{ "id": "AIBD-0092", "title": "Independent evaluation finds Google Flood Hub and GloFAS forecasts skillful beyond four days in Mali's frequently flooded regions, suggesting seven-day Red Cross early-action triggers", "summary": "Forecasts could allow earlier action in parts of Mali, but Google Flood Hub produced frequent false alarms. No benefit from an implemented early action was measured.", "date_observed": "2025-03-14", "date_basis": "source publication", "date_precision": "day", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Researchers evaluated Google Flood Hub and GloFAS forecasts against river-flow observations and records of flood impacts in Mali. Their results suggest that some early-action plans could extend from four to seven days without much loss of forecast skill. Performance varied across districts and thresholds, and no correctly predicted floods were found in the northern districts that were evaluated. At a seven-day lead time, Google Flood Hub’s false-alarm ratio was around 0.8 across discharge thresholds, compared with around 0.5 for GloFAS. The authors describe GloFAS as more balanced in several comparisons. They used a ten-day matching window to compare forecasts with reported impacts, which affects the interpretation of performance. This was a retrospective forecast evaluation; it did not measure benefits from an implemented early action. The researchers are independent of Google, although one coauthor works at the Joint Research Centre, which contributes to GloFAS.", "category": "general benefit", "unexpected": false, "purpose": "AI-based riverine flood forecasting for ungauged basins to support early warning and anticipatory action.", "system": "Google Flood Hub", "model_version": null, "developer": "Google", "deployer": "Evaluated for the Mali Red Cross Early Action Protocol; not documented as an operational trigger", "location": null, "domain": "Hydrology / flood forecasting", "segment": "Humanitarian anticipatory action", "benefit_type": "Improved Task Accuracy", "taxonomy_note": "A forecast-skill evaluation is read as task accuracy; no early action is documented.", "registry_ids": {}, "ratings": [ { "group": "personal", "depth": null, "reason": "Skill evaluation, no discrete event." }, { "group": "organizational", "depth": null, "reason": "Skill evaluation, no discrete event." }, { "group": "societal", "depth": null, "reason": "Skill evaluation, no discrete event." } ], "ai_role": { "status": "assessed", "statement": "The study directly evaluates Google Flood Hub’s machine-learning forecasts. It measures forecast performance, not a humanitarian outcome or a deployed change to the Mali Red Cross’s early-action protocol." }, "evidence": [ { "kind": "peer-reviewed study", "citation": "Kuipers, E. R., Oldenburg, V., Phung, P., Sutanudjaja, E., Ficchi, A., Salamon, P., van den Homberg, M. (2026). Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali. Journal of Flood Risk Management, doi:10.1111/jfr3.70247.", "title": "Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali", "url": "https://doi.org/10.1111/jfr3.70247", "date": "2026-09-16", "written_by": "independent", "quote": null } ], "replication": { "produced_by": [ "Global AI flood forecasts available for ungauged Malian rivers", "Evaluation against discharge observations and text-mined district-level impact data across lead times and thresholds" ], "must_hold": [ "Forecast thresholds and matching windows require local validation; performance differs substantially by district", "Frequent false alarms need to be considered alongside the potential for earlier warnings", "The proposed change to early-action planning requires implementation and outcome evaluation" ], "echoes": [] }, "paired_incident": { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "severity": null, "group": "societal", "basis": "Google-developed hazard early-warning system failed to alert millions; Flood Hub is Google's flood equivalent, with the same flood-exposed public as beneficiaries." }, "headline": "Study suggests seven-day flood warnings in parts of Mali", "metric": "skillful beyond 4-day lead time, enough for 7-day Mali Red Cross early action triggers", "comparator": null, "later": { "status": "unknown", "date": null, "note": "The study proposes changes to early-action planning; implementation and subsequent benefits are not established.", "quote": null, "url": "https://doi.org/10.1111/jfr3.70247" }, "value": null, "developer_country": "United States", "deployer_country": null, "unrated_because": null, "brief_notes": null, "brief": null, "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "source": null, "editor": "AIBD" }, { "date": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Moved the date observed and both study dates from 1 to 16 September 2026 because the Crossref record gives published-online 16 September 2026 and an issue date of September 2026 (19(3)) with no day, listed the Netherlands Red Cross 510 team first among the author institutions as four of the seven authors including the first and last are affiliated there, and retitled so that the skill result is credited to Google Flood Hub and GloFAS jointly and the seven-day lead time stays the abstract's suggestion rather than a finding.", "source": "https://api.crossref.org/works/10.1111/jfr3.70247", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to Google.", "source": null, "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "source": "https://doi.org/10.1111/jfr3.70247", "editor": "AIBD" } ], "confidence": "studied", "shade": "high", "claim_status": "Independently studied", "claim_basis": "Sources: one independent peer-reviewed study. The cited evidence includes no finding by a regulator or court.", "profile": { "case_id": "AIBD-0092", "catalog_version": "1.0.0", "source_fingerprint": "6a7e928484f2c855dedc6488ab41753b9edb46481b759f3433d7738dd3e35bab", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" }, { "collection_id": "chanticleer", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0092-source-0001" ], "families": { "strategic assessments": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "evaluations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "monetary observations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "institutional decisions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] } }, "fields": { "actors[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "developer": "Google", "deployer": "Evaluated for the Mali Red Cross Early Action Protocol; not documented as an operational trigger" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "developer", "deployer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "actors[].ownership_control": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "ai_contribution": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ai_role": { "status": "assessed", "statement": "The study directly evaluates Google Flood Hub’s machine-learning forecasts. It measures forecast performance, not a humanitarian outcome or a deployed change to the Mali Red Cross’s early-action protocol." } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "ai_role" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "general benefit", "ai_role": { "status": "assessed", "statement": "The study directly evaluates Google Flood Hub’s machine-learning forecasts. It measures forecast performance, not a humanitarian outcome or a deployed change to the Mali Red Cross’s early-action protocol." } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "category", "ai_role" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].alternatives": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].assessor_date": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].depth": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "high", "evidence_word": "studied", "claim_status": "Independently studied", "basis": "Sources: one independent peer-reviewed study. The cited evidence includes no finding by a regulator or court.", "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review." } }, "provenance": { "kind": "curatorial", "basis": "Derived from the existing case display properties; not a new evidentiary judgment.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rationale": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "Skill evaluation, no discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no discrete event." }, { "group": "societal", "reason": "Skill evaluation, no discrete event." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rubric_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].status_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].target": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "Skill evaluation, no discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no discrete event." }, { "group": "societal", "reason": "Skill evaluation, no discrete event." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "availability": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "brief": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_kind": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_links[]": { "state": "value_present", "value": { "kind": "structured", "data": { "answer": "Google-developed hazard early-warning system failed to alert millions; Flood Hub is Google's flood equivalent, with the same flood-exposed public as beneficiaries.", "links": [ { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "group": "societal", "basis": "Google-developed hazard early-warning system failed to alert millions; Flood Hub is Google's flood equivalent, with the same flood-exposed public as beneficiaries.", "relation": "comparable_harm" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Existing paired_incident classification; no new source review.", "record_fields": [ "paired_incident" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "claims[].evidence_links": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_strength": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].missingness": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].proposition": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "cross_border_flows[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "decisions[].action_outcome": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].grounds": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].institution_task": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].success_criterion": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "deployment_stage": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "economics[].amount": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].costs[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].counterfactual": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].currency_price_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].gross_net": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].measure_type": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].period_unit": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].realization": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].recipient_payer": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].return_payback": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].valuation_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "evaluations[].ai_uplift": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].comparator": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].design": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].effect": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].exposure": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].measurement_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].metric": { "state": "not_assessed", "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "metric" ], "source_refs": [] }, "review_state": "not_assessed", "coverage": "partial", "family": "evaluations", "display": { "answer": "skillful beyond 4-day lead time, enough for 7-day Mali Red Cross early action triggers", "editor_note": "" } }, "evaluations[].reproduction_materials": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].setting_sample": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].uncertainty_limitations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "external_references[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "paired_incident": { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "group": "societal", "basis": "Google-developed hazard early-warning system failed to alert millions; Flood Hub is Google's flood equivalent, with the same flood-exposed public as beneficiaries." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "paired_incident" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "unknown", "note": "The study proposes changes to early-action planning; implementation and subsequent benefits are not established.", "url": "https://doi.org/10.1111/jfr3.70247" } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "later" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "human_oversight": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "id": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "id": "AIBD-0092" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "id" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "infrastructure_dependencies[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiaries": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiary_count": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].benefit_type": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "benefit_type": "Improved Task Accuracy", "taxonomy_note": "A forecast-skill evaluation is read as task accuracy; no early action is documented." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "benefit_type", "taxonomy_note" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].claim": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Researchers evaluated Google Flood Hub and GloFAS forecasts against river-flow observations and records of flood impacts in Mali. Their results suggest that some early-action plans could extend from four to seven days without much loss of forecast skill. Performance varied across districts and thresholds, and no correctly predicted floods were found in the northern districts that were evaluated. At a seven-day lead time, Google Flood Hub’s false-alarm ratio was around 0.8 across discharge thresholds, compared with around 0.5 for GloFAS. The authors describe GloFAS as more balanced in several comparisons. They used a ten-day matching window to compare forecasts with reported impacts, which affects the interpretation of performance. This was a retrospective forecast evaluation; it did not measure benefits from an implemented early action. The researchers are independent of Google, although one coauthor works at the Joint Research Centre, which contributes to GloFAS.", "benefit_type": "Improved Task Accuracy" } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "account", "benefit_type" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].distribution": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].duration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].stakeholder_group": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "Skill evaluation, no discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no discrete event." }, { "group": "societal", "reason": "Skill evaluation, no discrete event." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].status": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].tradeoffs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].unexpected": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "unexpected": false, "purpose": "AI-based riverine flood forecasting for ungauged basins to support early warning and anticipatory action." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "unexpected", "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "places[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "developer_country": "United States" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "developer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "AI-based riverine flood forecasting for ungauged basins to support early warning and anticipatory action." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "record_dates": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "date_observed": "2025-03-14", "date_basis": "source publication", "date_precision": "day", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Moved the date observed and both study dates from 1 to 16 September 2026 because the Crossref record gives published-online 16 September 2026 and an issue date of September 2026 (19(3)) with no day, listed the Netherlands Red Cross 510 team first among the author institutions as four of the seven authors including the first and last are affiliated there, and retitled so that the skill result is credited to Google Flood Hub and GloFAS jointly and the seven-day lead time stays the abstract's suggestion rather than a finding.", "source": "https://api.crossref.org/works/10.1111/jfr3.70247", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to Google.", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "source": "https://doi.org/10.1111/jfr3.70247", "editor": "AIBD" } ] } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "date_observed", "revisions", "date_basis", "date_precision" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "replication.attempts[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "Global AI flood forecasts available for ungauged Malian rivers", "Evaluation against discharge observations and text-mined district-level impact data across lead times and thresholds" ], "must_hold": [ "Forecast thresholds and matching windows require local validation; performance differs substantially by district", "Frequent false alarms need to be considered alongside the potential for earlier warnings", "The proposed change to early-action planning requires implementation and outcome evaluation" ], "echoes": [] } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "replication" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "replication.conditions": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "Global AI flood forecasts available for ungauged Malian rivers", "Evaluation against discharge observations and text-mined district-level impact data across lead times and thresholds" ], "must_hold": [ "Forecast thresholds and matching windows require local validation; performance differs substantially by district", "Frequent false alarms need to be considered alongside the potential for earlier warnings", "The proposed change to early-action planning requires implementation and outcome evaluation" ], "echoes": [] } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "replication" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "revision_history[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Moved the date observed and both study dates from 1 to 16 September 2026 because the Crossref record gives published-online 16 September 2026 and an issue date of September 2026 (19(3)) with no day, listed the Netherlands Red Cross 510 team first among the author institutions as four of the seven authors including the first and last are affiliated there, and retitled so that the skill result is credited to Google Flood Hub and GloFAS jointly and the seven-day lead time stays the abstract's suggestion rather than a finding.", "source": "https://api.crossref.org/works/10.1111/jfr3.70247", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: account rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to Google.", "editor": "AIBD" }, { "date": "2026-10-24", "change": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "source": "https://doi.org/10.1111/jfr3.70247", "editor": "AIBD" } ] } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "revisions" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Hydrology / flood forecasting", "segment": "Humanitarian anticipatory action" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "domain", "segment" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].access_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].citation_locator": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "peer-reviewed study", "citation": "Kuipers, E. R., Oldenburg, V., Phung, P., Sutanudjaja, E., Ficchi, A., Salamon, P., van den Homberg, M. (2026). Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali. Journal of Flood Risk Management, doi:10.1111/jfr3.70247.", "title": "Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali", "url": "https://doi.org/10.1111/jfr3.70247", "date": "2026-09-16", "written_by": "independent" } ] } }, "provenance": { "kind": "source_review", "basis": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0092-source-0001" ], "role": "Active evidence sources in reviewed order" }, "provenance": { "kind": "curatorial", "basis": "Assigned to the retained evidence in the dated source review.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "complete" }, "sources[].language": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "peer-reviewed study", "citation": "Kuipers, E. R., Oldenburg, V., Phung, P., Sutanudjaja, E., Ficchi, A., Salamon, P., van den Homberg, M. (2026). Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali. Journal of Flood Risk Management, doi:10.1111/jfr3.70247.", "title": "Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali", "url": "https://doi.org/10.1111/jfr3.70247", "date": "2026-09-16", "written_by": "independent" } ] } }, "provenance": { "kind": "source_review", "basis": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial" }, "sources[].upstream_sources": { "state": "value_present", "value": { "kind": "structured", "data": { "origins": [ { "source_refs": [ "AIBD-0092-source-0001" ], "url": "https://doi.org/10.1111/jfr3.70247", "title": "Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali", "published_on": "2026-09-16", "relationship": "independent", "citation": "Kuipers, E. R., Oldenburg, V., Phung, P., Sutanudjaja, E., Ficchi, A., Salamon, P., van den Homberg, M. (2026). Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali. Journal of Flood Risk Management, doi:10.1111/jfr3.70247." } ], "excluded_republications": [ { "url": "https://doi.org/10.1111/jfr3.70247", "title": "Assessing the Riverine Flood Forecast Skill of GloFAS and Google Flood Hub With Impact Data and Discharge Observations to Support Early Actions in Mali", "published_on": "2026-09-16", "relationship": "Repeated quotation or alternate version of a retained original work", "previous_source_ref": "AIBD-0092-source-0002" }, { "url": "https://arxiv.org/abs/2307.16104", "title": "AI Increases Global Access to Reliable Flood Forecasts", "published_on": "2023-11-03", "relationship": "Retained as source history; replaced by the original evidence or omitted because no distinct evidence is used for the revised claims", "previous_source_ref": "AIBD-0092-source-0003" } ], "independent_evaluations_of_reported_results": 1, "lead_source_ref": "AIBD-0092-source-0001", "retained_source_order": [ "AIBD-0092-source-0001" ], "ordering_basis": "The source that directly supports the central case leads. Additional sources contribute the specific evidence or limitations described in claim_lineage.", "claim_lineage": [ { "claim": "Lead-time potential, false alarms, and geographic limits", "source_chain": [ { "url": "https://onlinelibrary.wiley.com/doi/full/10.1111/jfr3.70247", "locator": "Sections 2.4, 3, 4.1, 4.2, 5.1; Table 1; Appendices A–C", "role": "Original full evaluation paper and appendices", "access_status": "Full relevant text reviewed", "published_on": "2026-09-16" } ], "limitations": [ "Seven-day Flood Hub false-alarm ratio around 0.8; local skill varies", "No implemented early-action benefit measured" ], "source_ref": "AIBD-0092-source-0001" }, { "claim": "Forecast inputs, impact data, and reproducibility", "source_chain": [ { "url": "https://sites.research.google/gr/floodforecasting/resources/", "locator": "GRRR historical forecast resource", "role": "Original Google dataset documentation", "access_status": "Full relevant text reviewed" }, { "url": "https://ewds.climate.copernicus.eu/datasets/cems-glofas-reforecast", "locator": "GloFAS reforecasts", "role": "Original comparison-data catalog", "access_status": "Full relevant text reviewed" }, { "url": "https://github.com/rodekruis/river-flood-data-analysis", "locator": "README and repository description", "role": "Authors’ analysis-code repository", "access_status": "Full relevant text reviewed" }, { "url": "https://doi.org/10.1111/jfr3.70247", "locator": "Data Availability statement; Appendix A impact-source inventory", "role": "Original declaration of source access and constraints", "access_status": "Full relevant text reviewed" } ], "limitations": [ "Mali DNH flow observations for 2016–2018 are under a nondisclosure agreement", "Text-mined impact data are available on request; underlying observations were not independently reanalyzed", "The evaluation is independent of Google; a JRC coauthor is connected to GloFAS" ], "source_ref": "AIBD-0092-source-0001" }, { "claim": "Earlier public version of the longer-lead-time finding", "source_chain": [ { "url": "https://meetingorganizer.copernicus.org/EGU25/EGU25-302.html", "locator": "Abstract: results paragraph; page marked updated March 14, 2025", "role": "Original preliminary conference abstract", "access_status": "Full relevant text reviewed", "published_on": "2025-03-14" }, { "url": "https://eartharxiv.org/repository/view/11374/", "locator": "Preprint cited in the journal paper’s Data Availability statement", "role": "Earlier manuscript version", "access_status": "Repository returned a bot-verification page; full preprint not retrieved" } ], "limitations": [ "March 14 is the earliest verified public version date, not a verified initial publication date", "The preliminary abstract supports lead times beyond four days; the detailed seven-day and false-alarm results are supported by the 2026 full paper", "The conference presentation requires registration and was not obtained" ], "source_ref": "AIBD-0092-source-0001" } ], "limitations": [ "Confidential observations and on-request impact data prevent complete independent reproduction", "EarthArXiv full preprint and the conference presentation were inaccessible" ], "chronology_source": { "url": "https://meetingorganizer.copernicus.org/EGU25/EGU25-302.html", "locator": "Abstract page updated March 14, 2025", "role": "Earliest verified public version of the central finding", "access_status": "Full relevant text reviewed", "published_on": "2025-03-14", "date": "2025-03-14", "title": "Assessing the riverine flood forecast skill of GloFAS and Google Flood Hub with impact data and river flow observations to support early actions in Mali" } } }, "provenance": { "kind": "source_review", "basis": "Consolidated repeated quotations of one paper, added material limitations from the full results and appendices, and traced the finding to its earlier EGU abstract.", "record_fields": [ "evidence" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "reviewed", "coverage": "partial", "display": { "answer": "Some observations are confidential, and the impact data are available only on request. The EarthArXiv preprint and conference presentation were inaccessible.", "editor_note": "" } }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "Forecasts could allow earlier action in parts of Mali, but Google Flood Hub produced frequent false alarms. No benefit from an implemented early action was measured.", "account": "Researchers evaluated Google Flood Hub and GloFAS forecasts against river-flow observations and records of flood impacts in Mali. Their results suggest that some early-action plans could extend from four to seven days without much loss of forecast skill. Performance varied across districts and thresholds, and no correctly predicted floods were found in the northern districts that were evaluated. At a seven-day lead time, Google Flood Hub’s false-alarm ratio was around 0.8 across discharge thresholds, compared with around 0.5 for GloFAS. The authors describe GloFAS as more balanced in several comparisons. They used a ten-day matching window to compare forecasts with reported impacts, which affects the interpretation of performance. This was a retrospective forecast evaluation; it did not measure benefits from an implemented early action. The researchers are independent of Google, although one coauthor works at the Joint Research Centre, which contributes to GloFAS." } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "summary", "account" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].autonomy_permissions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].component_role": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].deployment_configuration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].inputs_outputs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_name": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].product_name": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "system": "Google Flood Hub" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "system" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].provider": { "state": "value_present", "value": { "kind": "structured", "data": { "application_developer": "Google" } }, "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "developer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "taxonomy_crosswalks[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "title": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "title": "Independent evaluation finds Google Flood Hub and GloFAS forecasts skillful beyond four days in Mali's frequently flooded regions, suggesting seven-day Red Cross early-action triggers", "headline": "Study suggests seven-day flood warnings in parts of Mali" } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "title", "headline" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "6a7e928484f2c855dedc6488ab41753b9edb46481b759f3433d7738dd3e35bab" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Deterministic content version after the October 24, 2026 primary-source review.", "record_fields": [], "source_refs": [], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Researchers evaluated Google Flood Hub and GloFAS forecasts against river-flow observations and records of flood impacts in Mali. Their results suggest that some early-action plans could extend from four to seven days without much loss of forecast skill. Performance varied across districts and thresholds, and no correctly predicted floods were found in the northern districts that were evaluated. At a seven-day lead time, Google Flood Hub’s false-alarm ratio was around 0.8 across discharge thresholds, compared with around 0.5 for GloFAS. The authors describe GloFAS as more balanced in several comparisons. They used a ten-day matching window to compare forecasts with reported impacts, which affects the interpretation of performance. This was a retrospective forecast evaluation; it did not measure benefits from an implemented early action. The researchers are independent of Google, although one coauthor works at the Joint Research Centre, which contributes to GloFAS.", "replication": { "produced_by": [ "Global AI flood forecasts available for ungauged Malian rivers", "Evaluation against discharge observations and text-mined district-level impact data across lead times and thresholds" ], "must_hold": [ "Forecast thresholds and matching windows require local validation; performance differs substantially by district", "Frequent false alarms need to be considered alongside the potential for earlier warnings", "The proposed change to early-action planning requires implementation and outcome evaluation" ], "echoes": [] } } }, "provenance": { "kind": "curatorial", "basis": "Updated affected case fields after the dated primary-source review. Unrelated requirement assessments retain their existing status.", "record_fields": [ "account", "replication" ], "source_refs": [ "AIBD-0092-source-0001" ], "reviewed_on": "2026-10-24" }, "review_state": "record_mapped", "coverage": "partial" } }, "summary": { "total": 91, "addressed": 91, "known": 31, "reviewed": 4, "record_mapped": 27, "not_assessed": 60, "complete": false, "by_state": { "value_present": 31, "not_reported": 0, "unresolved": 0, "not_assessed": 60, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }