{"id":"W4221088376","doi":"10.5194/bg-19-1705-2022","title":"Improved prediction of dimethyl sulfide (DMS) distributions in the northeast subarctic Pacific using machine-learning algorithms","year":2022,"lang":"en","type":"article","venue":"Biogeosciences","topic":"Atmospheric chemistry and aerosols","field":"Earth and Planetary Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimethyl sulfide; Subarctic climate; Mesoscale meteorology; Environmental science; Sea surface temperature; Dimethylsulfoniopropionate; Climatology; Atmospheric sciences; Nutrient; Geology; Oceanography; Chemistry; Phytoplankton","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":[0.000893965,0.00009845161,0.0001161033,0.00001686451,0.0008078607,0.00004866188,0.0003943104,0.00002525707,0.0005656436],"category_scores_gemma":[0.00008226527,0.0000689452,0.00005844253,0.001062969,0.0002562462,0.0001618995,0.00003292703,0.0002112215,0.000001468743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001142026,"about_ca_system_score_gemma":0.00008823312,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01185523,"about_ca_topic_score_gemma":0.0005341163,"domain_scores_codex":[0.9986981,0.0001785251,0.000238192,0.0002491178,0.0003742756,0.000261752],"domain_scores_gemma":[0.9995002,0.0001569284,0.0001349863,0.000139526,0.00001958053,0.00004882476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001256519,0.00003978314,0.987317,0.000007438476,0.000003637148,0.000004124064,0.0004574702,0.001246205,0.008301819,0.00000993983,0.000004985676,0.002595056],"study_design_scores_gemma":[0.0003175847,0.0003447992,0.5492697,0.00001336192,0.00002681368,0.00009057055,0.0132174,0.4306845,0.002459878,0.0002464128,0.003093589,0.0002353726],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976044,0.0003092648,0.0004141668,0.0001484692,0.0002375852,0.0001349458,0.0007818135,0.00001960212,0.0003497226],"genre_scores_gemma":[0.9991587,0.00001796384,0.000517602,0.00001483776,0.00004232254,0.000003978286,0.0001988854,0.00000147042,0.00004424493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4380472,"threshold_uncertainty_score":0.9947249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01845474497771164,"score_gpt":0.2170337739367773,"score_spread":0.1985790289590656,"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."}}