{"id":"W4406787388","doi":"10.1016/j.rse.2025.114607","title":"Enhanced sea ice classification for ICESat-2 using combined unsupervised and supervised machine learning","year":2025,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"Fundamental Research Funds for the Central Universities; China Scholarship Council; National Natural Science Foundation of China; European Space Agency","keywords":"Remote sensing; Sea ice; Geology; Computer science; Environmental science; Climatology","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":[0.0002442727,0.0001326186,0.0002041384,0.00006703965,0.0002246692,0.00001872008,0.00006537628,0.00006683703,0.00004372254],"category_scores_gemma":[0.00004526066,0.0001263054,0.00005002668,0.00008160088,0.0001152517,0.00006858182,0.00001786492,0.0001102802,0.000003183018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001862248,"about_ca_system_score_gemma":0.0000292831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001157985,"about_ca_topic_score_gemma":0.0001031456,"domain_scores_codex":[0.9990827,0.00006937343,0.0002492568,0.0002556244,0.0001412834,0.0002017114],"domain_scores_gemma":[0.9994516,0.000220863,0.0001040453,0.0001523945,0.00001714531,0.00005400207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004320248,0.00004137647,0.04621377,0.0003745691,0.0001298024,0.000003298636,0.0008112205,0.0309286,0.05363652,0.0001242659,0.000007640459,0.8672969],"study_design_scores_gemma":[0.0006337698,0.00009611574,0.04421881,0.00007621504,0.00006713878,0.000002730339,0.0003278491,0.9523784,0.00126693,0.0004300694,0.0003796201,0.0001223744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8198256,0.000149208,0.1787558,0.0003283153,0.00008739394,0.0002476003,0.00001576367,0.00001774684,0.000572462],"genre_scores_gemma":[0.9393733,0.0002751454,0.05993322,0.0001084187,0.00001942633,2.819429e-8,0.0001231913,0.000005284065,0.0001620273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9214498,"threshold_uncertainty_score":0.5150585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812853470977914,"score_gpt":0.2218375786074742,"score_spread":0.2037090438976951,"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."}}