{"id":"W3200303296","doi":"10.1073/pnas.2106140118","title":"Deep learning for early warning signals of tipping points","year":2021,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Ecosystem dynamics and resilience","field":"Environmental Science","cited_by":274,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Tipping point (physics); Warning system; Computer science; False positives and false negatives; Artificial intelligence; False positive paradox; Deep learning; State (computer science); Point (geometry); Machine learning; Early warning system; Algorithm; Mathematics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008447281,0.0007677287,0.0006773514,0.0009089624,0.000340653,0.0007513296,0.001149741,0.001026595,0.002003188],"category_scores_gemma":[0.003957035,0.0003959328,0.0004367678,0.0006210408,0.0005326658,0.001398847,0.001063317,0.002105518,0.0003947795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001017998,"about_ca_system_score_gemma":0.0008675754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006008646,"about_ca_topic_score_gemma":0.006427728,"domain_scores_codex":[0.9997821,0.00004925595,0.00001526935,0.00006427134,0.00004422616,0.00004483556],"domain_scores_gemma":[0.9992455,0.0004122705,0.00009446545,0.00006433168,0.0001374517,0.00004593165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000134455,0.0001275375,0.004490921,0.0001208525,0.00008333291,0.0001060924,0.00009088159,0.7763499,0.003706842,0.01579095,0.005934891,0.1930633],"study_design_scores_gemma":[0.000002415003,0.000007565314,0.0001618275,0.000005740439,0.000002790227,0.000005028361,0.00000412745,0.9937305,0.0004079411,0.00545842,0.0002108128,0.000002741883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1362758,0.00191912,0.8521467,0.001852049,0.000184097,0.00004915589,0.000649985,0.002861256,0.004061773],"genre_scores_gemma":[0.9226877,0.0004327505,0.07236892,0.0002540101,0.00007373205,0.00005447892,0.0007107939,0.00007713609,0.003340539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006008646,"threshold_uncertainty_score":0.01194733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02057111372301025,"score_gpt":0.2696838983739479,"score_spread":0.2491127846509376,"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."}}