        "version": 1,
        "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
      },
      "what_changed": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead.",
      "scope": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead. Two 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
        "version": 1,
        "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-16T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Jaideep Pathak",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Shashank Subramanian",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Peter Harrington",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sanjeev Raja",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ashesh Chattopadhyay",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Morteza Mardani",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thorsten Kurth",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "David Hall",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zongyi Li",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Kamyar Azizzadenesheli",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Pedram Hassanzadeh",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Karthik Kashinath",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Animashree Anandkumar",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Andrea Miele",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2208.05419v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2202.11214v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators",
            "url": "https://arxiv.org/pdf/2208.05419v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Two 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.",
        "domain": "AI weather forecasting"
      },
      "sources": [
        {
          "citation": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
          "url": "https://arxiv.org/pdf/2202.11214v1"
        },
        {
          "citation": "FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators",
          "url": "https://arxiv.org/pdf/2208.05419v1"
        }
      ],
      "statement": "# FourCastNet high-resolution weather forecasting and distributed training\n\nApplies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead.\n\n## Scientific scope\n\nTwo 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nJaideep Pathak; Shashank Subramanian; Peter Harrington; Sanjeev Raja; Ashesh Chattopadhyay; Morteza Mardani; Thorsten Kurth; David Hall; Zongyi Li; Kamyar Azizzadenesheli; Pedram Hassanzadeh; Karthik Kashinath; Animashree Anandkumar; Andrea Miele\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://arxiv.org/pdf/2202.11214v1)\n- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://arxiv.org/pdf/2208.05419v1)\n",
      "summary": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead.",
      "title": "FourCastNet high-resolution weather forecasting and distributed training"
    },
    "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
      "version": 1,
      "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:8b45e53b63c657fffa26ba420beb54ae20db753fdfe5d5edc35c46890eb3cec7"
  },
  "target": {
    "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
    "version": 1,
    "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "ai-oct-fourcastnet-family",
    "entry_id": "ai-oct-fourcastnet-family",
    "revision": 1,
    "title": "FourCastNet high-resolution weather forecasting and distributed training",
    "context": "AI weather forecasting",
    "track": "Human-designed research method or resource",
    "band": "A",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-16",
    "evidence_cutoff": "2026-10-16",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead.",
    "scope": "Applies AFNO to autoregressive high-resolution global weather fields and develops feature/data-parallel GPU training with optimized spectral operations, I/O and launch overhead. Two 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.",
    "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Two 2022 sources bundled with separate 13/9-person bylines; SC account shares contribution among Subramanian/Harrington/Pathak, not automatically first author. Forecast speed is inference-only on specific hardware/variables; ERA5 reanalysis/training cost and fewer vertical variables matter. Distributed timings include exposed I/O/validation but exclude setup/warm-up/capture and extrapolate some 80-epoch costs from five epochs. No general climate or exact physical-simulation certificate.",
    "references": [
      {
        "title": "FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators",
        "url": "https://arxiv.org/pdf/2202.11214v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      },
      {
        "title": "FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators",
        "url": "https://arxiv.org/pdf/2208.05419v1",
        "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification."
      }
    ],
    "roles": [
      {
        "who": "Source-listed authors and technical contributors",
        "credit": "SCIENCE",
        "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities."
      }
    ],
    "target": {
      "record_id": "urn:uuid:befd9005-314c-4b08-a85f-c07c9fa7688b",
      "version": 1,
      "content_hash": "sha256:98d7b6be8cc51ff2b821a5c64f46f662478b4ae4e698842551f0e75c277a7ea1"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "155000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}