{"id":"W4387496125","doi":"10.1038/s41467-023-42020-z","title":"Predicting discrete-time bifurcations with deep learning","year":2023,"lang":"en","type":"article","venue":"Nature Communications","topic":"Ecosystem dynamics and resilience","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Waterloo; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Heart and Stroke Foundation of Canada","keywords":"Bifurcation; Deep learning; Artificial intelligence; Computer science; Classifier (UML); Period-doubling bifurcation; Discrete time and continuous time; Bifurcation theory; Warning system; Machine learning; Pattern recognition (psychology); Nonlinear system; Mathematics; Physics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002393769,0.00008372642,0.0000781456,0.00005003279,0.0007861839,0.00003985099,0.0008508249,0.0001032055,0.0001290506],"category_scores_gemma":[0.0001103659,0.00006604326,0.00002896555,0.000925921,0.0001648717,0.0001409173,0.000538465,0.0006159806,0.001057045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006692512,"about_ca_system_score_gemma":0.00000929678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006783275,"about_ca_topic_score_gemma":0.002068744,"domain_scores_codex":[0.9992185,0.00008744111,0.0001297172,0.0001799437,0.0001957127,0.0001887032],"domain_scores_gemma":[0.9987057,0.0002209244,0.0000767585,0.0009162807,0.00001644611,0.00006388439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004730109,0.00007183103,0.9455708,0.000008683088,0.00002940926,0.000002717892,0.001515408,0.04150242,0.003147772,0.003673376,0.0010855,0.00338733],"study_design_scores_gemma":[0.0001361932,0.00004018523,0.3453572,0.00003877322,0.00002017721,0.00001175808,0.000555968,0.6234165,0.00002779627,0.0001715147,0.03002721,0.0001966658],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7927327,0.0007467894,0.0008932708,0.008342968,0.0001277954,0.0006377952,0.00002432786,0.0009642062,0.1955301],"genre_scores_gemma":[0.9946576,0.0001638945,0.002802629,0.00005323672,0.0000125038,0.00004918165,0.00009679264,0.0000154201,0.002148757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6002136,"threshold_uncertainty_score":0.9997208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005226384799582167,"score_gpt":0.2426402506370429,"score_spread":0.2374138658374607,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}