{"id":"W2049356376","doi":"10.1155/2009/167239","title":"Forecasts of Tropical Pacific Sea Surface Temperatures by Neural Networks and Support Vector Regression","year":2009,"lang":"en","type":"article","venue":"International Journal of Oceanography","topic":"Oceanographic and Atmospheric Processes","field":"Earth and Planetary Sciences","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Oceanic and Atmospheric Administration; Canadian Foundation for Climate and Atmospheric Sciences","keywords":"Sea surface temperature; Support vector machine; Artificial neural network; Outlier; Principal component analysis; Linear regression; Regression; Algorithm; Artificial intelligence; Computer science; Geology; Mathematics; Climatology; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001388604,0.0001434764,0.0002319033,0.00007731326,0.00005556421,0.00007578776,0.0003177885,0.00006759605,0.0001557133],"category_scores_gemma":[0.00002596968,0.00009791062,0.0001595516,0.0002761905,0.0001334747,0.0003685212,0.000008149013,0.0002270228,4.218699e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002056003,"about_ca_system_score_gemma":0.00002833406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006392866,"about_ca_topic_score_gemma":0.000003837073,"domain_scores_codex":[0.9987359,0.00004368606,0.0004123046,0.0001340569,0.0005005207,0.0001735048],"domain_scores_gemma":[0.9990947,0.00008614781,0.0003541929,0.000064855,0.0002564119,0.0001436612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003050528,0.00005275487,0.9774177,0.000006161345,0.00007895753,0.00005766008,0.00006571147,0.0008790698,0.00007890732,0.00002431796,0.006343112,0.01469059],"study_design_scores_gemma":[0.0009032904,0.001261292,0.9822076,0.0001161165,0.0000387051,0.0004590491,0.0001761781,0.01120406,0.0005546603,0.0005510758,0.002314997,0.0002129733],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935572,0.004284209,0.0003564949,0.000766156,0.0005965764,0.00004222916,0.00004767715,0.00001052424,0.0003389578],"genre_scores_gemma":[0.9978161,0.001033021,0.0007120981,0.0001958911,0.0001855725,2.429874e-8,0.00003025334,0.000002935782,0.00002403993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01447762,"threshold_uncertainty_score":0.3992679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006167890557689708,"score_gpt":0.219274841081855,"score_spread":0.2131069505241653,"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."}}