{"id":"W4403086128","doi":"10.22541/essoar.172798936.65411263/v1","title":"Adjustment of decadal ocean carbon sink predictions using deep learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sink (geography); Carbon sink; Environmental science; Climatology; Oceanography; Geology; Climate change; Geography; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006801928,0.0005364405,0.0002811939,0.0002926275,0.0002137389,0.0005611663,0.0005725859,0.0004893911,0.001057602],"category_scores_gemma":[0.003138047,0.0003347838,0.0001945523,0.0002700748,0.0002485832,0.000641705,0.0007473436,0.0009206246,0.0002954722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000577785,"about_ca_system_score_gemma":0.0008568705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01276036,"about_ca_topic_score_gemma":0.01696335,"domain_scores_codex":[0.9998716,0.00002069753,0.00000797118,0.00004832858,0.00003020993,0.00002119971],"domain_scores_gemma":[0.9995083,0.0001604492,0.00007418631,0.00007967405,0.0001473523,0.00002995017],"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":[0.00008627294,0.00006576219,0.007695535,0.00002195538,0.00005317707,0.00004247995,0.00003546062,0.9252666,0.005518015,0.001366982,0.001386132,0.05846157],"study_design_scores_gemma":[0.000003370538,0.000005166939,0.0006225004,0.00000136615,0.000002095863,0.000002411233,0.000002123027,0.9976045,0.001116544,0.0004613307,0.0001756268,0.000002937868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5818667,0.0003238883,0.4051941,0.0007451223,0.0003010742,0.00004220367,0.0009704271,0.004886928,0.005669465],"genre_scores_gemma":[0.9533,0.00006821235,0.04405632,0.0001000668,0.0000294278,0.00002402251,0.0006431259,0.0001479046,0.001630832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01276036,"threshold_uncertainty_score":0.02537221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00901767315584877,"score_gpt":0.2191675620865558,"score_spread":0.210149888930707,"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."}}