{"id":"W4414229893","doi":"10.1109/jstars.2025.3610260","title":"Fusing Ice Surface Temperature With the AI4Arctic Dataset for Improved Deep Learning-Based Sea Ice Mapping","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Alliance de recherche numérique du Canada; Environment and Climate Change Canada","keywords":"Sea ice; Sea ice concentration; Sea ice thickness; Synthetic aperture radar; Arctic ice pack; Sea surface temperature; Cryosphere; Arctic","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007598907,0.002275476,0.000782838,0.001615662,0.0004504199,0.001054061,0.001400968,0.0009190233,0.002370494],"category_scores_gemma":[0.001577198,0.0003288472,0.001431609,0.001345125,0.0003189548,0.001027619,0.001116307,0.001559931,0.001758024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009022484,"about_ca_system_score_gemma":0.001307889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03867922,"about_ca_topic_score_gemma":0.06577168,"domain_scores_codex":[0.9996508,0.00004910049,0.00002319586,0.0001183013,0.00008388795,0.00007461006],"domain_scores_gemma":[0.9996494,0.00006845896,0.00003338432,0.00007439766,0.0001411739,0.00003314007],"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":[0.00104894,0.001355366,0.06494313,0.0007204394,0.001025407,0.0008194747,0.0001369331,0.5041299,0.01387512,0.001283098,0.149026,0.2616362],"study_design_scores_gemma":[0.0001027862,0.0001299625,0.02058486,0.0001235961,0.000128618,0.00009830312,0.0001224631,0.9503075,0.009586526,0.001052533,0.01770062,0.00006222943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7114034,0.007863763,0.08017153,0.001975818,0.002232027,0.0004323148,0.1466141,0.02930752,0.0199995],"genre_scores_gemma":[0.5828992,0.001262582,0.06805807,0.0006623755,0.0002983622,0.0003266976,0.3361013,0.0007352941,0.009656142],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03867922,"threshold_uncertainty_score":0.07690817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01246031342328352,"score_gpt":0.2135972010987378,"score_spread":0.2011368876754543,"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."}}