{"id":"b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968","title":"Study tests AlphaEarth embeddings for streamflow prediction across basins","argument":"Pengfei Qu and coauthors test whether AlphaEarth Foundations embeddings can help hydrological models predict streamflow in basins without measurement gauges. The authors compare the 64-dimensional embeddings with conventional CAMELS attributes, using in-sample and out-of-sample evaluations on the CAMELS dataset. They report nearly identical in-sample performance, but higher out-of-sample robustness with the embeddings. For prediction in ungauged basins (PUB), the embeddings generally improve performance across target basins. When donor-basin selection is based on similarity, it performs better than random selection with smaller donor pools; that advantage diminishes as the pool grows, and adding basins does not consistently improve performance. The authors also report that benefits in leave-one-cluster-out experiments depend on basin partitioning. Their results make basin representation and donor-pool design central to their account of transfer between regions, while showing that transferability remains sensitive to which catchment conditions are represented during training. The abstract reports evaluations on CAMELS; it does not establish how the results generalize beyond those experiments.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported evaluations use the CAMELS dataset; the abstract does not establish how results generalize beyond those experiments. The abstract reports that benefits depended on basin partitioning but does not specify which partitions or catchment conditions account for that variation.","speaker":{"name":"Qu, Pengfei, Ye, Lei, Ouyang, Wenyu, Zhang, Chi, Chai, Yikai, Xu, Shuolong, Piao, Yongri, Zhang, Miao, Lu, Huchuan","roleAtSource":"Article author"},"source":{"title":"Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2601.01558","publishedAt":"2026-01-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors report higher out-of-sample robustness with AlphaEarth Foundations embeddings than with CAMELS attributes, despite nearly identical in-sample performance.","excerpt":"AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"Across target basins, the authors report that AlphaEarth Foundations static inputs generally improved prediction in ungauged basins.","excerpt":"Across 100 target basins, AEF static inputs generally improved PUB performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"The authors report that similarity-based donor selection’s advantage over random selection diminished as donor-pool size increased, and that adding donor basins did not consistently improve performance.","excerpt":"its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"The authors report that benefits depended on basin partitioning, indicating that transferability remained sensitive to the catchment conditions represented during training.","excerpt":"AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2601.01558","checkedAt":"2026-11-09T12:56:07.361Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the embeddings’ benefits change with the catchment conditions represented during training?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Study tests AlphaEarth embeddings for streamflow prediction across basins","summary":"Pengfei Qu and coauthors test whether AlphaEarth Foundations embeddings can help hydrological models predict streamflow in basins without measurement gauges. The authors compare the 64-dimensional embeddings with conventional CAMELS attributes, using in-sample and out-of-sample evaluations on the CAMELS dataset. They report nearly identical in-sample performance, but higher out-of-sample robustness with the embeddings. For prediction in ungauged basins (PUB), the embeddings generally improve performance across target basins. When donor-basin selection is based on similarity, it performs better than random selection with smaller donor pools; that advantage diminishes as the pool grows, and adding basins does not consistently improve performance. The authors also report that benefits in leave-one-cluster-out experiments depend on basin partitioning. Their results make basin representation and donor-pool design central to their account of transfer between regions, while showing that transferability remains sensitive to which catchment conditions are represented during training. The abstract reports evaluations on CAMELS; it does not establish how the results generalize beyond those experiments.","question":"How do the embeddings’ benefits change with the catchment conditions represented during training?","claims":[{"text":"The authors report higher out-of-sample robustness with AlphaEarth Foundations embeddings than with CAMELS attributes, despite nearly identical in-sample performance.","excerpt":"AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance.","support":"source-stated"},{"text":"Across target basins, the authors report that AlphaEarth Foundations static inputs generally improved prediction in ungauged basins.","excerpt":"Across 100 target basins, AEF static inputs generally improved PUB performance.","support":"source-stated"},{"text":"The authors report that similarity-based donor selection’s advantage over random selection diminished as donor-pool size increased, and that adding donor basins did not consistently improve performance.","excerpt":"its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance.","support":"source-stated"},{"text":"The authors report that benefits depended on basin partitioning, indicating that transferability remained sensitive to the catchment conditions represented during training.","excerpt":"AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training.","support":"source-stated"}],"limitations":["The reported evaluations use the CAMELS dataset; the abstract does not establish how results generalize beyond those experiments.","The abstract reports that benefits depended on basin partitioning but does not specify which partitions or catchment conditions account for that variation."],"mediaId":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","correctionReason":null,"id":"b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968","publicationId":"bd17d898-65a4-4f08-8cb8-f51ba45ce6eb","version":1,"sourceUrl":"https://arxiv.org/abs/2601.01558","sourceTitle":"Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-01-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:43.324Z","createdAt":"2026-11-09T12:40:10.604Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","kind":"article","url":"https://arxiv.org/abs/2601.01558","sourceUrl":"https://arxiv.org/abs/2601.01558","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T12:39:23.919Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2601.01558","checkedAt":"2026-11-09T12:56:07.361Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","confidence":0.72,"provider":"typesafe","model":"jev-1.13.0","inputHash":"3a882e9547a1cbd64354ea85796c4e25fcb13f8dc18a595aaaaad0d89ad8f70a","decidedAt":"2026-11-09T12:39:24.563Z"},"provenance":{"textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observationId":"cbb0c1d65cea5f0a34db3ec436daac70b103a5afa6f09304c81d7feb83cf0392","retrievedAt":"2026-11-09T12:39:23.837Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"d3f3f5af-f430-4ae8-86f6-6d8e2c10b0a8"},"reviewer":{"model":"gpt-6-luna","runId":"2800d062-7fb9-4be9-8c70-5d418d326227"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T12:40:10.604Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Qu, Pengfei","url":null,"kind":"unknown"},{"name":"Ye, Lei","url":null,"kind":"unknown"},{"name":"Ouyang, Wenyu","url":null,"kind":"unknown"},{"name":"Zhang, Chi","url":null,"kind":"unknown"},{"name":"Chai, Yikai","url":null,"kind":"unknown"},{"name":"Xu, Shuolong","url":null,"kind":"unknown"},{"name":"Piao, Yongri","url":null,"kind":"unknown"},{"name":"Zhang, Miao","url":null,"kind":"unknown"},{"name":"Lu, Huchuan","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Qu, Pengfei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Qu, Pengfei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Ye, Lei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ye, Lei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Ouyang, Wenyu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ouyang, Wenyu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Zhang, Chi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Chi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Chai, Yikai","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chai, Yikai","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Xu, Shuolong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Xu, Shuolong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Piao, Yongri","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Piao, Yongri","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Zhang, Miao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Miao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Lu, Huchuan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Lu, Huchuan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}}],"participationCoverage":{"total":9,"returned":9,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2601.01558","snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z","basis":"publisher-page-metadata","sourceLinks":49,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968/source"}},"canonicalUrl":"https://escapemeridian.com/readings/study-tests-alphaearth-embeddings-for-streamflow-prediction-b2e5537c","formats":{"html":"/readings/study-tests-alphaearth-embeddings-for-streamflow-prediction-b2e5537c","markdown":"/readings/study-tests-alphaearth-embeddings-for-streamflow-prediction-b2e5537c.md","json":"/readings/study-tests-alphaearth-embeddings-for-streamflow-prediction-b2e5537c.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-embedding-vector","name":"Embedding vector","explanation":"A list of numbers that represents a piece of text, an image or another item so software can compare meanings.","referenceUrl":"https://developers.google.com/machine-learning/glossary#embedding-vector"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968","revision":"bd17d898-65a4-4f08-8cb8-f51ba45ce6eb","revisionKind":"publication-id","title":"Study tests AlphaEarth embeddings for streamflow prediction across basins","url":"https://escapemeridian.com/readings/study-tests-alphaearth-embeddings-for-streamflow-prediction-b2e5537c"},"source":{"type":"source","id":"https://arxiv.org/abs/2601.01558","revision":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","revisionKind":"sha256-source-text","title":"Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings","url":"https://arxiv.org/abs/2601.01558"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968","title":"Study tests AlphaEarth embeddings for streamflow prediction across basins","argument":"Pengfei Qu and coauthors test whether AlphaEarth Foundations embeddings can help hydrological models predict streamflow in basins without measurement gauges. The authors compare the 64-dimensional embeddings with conventional CAMELS attributes, using in-sample and out-of-sample evaluations on the CAMELS dataset. They report nearly identical in-sample performance, but higher out-of-sample robustness with the embeddings. For prediction in ungauged basins (PUB), the embeddings generally improve performance across target basins. When donor-basin selection is based on similarity, it performs better than random selection with smaller donor pools; that advantage diminishes as the pool grows, and adding basins does not consistently improve performance. The authors also report that benefits in leave-one-cluster-out experiments depend on basin partitioning. Their results make basin representation and donor-pool design central to their account of transfer between regions, while showing that transferability remains sensitive to which catchment conditions are represented during training. The abstract reports evaluations on CAMELS; it does not establish how the results generalize beyond those experiments.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported evaluations use the CAMELS dataset; the abstract does not establish how results generalize beyond those experiments. The abstract reports that benefits depended on basin partitioning but does not specify which partitions or catchment conditions account for that variation.","speaker":{"name":"Qu, Pengfei, Ye, Lei, Ouyang, Wenyu, Zhang, Chi, Chai, Yikai, Xu, Shuolong, Piao, Yongri, Zhang, Miao, Lu, Huchuan","roleAtSource":"Article author"},"source":{"title":"Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2601.01558","publishedAt":"2026-01-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors report higher out-of-sample robustness with AlphaEarth Foundations embeddings than with CAMELS attributes, despite nearly identical in-sample performance.","excerpt":"AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"Across target basins, the authors report that AlphaEarth Foundations static inputs generally improved prediction in ungauged basins.","excerpt":"Across 100 target basins, AEF static inputs generally improved PUB performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"The authors report that similarity-based donor selection’s advantage over random selection diminished as donor-pool size increased, and that adding donor basins did not consistently improve performance.","excerpt":"its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"},{"text":"The authors report that benefits depended on basin partitioning, indicating that transferability remained sensitive to the catchment conditions represented during training.","excerpt":"AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training.","url":"https://arxiv.org/abs/2601.01558","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2601.01558","checkedAt":"2026-11-09T12:56:07.361Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do the embeddings’ benefits change with the catchment conditions represented during training?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Study tests AlphaEarth embeddings for streamflow prediction across basins","summary":"Pengfei Qu and coauthors test whether AlphaEarth Foundations embeddings can help hydrological models predict streamflow in basins without measurement gauges. The authors compare the 64-dimensional embeddings with conventional CAMELS attributes, using in-sample and out-of-sample evaluations on the CAMELS dataset. They report nearly identical in-sample performance, but higher out-of-sample robustness with the embeddings. For prediction in ungauged basins (PUB), the embeddings generally improve performance across target basins. When donor-basin selection is based on similarity, it performs better than random selection with smaller donor pools; that advantage diminishes as the pool grows, and adding basins does not consistently improve performance. The authors also report that benefits in leave-one-cluster-out experiments depend on basin partitioning. Their results make basin representation and donor-pool design central to their account of transfer between regions, while showing that transferability remains sensitive to which catchment conditions are represented during training. The abstract reports evaluations on CAMELS; it does not establish how the results generalize beyond those experiments.","question":"How do the embeddings’ benefits change with the catchment conditions represented during training?","claims":[{"text":"The authors report higher out-of-sample robustness with AlphaEarth Foundations embeddings than with CAMELS attributes, despite nearly identical in-sample performance.","excerpt":"AEF embeddings offer higher OOS robustness than CAMELS attributes, despite nearly identical IS performance.","support":"source-stated"},{"text":"Across target basins, the authors report that AlphaEarth Foundations static inputs generally improved prediction in ungauged basins.","excerpt":"Across 100 target basins, AEF static inputs generally improved PUB performance.","support":"source-stated"},{"text":"The authors report that similarity-based donor selection’s advantage over random selection diminished as donor-pool size increased, and that adding donor basins did not consistently improve performance.","excerpt":"its advantage diminished as pool size increased. Adding more donor basins did not consistently improve performance.","support":"source-stated"},{"text":"The authors report that benefits depended on basin partitioning, indicating that transferability remained sensitive to the catchment conditions represented during training.","excerpt":"AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training.","support":"source-stated"}],"limitations":["The reported evaluations use the CAMELS dataset; the abstract does not establish how results generalize beyond those experiments.","The abstract reports that benefits depended on basin partitioning but does not specify which partitions or catchment conditions account for that variation."],"mediaId":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","correctionReason":null,"id":"b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968","publicationId":"bd17d898-65a4-4f08-8cb8-f51ba45ce6eb","version":1,"sourceUrl":"https://arxiv.org/abs/2601.01558","sourceTitle":"Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-01-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:43.324Z","createdAt":"2026-11-09T12:40:10.604Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","kind":"article","url":"https://arxiv.org/abs/2601.01558","sourceUrl":"https://arxiv.org/abs/2601.01558","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T12:39:23.919Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2601.01558","checkedAt":"2026-11-09T12:56:07.361Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"d7f0a858e7b49c5e63c7fbaf62e5447780b3673321981f98de106d48603942ed","confidence":0.72,"provider":"typesafe","model":"jev-1.13.0","inputHash":"3a882e9547a1cbd64354ea85796c4e25fcb13f8dc18a595aaaaad0d89ad8f70a","decidedAt":"2026-11-09T12:39:24.563Z"},"provenance":{"textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observationId":"cbb0c1d65cea5f0a34db3ec436daac70b103a5afa6f09304c81d7feb83cf0392","retrievedAt":"2026-11-09T12:39:23.837Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"d3f3f5af-f430-4ae8-86f6-6d8e2c10b0a8"},"reviewer":{"model":"gpt-6-luna","runId":"2800d062-7fb9-4be9-8c70-5d418d326227"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-09T12:40:10.604Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Qu, Pengfei","url":null,"kind":"unknown"},{"name":"Ye, Lei","url":null,"kind":"unknown"},{"name":"Ouyang, Wenyu","url":null,"kind":"unknown"},{"name":"Zhang, Chi","url":null,"kind":"unknown"},{"name":"Chai, Yikai","url":null,"kind":"unknown"},{"name":"Xu, Shuolong","url":null,"kind":"unknown"},{"name":"Piao, Yongri","url":null,"kind":"unknown"},{"name":"Zhang, Miao","url":null,"kind":"unknown"},{"name":"Lu, Huchuan","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Qu, Pengfei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Qu, Pengfei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Ye, Lei","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ye, Lei","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Ouyang, Wenyu","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ouyang, Wenyu","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Zhang, Chi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Chi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Chai, Yikai","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chai, Yikai","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Xu, Shuolong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Xu, Shuolong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Piao, Yongri","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Piao, Yongri","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Zhang, Miao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Miao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}},{"actor":{"name":"Lu, Huchuan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Lu, Huchuan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2601.01558","locator":"head/meta[name=author|citation_author]"},"assertionId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T12:56:07.361Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","sourceUrl":"https://arxiv.org/abs/2601.01558","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z"}}],"participationCoverage":{"total":9,"returned":9,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2601.01558","snapshotId":"bd54a67926a9368486fc56567f38d1fe34e55c2f1cb5f9c8fcc83462ee2d87bc","contentSha256":"e3032b72505271403bfe296a28332424956d65a99b47fc86d36571fcfcd6c9ff","textHash":"a2cb3e61fb475bc3c770976c998bac7f9f542a7074c848c6b90e143a0d66242b","observedAt":"2026-11-09T12:56:07.361Z","basis":"publisher-page-metadata","sourceLinks":49,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/b2e5537c12c24bce03b484a4138df76b31e434b896fe851c036027d37083d968/source"}}}],"audits":[{"publicationId":"bd17d898-65a4-4f08-8cb8-f51ba45ce6eb","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The study is correctly attributed to Pengfei Qu and coauthors, and its results are consistently framed as what the authors report rather than as established fact.","excerpt":"Authors:Pengfei Qu, Lei Ye, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu"},{"dimension":"summary","status":"uncertain","explanation":"The reading tracks the abstract, but several central terms go unexplained for a non-specialist: embeddings (compressed numeric summaries of satellite data), CAMELS attributes (conventional basin descriptors such as terrain and vegetation), donor basins, and in-sample versus out-of-sample testing. The summary never says that an Earth Foundation Model learns from multi-modal satellite data, which is the core idea. Smallest repair: add plain-language glosses for these terms, or term-library tooltips while keeping the exact terms.","excerpt":"Earth Foundation Models (EFMs) provide a promising alternative by learning environmental representations from multi-modal satellite data."},{"dimension":"date","status":"pass","explanation":"originalPublished is 2026-01-04, which matches the v1 submission date. It is not the date of the v3 revision on 4 Nov 2026 or the feed date.","excerpt":"[Submitted on 4 Jan 2026 (v1), last revised 4 Nov 2026 (this version, v3)]"},{"dimension":"support","status":"uncertain","explanation":"The summary says the results are 'showing that transferability remains sensitive' to training conditions, but the authors only say the leave-one-cluster-out results are 'suggesting' this. The summary also drops the 'With AEF inputs' condition on the donor-selection result. Smallest repair: restore 'suggesting' and the AEF-input condition. The claims list, limitations and question are otherwise supported.","excerpt":"AEF input benefits depended on basin partitioning, suggesting that transferability remains sensitive to the catchment conditions represented during training."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the original arXiv abstract page, which is the most relevant access point to the source.","excerpt":null}],"createdAt":"2026-11-09T12:40:10.604Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}