{"id":"W7092367461","doi":"10.1016/j.jag.2025.104911","title":"A novel sea ice floe fragmentation index using Sentinel-2 and AMSR2 satellite data based on machine learning","year":2025,"lang":"en","type":"article","venue":"International Journal of Applied Earth Observation and Geoinformation","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Korea Institute of Marine Science and Technology promotion; Korea Polar Research Institute; Ministry of Oceans and Fisheries","keywords":"Sea ice; Fragmentation (computing); Gradient boosting; Random forest; Support vector machine; Satellite; Ice field; Sea ice concentration","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006428383,0.0006341001,0.0003634631,0.002906546,0.000194752,0.0006054957,0.000438668,0.0004091021,0.0004742673],"category_scores_gemma":[0.001373171,0.0001709461,0.0004813778,0.001392572,0.0002154026,0.0009978171,0.0004931006,0.0002672486,0.000189372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004497502,"about_ca_system_score_gemma":0.000321868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005298682,"about_ca_topic_score_gemma":0.007001508,"domain_scores_codex":[0.9996978,0.00003572168,0.0000277762,0.0000993514,0.000099321,0.00004014558],"domain_scores_gemma":[0.9994562,0.00008638557,0.0002096866,0.00004462556,0.0001623648,0.00004067243],"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":[0.0003510365,0.0003290705,0.355655,0.0003562314,0.000476474,0.0003864036,0.0002999412,0.1885223,0.0402655,0.001901454,0.006058309,0.4053983],"study_design_scores_gemma":[0.00001965226,0.0001183893,0.1495032,0.00003986965,0.00006972194,0.0001876286,0.0001195702,0.8389359,0.007550224,0.0008997583,0.00250305,0.00005301283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7988279,0.0006704769,0.1911344,0.0001185016,0.0001041945,0.000197285,0.003257186,0.001540559,0.004149579],"genre_scores_gemma":[0.9146712,0.0001995742,0.08042353,0.00005640405,0.00004663728,0.0001242152,0.003805371,0.00005147807,0.0006215624],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005298682,"threshold_uncertainty_score":0.01053566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411979895745619,"score_gpt":0.2498748505248702,"score_spread":0.225755051567414,"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."}}