{"id":"W4413640845","doi":"10.1016/j.coldregions.2025.104656","title":"Assessing regression-based deep learning for river ice estimation from drone images","year":2025,"lang":"en","type":"article","venue":"Cold Regions Science and Technology","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Drone; Regression; Regression analysis; Geology; Estimation; Deep learning; Artificial intelligence; Remote sensing; Environmental science; Computer science; Machine learning; Engineering; Statistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003215009,0.00009270043,0.0001246135,0.0003677649,0.001145158,0.0001156843,0.0002619346,0.000103873,0.00002050071],"category_scores_gemma":[0.0005835859,0.00007405934,0.00001865616,0.001043787,0.001617213,0.0003985517,0.00003204031,0.0001622079,0.000006134061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001478079,"about_ca_system_score_gemma":0.0002419861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001932178,"about_ca_topic_score_gemma":0.00007645549,"domain_scores_codex":[0.9991195,0.00001818097,0.000123583,0.0003291494,0.0001466002,0.0002630271],"domain_scores_gemma":[0.9992268,0.0003303519,0.00007765742,0.0001669732,0.0001520064,0.00004622677],"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":[0.00002115282,0.0000328749,0.2444633,0.00004019178,0.00001405244,0.00001022849,0.0001491155,0.003321682,0.00367067,0.01329277,0.0003428983,0.7346411],"study_design_scores_gemma":[0.0003876871,0.00008080045,0.04257457,0.0001420352,0.00003702856,0.000004808682,0.001386064,0.9253529,0.001508218,0.02488204,0.003477864,0.0001660143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6044364,0.0004924192,0.3820458,0.01059319,0.0003302785,0.000322664,0.00001064802,0.0002265754,0.001541962],"genre_scores_gemma":[0.965179,0.00004537079,0.03432781,0.0002217465,0.00001251853,0.000004984992,0.00002123538,0.000001709139,0.0001856754],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9220312,"threshold_uncertainty_score":0.8807747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01040386193241881,"score_gpt":0.257670641972657,"score_spread":0.2472667800402382,"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."}}