{ "id": "AIBD-0165", "title": "Princeton deep RL controller steers DIII-D plasmas clear of tearing instability; only two of the controlled shots disrupt", "summary": "An RL controller trained on a tearing-likelihood model kept DIII-D plasmas below the instability threshold; before RL control all but one shot disrupted, after it only two did (Nature, 21 Feb 2024).", "date_observed": "2024-02-21", "date_basis": "unassessed", "date_precision": "unassessed", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Seo et al. (Nature, published 21 February 2024), from Princeton University, the Princeton Plasma Physics Laboratory and partners, trained a reinforcement-learning (RL) controller. Its training environment was built from a multimodal dynamic model that estimates the likelihood of future tearing instability, the leading cause of disruptions. It was deployed on DIII-D, the largest magnetic fusion facility in the United States, at General Atomics in San Diego. It adjusted total beam power and plasma triangularity to keep the estimated tearability under a threshold while maintaining H-mode performance. It did so even at low safety factor and low torque. In the experimental session, discharges up to 193276 either had no RL control or tore before control started. Of the controlled discharges from 193277, only two (193277 and 193282) were disrupted. Before RL control all shots except one were disrupted. Average time-integrated normalized beta rose. Princeton Engineering's release (21 February 2024) says the model could forecast tearing mode instabilities up to 300 milliseconds in advance. The OECD AI Incidents Monitor logged the result as a positive outcome. The experiment dates are not given.", "category": "benefit created", "unexpected": false, "purpose": "The controller was built to avoid tearing instability while maintaining high-pressure plasma in DIII-D. The avoided disruptions were its intended use.", "system": "Deep reinforcement learning tearing-avoidance controller with a DNN tearability predictor (Keras model converted to real-time C)", "model_version": null, "developer": "Princeton University / Princeton Plasma Physics Laboratory (Kolemen group), with Chung-Ang University", "deployer": "DIII-D National Fusion Facility, General Atomics", "location": "San Diego, United States", "domain": "Energy research (magnetic confinement fusion)", "segment": "Tokamak plasma control", "benefit_type": "Improved Task Accuracy", "taxonomy_note": "The gain is control performance in a fusion experiment rather than accuracy of a human task.", "registry_ids": {}, "ratings": [ { "group": "organizational", "depth": 2, "reason": "The DIII-D session obtained plasmas tracking a stable path with fewer disruptions and higher time-integrated beta. The paper calls it a path toward ITER-relevant scenarios." }, { "group": "societal", "depth": null, "reason": "No outcome beyond fusion research is documented." } ], "ai_role": { "status": "assessed", "statement": "The RL controller set the high-level actuator commands that the plasma control system executed. The disruption outcomes in the controlled shots are therefore attributable to it. The comparison is within one session, and the paper is authored by the system's developers. Independent evaluation is the journal's peer review and the OECD AIM registry entry." }, "evidence": [ { "kind": "peer-reviewed study", "citation": "Seo, J., Kim, S., Jalalvand, A. et al., 'Avoiding fusion plasma tearing instability with deep reinforcement learning', Nature (2024), doi:10.1038/s41586-024-07024-9", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "We demonstrate artificial intelligence control to lower the possibility of disruptive tearing instabilities in DIII-D, the largest magnetic fusion facility in the United States." }, { "kind": "peer-reviewed study", "citation": "Seo et al., Nature 2024, results on controlled discharges", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "after RL control was applied, only two (193277 and 193282) were disrupted" }, { "kind": "press release", "citation": "Princeton Engineering news, 'Engineers use AI to wrangle fusion power for the grid', 21 February 2024", "title": "Engineers use AI to wrangle fusion power for the grid", "url": "https://engineering.princeton.edu/news/2024/02/21/engineers-use-ai-wrangle-fusion-power-grid", "date": "2024-02-21", "written_by": "makers", "quote": "could forecast potential plasma instabilities known as tearing mode instabilities up to 300 milliseconds in advance" }, { "kind": "registry label", "citation": "OECD AI Incidents Monitor, record 2024-02-24-7d77", "title": "AI Breakthrough Enables Real-Time Prediction and Prevention of Plasma Instabilities in Nuclear Fusion Reactors", "url": "https://oecd.ai/en/incidents/2024-02-24-7d77", "date": "2024-02-24", "written_by": "independent", "quote": "This is a clear example of AI use leading to a positive outcome by preventing harm" } ], "replication": { "produced_by": [ "A database of past DIII-D discharges to train the tearability predictor", "Real-time profile reconstruction and equilibrium fitting feeding the DNN", "A plasma control system that accepts high-level beam-power and shape commands" ], "must_hold": [ "A tearability model valid for the operating regime", "Actuators (beam power, triangularity) able to move the plasma along the stable path", "Session-level comparison shots to judge disruption rates" ], "echoes": [ { "date": "2022-02-16", "setting": "TCV, Lausanne; DeepMind deep RL magnetic controller (different objective)", "model_version": null, "outcome": "recurred", "source": "https://www.nature.com/articles/s41586-021-04301-9" } ] }, "paired_incident": null, "headline": "Princeton RL controller cuts DIII-D disruptions to two shots", "metric": "before RL control all but one shot disrupted, after it only two did", "comparator": { "against": "DIII-D discharges in the same experiment session without RL control", "before": "all shots except one (193266: low-βN reference shown in Fig. 3b) were disrupted", "after": "only two (193277 and 193282) were disrupted", "basis": "measured", "quote": "Before RL control, all shots except one (193266: low-βN reference shown in Fig. 3b) were disrupted, but after RL control was applied, only two (193277 and 193282) were disrupted, which were discussed earlier.", "url": "https://www.nature.com/articles/s41586-024-07024-9" }, "later": { "status": "unknown", "date": null, "note": "Later DIII-D papers from the same group describe successor tearing-mode controllers but no further result for this RL controller was found.", "quote": null, "url": null }, "value": null, "developer_country": "United States", "deployer_country": "United States", "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": "2026-10-21", "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": "Added what the benefit is measured against from the cited sources.", "source": "https://www.nature.com/articles/s41586-024-07024-9", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Princeton_Plasma_Physics_Laboratory; https://en.wikipedia.org/wiki/DIII-D_(tokamak)", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" } ], "confidence": "claimed", "shade": "low", "claim_status": "The makers' claim", "claim_basis": "Sources: a registry entry, the makers' peer-reviewed study and the makers' press release. The cited evidence includes no independent study or report and no finding by a regulator or court.", "profile": { "case_id": "AIBD-0165", "catalog_version": "1.0.0", "source_fingerprint": "114ba554771a8a1677f54ce7344ce5153ea8ef3e39ea21bcb8193a110b838600", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0165-source-0001", "AIBD-0165-source-0002", "AIBD-0165-source-0003", "AIBD-0165-source-0004" ], "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": "Princeton University / Princeton Plasma Physics Laboratory (Kolemen group), with Chung-Ang University", "deployer": "DIII-D National Fusion Facility, General Atomics" } }, "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 RL controller set the high-level actuator commands that the plasma control system executed. The disruption outcomes in the controlled shots are therefore attributable to it. The comparison is within one session, and the paper is authored by the system's developers. Independent evaluation is the journal's peer review and the OECD AIM registry entry." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "benefit created", "ai_role": { "status": "assessed", "statement": "The RL controller set the high-level actuator commands that the plasma control system executed. The disruption outcomes in the controlled shots are therefore attributable to it. The comparison is within one session, and the paper is authored by the system's developers. Independent evaluation is the journal's peer review and the OECD AIM registry entry." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role", "category" ], "source_refs": [] }, "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": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "organizational", "depth": 2, "reason": "The DIII-D session obtained plasmas tracking a stable path with fewer disruptions and higher time-integrated beta. The paper calls it a path toward ITER-relevant scenarios." }, { "group": "societal", "reason": "No outcome beyond fusion research is documented." } ] } }, "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[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "low", "evidence_word": "claimed", "claim_status": "The makers' claim", "basis": "Sources: a registry entry, the makers' peer-reviewed study and the makers' press release. The cited evidence includes no independent study or report and 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": "organizational", "depth": 2, "reason": "The DIII-D session obtained plasmas tracking a stable path with fewer disruptions and higher time-integrated beta. The paper calls it a path toward ITER-relevant scenarios." }, { "group": "societal", "reason": "No outcome beyond fusion research is documented." } ] } }, "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": "organizational", "depth": 2, "reason": "The DIII-D session obtained plasmas tracking a stable path with fewer disruptions and higher time-integrated beta. The paper calls it a path toward ITER-relevant scenarios." }, { "group": "societal", "reason": "No outcome beyond fusion research is documented." } ] } }, "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": "not_assessed", "review_state": "not_assessed", "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": "before RL control all but one shot disrupted, after it only two did", "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": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "unknown", "note": "Later DIII-D papers from the same group describe successor tearing-mode controllers but no further result for this RL controller was found." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "later" ], "source_refs": [] }, "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-0165" } }, "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": "The gain is control performance in a fusion experiment rather than accuracy of a human task." } }, "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": "Seo et al. (Nature, published 21 February 2024), from Princeton University, the Princeton Plasma Physics Laboratory and partners, trained a reinforcement-learning (RL) controller. Its training environment was built from a multimodal dynamic model that estimates the likelihood of future tearing instability, the leading cause of disruptions. It was deployed on DIII-D, the largest magnetic fusion facility in the United States, at General Atomics in San Diego. It adjusted total beam power and plasma triangularity to keep the estimated tearability under a threshold while maintaining H-mode performance. It did so even at low safety factor and low torque. In the experimental session, discharges up to 193276 either had no RL control or tore before control started. Of the controlled discharges from 193277, only two (193277 and 193282) were disrupted. Before RL control all shots except one were disrupted. Average time-integrated normalized beta rose. Princeton Engineering's release (21 February 2024) says the model could forecast tearing mode instabilities up to 300 milliseconds in advance. The OECD AI Incidents Monitor logged the result as a positive outcome. The experiment dates are not given.", "benefit_type": "Improved Task Accuracy" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "benefit_type" ], "source_refs": [] }, "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": "organizational", "depth": 2, "reason": "The DIII-D session obtained plasmas tracking a stable path with fewer disruptions and higher time-integrated beta. The paper calls it a path toward ITER-relevant scenarios." }, { "group": "societal", "reason": "No outcome beyond fusion research is documented." } ] } }, "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": "The controller was built to avoid tearing instability while maintaining high-pressure plasma in DIII-D. The avoided disruptions were its intended use." } }, "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": { "location": "San Diego, United States", "developer_country": "United States", "deployer_country": "United States" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "location", "developer_country", "deployer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "The controller was built to avoid tearing instability while maintaining high-pressure plasma in DIII-D. The avoided disruptions were its intended use." } }, "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": "2024-02-21", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "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": "Added what the benefit is measured against from the cited sources.", "source": "https://www.nature.com/articles/s41586-024-07024-9", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Princeton_Plasma_Physics_Laboratory; https://en.wikipedia.org/wiki/DIII-D_(tokamak)", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "date_observed", "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.attempts[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "A database of past DIII-D discharges to train the tearability predictor", "Real-time profile reconstruction and equilibrium fitting feeding the DNN", "A plasma control system that accepts high-level beam-power and shape commands" ], "must_hold": [ "A tearability model valid for the operating regime", "Actuators (beam power, triangularity) able to move the plasma along the stable path", "Session-level comparison shots to judge disruption rates" ], "echoes": [ { "date": "2022-02-16", "setting": "TCV, Lausanne; DeepMind deep RL magnetic controller (different objective)", "outcome": "recurred", "source": "https://www.nature.com/articles/s41586-021-04301-9" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.conditions": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "A database of past DIII-D discharges to train the tearability predictor", "Real-time profile reconstruction and equilibrium fitting feeding the DNN", "A plasma control system that accepts high-level beam-power and shape commands" ], "must_hold": [ "A tearability model valid for the operating regime", "Actuators (beam power, triangularity) able to move the plasma along the stable path", "Session-level comparison shots to judge disruption rates" ], "echoes": [ { "date": "2022-02-16", "setting": "TCV, Lausanne; DeepMind deep RL magnetic controller (different objective)", "outcome": "recurred", "source": "https://www.nature.com/articles/s41586-021-04301-9" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "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": "2026-10-21", "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": "Added what the benefit is measured against from the cited sources.", "source": "https://www.nature.com/articles/s41586-024-07024-9", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Princeton_Plasma_Physics_Laboratory; https://en.wikipedia.org/wiki/DIII-D_(tokamak)", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Energy research (magnetic confinement fusion)", "segment": "Tokamak plasma control" } }, "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": "Seo, J., Kim, S., Jalalvand, A. et al., 'Avoiding fusion plasma tearing instability with deep reinforcement learning', Nature (2024), doi:10.1038/s41586-024-07024-9", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "We demonstrate artificial intelligence control to lower the possibility of disruptive tearing instabilities in DIII-D, the largest magnetic fusion facility in the United States." }, { "kind": "peer-reviewed study", "citation": "Seo et al., Nature 2024, results on controlled discharges", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "after RL control was applied, only two (193277 and 193282) were disrupted" }, { "kind": "press release", "citation": "Princeton Engineering news, 'Engineers use AI to wrangle fusion power for the grid', 21 February 2024", "title": "Engineers use AI to wrangle fusion power for the grid", "url": "https://engineering.princeton.edu/news/2024/02/21/engineers-use-ai-wrangle-fusion-power-grid", "date": "2024-02-21", "written_by": "makers", "quote": "could forecast potential plasma instabilities known as tearing mode instabilities up to 300 milliseconds in advance" }, { "kind": "registry label", "citation": "OECD AI Incidents Monitor, record 2024-02-24-7d77", "title": "AI Breakthrough Enables Real-Time Prediction and Prevention of Plasma Instabilities in Nuclear Fusion Reactors", "url": "https://oecd.ai/en/incidents/2024-02-24-7d77", "date": "2024-02-24", "written_by": "independent", "quote": "This is a clear example of AI use leading to a positive outcome by preventing harm" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0165-source-0001", "AIBD-0165-source-0002", "AIBD-0165-source-0003", "AIBD-0165-source-0004" ], "role": "Existing evidence items, in their original order" }, "provenance": { "kind": "curatorial", "basis": "Stable within the fingerprinted record version; no source content or source review has been added.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "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": "Seo, J., Kim, S., Jalalvand, A. et al., 'Avoiding fusion plasma tearing instability with deep reinforcement learning', Nature (2024), doi:10.1038/s41586-024-07024-9", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "We demonstrate artificial intelligence control to lower the possibility of disruptive tearing instabilities in DIII-D, the largest magnetic fusion facility in the United States." }, { "kind": "peer-reviewed study", "citation": "Seo et al., Nature 2024, results on controlled discharges", "title": "Avoiding fusion plasma tearing instability with deep reinforcement learning", "url": "https://www.nature.com/articles/s41586-024-07024-9", "date": "2024-02-21", "written_by": "makers", "quote": "after RL control was applied, only two (193277 and 193282) were disrupted" }, { "kind": "press release", "citation": "Princeton Engineering news, 'Engineers use AI to wrangle fusion power for the grid', 21 February 2024", "title": "Engineers use AI to wrangle fusion power for the grid", "url": "https://engineering.princeton.edu/news/2024/02/21/engineers-use-ai-wrangle-fusion-power-grid", "date": "2024-02-21", "written_by": "makers", "quote": "could forecast potential plasma instabilities known as tearing mode instabilities up to 300 milliseconds in advance" }, { "kind": "registry label", "citation": "OECD AI Incidents Monitor, record 2024-02-24-7d77", "title": "AI Breakthrough Enables Real-Time Prediction and Prevention of Plasma Instabilities in Nuclear Fusion Reactors", "url": "https://oecd.ai/en/incidents/2024-02-24-7d77", "date": "2024-02-24", "written_by": "independent", "quote": "This is a clear example of AI use leading to a positive outcome by preventing harm" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].upstream_sources": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "An RL controller trained on a tearing-likelihood model kept DIII-D plasmas below the instability threshold; before RL control all but one shot disrupted, after it only two did (Nature, 21 Feb 2024).", "account": "Seo et al. (Nature, published 21 February 2024), from Princeton University, the Princeton Plasma Physics Laboratory and partners, trained a reinforcement-learning (RL) controller. Its training environment was built from a multimodal dynamic model that estimates the likelihood of future tearing instability, the leading cause of disruptions. It was deployed on DIII-D, the largest magnetic fusion facility in the United States, at General Atomics in San Diego. It adjusted total beam power and plasma triangularity to keep the estimated tearability under a threshold while maintaining H-mode performance. It did so even at low safety factor and low torque. In the experimental session, discharges up to 193276 either had no RL control or tore before control started. Of the controlled discharges from 193277, only two (193277 and 193282) were disrupted. Before RL control all shots except one were disrupted. Average time-integrated normalized beta rose. Princeton Engineering's release (21 February 2024) says the model could forecast tearing mode instabilities up to 300 milliseconds in advance. The OECD AI Incidents Monitor logged the result as a positive outcome. The experiment dates are not given." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "summary", "account" ], "source_refs": [] }, "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": "Deep reinforcement learning tearing-avoidance controller with a DNN tearability predictor (Keras model converted to real-time C)" } }, "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": "Princeton University / Princeton Plasma Physics Laboratory (Kolemen group), with Chung-Ang University" } }, "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": "Princeton deep RL controller steers DIII-D plasmas clear of tearing instability; only two of the controlled shots disrupt", "headline": "Princeton RL controller cuts DIII-D disruptions to two shots" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "title", "headline" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "114ba554771a8a1677f54ce7344ce5153ea8ef3e39ea21bcb8193a110b838600" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Deterministic content version assigned by the local migration.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Seo et al. (Nature, published 21 February 2024), from Princeton University, the Princeton Plasma Physics Laboratory and partners, trained a reinforcement-learning (RL) controller. Its training environment was built from a multimodal dynamic model that estimates the likelihood of future tearing instability, the leading cause of disruptions. It was deployed on DIII-D, the largest magnetic fusion facility in the United States, at General Atomics in San Diego. It adjusted total beam power and plasma triangularity to keep the estimated tearability under a threshold while maintaining H-mode performance. It did so even at low safety factor and low torque. In the experimental session, discharges up to 193276 either had no RL control or tore before control started. Of the controlled discharges from 193277, only two (193277 and 193282) were disrupted. Before RL control all shots except one were disrupted. Average time-integrated normalized beta rose. Princeton Engineering's release (21 February 2024) says the model could forecast tearing mode instabilities up to 300 milliseconds in advance. The OECD AI Incidents Monitor logged the result as a positive outcome. The experiment dates are not given.", "replication": { "produced_by": [ "A database of past DIII-D discharges to train the tearability predictor", "Real-time profile reconstruction and equilibrium fitting feeding the DNN", "A plasma control system that accepts high-level beam-power and shape commands" ], "must_hold": [ "A tearability model valid for the operating regime", "Actuators (beam power, triangularity) able to move the plasma along the stable path", "Session-level comparison shots to judge disruption rates" ], "echoes": [ { "date": "2022-02-16", "setting": "TCV, Lausanne; DeepMind deep RL magnetic controller (different objective)", "outcome": "recurred", "source": "https://www.nature.com/articles/s41586-021-04301-9" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" } }, "summary": { "total": 91, "addressed": 91, "known": 29, "reviewed": 0, "record_mapped": 29, "not_assessed": 62, "complete": false, "by_state": { "value_present": 29, "not_reported": 0, "unresolved": 0, "not_assessed": 62, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }