{"id":"W4415108044","doi":"10.1175/aies-d-24-0107.1","title":"Adjustment of Decadal Ocean Carbon Sink Predictions Using Deep Learning","year":2025,"lang":"en","type":"article","venue":"Artificial Intelligence for the Earth Systems","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Mean squared error; Artificial neural network; Anomaly (physics); Correlation coefficient; Carbon sink; Forecast skill; Climate model; Flexibility (engineering)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0006246479,0.0004931928,0.0002376883,0.0002723968,0.0001803312,0.0005046519,0.0004313824,0.0004109187,0.001191756],"category_scores_gemma":[0.002348205,0.0002580851,0.0001884139,0.0001983676,0.0002067932,0.0005280149,0.0005133711,0.0008402485,0.0003080622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005647186,"about_ca_system_score_gemma":0.0008152573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01176643,"about_ca_topic_score_gemma":0.01344623,"domain_scores_codex":[0.9998974,0.00001892335,0.000006238567,0.00003641286,0.00002351561,0.00001759497],"domain_scores_gemma":[0.999536,0.000149741,0.00007134918,0.00005987668,0.0001537723,0.00002912046],"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":[0.0001639435,0.0001308084,0.01834719,0.00002818536,0.00007040398,0.00004867184,0.00004123004,0.8817512,0.01171565,0.0008367121,0.001512512,0.08535345],"study_design_scores_gemma":[0.000004851825,0.000008372137,0.001688525,0.000001713063,0.000002886765,0.000002362526,0.000002907041,0.9957643,0.002168429,0.0002074832,0.0001446066,0.000003648462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8094178,0.0001869893,0.1823299,0.0005023532,0.0002018747,0.00003301599,0.0005571889,0.003012002,0.003758876],"genre_scores_gemma":[0.9771029,0.0000327947,0.02145909,0.00005918695,0.0000139451,0.00001050119,0.0002926198,0.00006336736,0.0009656564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01176643,"threshold_uncertainty_score":0.0233959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02235176106563529,"score_gpt":0.2546006528642195,"score_spread":0.2322488917985842,"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."}}