{"id":"W4380997829","doi":"10.3390/atmos14061023","title":"Sea Ice Extent Prediction with Machine Learning Methods and Subregional Analysis in the Arctic","year":2023,"lang":"en","type":"article","venue":"Atmosphere","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; McGill University","funders":"","keywords":"Sea ice; Climatology; Arctic ice pack; Arctic; Sea ice concentration; Environmental science; Cryosphere; Arctic sea ice decline; Climate change; Physical geography; Antarctic sea ice; Sea ice thickness; Oceanography; Geology; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0007398154,0.00009453057,0.0001269202,0.00001297637,0.0001989751,0.00004418327,0.0001033943,0.00003581834,0.0003913157],"category_scores_gemma":[0.00003941786,0.00005568978,0.00003942645,0.001064201,0.00007753052,0.0001202242,0.00001084526,0.0002217895,0.00002499174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004676904,"about_ca_system_score_gemma":0.00002010829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006387276,"about_ca_topic_score_gemma":0.006194263,"domain_scores_codex":[0.9990305,0.0002386227,0.0001187628,0.0002015838,0.000207651,0.0002028288],"domain_scores_gemma":[0.9993578,0.0004193416,0.00004563724,0.0001116883,0.00001869569,0.00004681863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002408507,0.000005545531,0.9380218,0.000009686739,0.00007276257,0.00002197316,0.0006513508,0.04549526,3.610889e-7,0.00006744012,0.00002075493,0.01560897],"study_design_scores_gemma":[0.00009880229,0.00005852967,0.6066312,0.000006423552,0.00009199997,0.00002115199,0.001291354,0.3908307,1.118436e-7,0.0001697209,0.0007532795,0.00004674996],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941666,0.0002244052,0.003484532,0.0009495299,0.00004185088,0.00009704819,0.00001444046,0.00004602417,0.0009756231],"genre_scores_gemma":[0.9934592,0.0002344494,0.005526987,0.0001868814,0.00003398001,0.000001921102,0.0002013079,0.000002976772,0.0003523115],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3453354,"threshold_uncertainty_score":0.9655693,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01202706762535917,"score_gpt":0.2432063847465003,"score_spread":0.2311793171211411,"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."}}