{"id":"W4283317119","doi":"10.3390/rs14132982","title":"Multiscale Object-Based Classification and Feature Extraction along Arctic Coasts","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada; University of Calgary","funders":"","keywords":"Tundra; Artificial intelligence; Arctic; Computer science; Remote sensing; Convolutional neural network; Scale (ratio); Segmentation; Thresholding; Feature extraction; Image segmentation; Feature (linguistics); Pattern recognition (psychology); Geology; Cartography; Image (mathematics); Geography; Oceanography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0003073247,0.0004464926,0.0004237284,0.001400955,0.0002796295,0.0007708252,0.0004001897,0.0002985291,0.0005123663],"category_scores_gemma":[0.000538808,0.0001960301,0.0005163811,0.0009006375,0.0002829884,0.0004247437,0.0003826994,0.0003101453,0.0002283285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006228004,"about_ca_system_score_gemma":0.0006602536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05230559,"about_ca_topic_score_gemma":0.06275808,"domain_scores_codex":[0.9998135,0.00001039938,0.00000915866,0.00005894473,0.00006537854,0.0000426032],"domain_scores_gemma":[0.9997864,0.00003729336,0.00002674912,0.0000245492,0.0001077366,0.00001724769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004067061,0.0001928109,0.03929479,0.0002495404,0.0001784615,0.0005991397,0.0004950033,0.1517553,0.3050643,0.001926917,0.00394436,0.4958926],"study_design_scores_gemma":[0.00001153141,0.00004959487,0.06609164,0.0000228927,0.00005166625,0.0001255779,0.0002025224,0.8820357,0.04842963,0.0007177467,0.002231682,0.00002975549],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8090781,0.0003660869,0.1840003,0.0001677638,0.00004420488,0.00008009677,0.00111752,0.002359688,0.002786311],"genre_scores_gemma":[0.8736591,0.0002246361,0.1224854,0.00005950738,0.00001909605,0.00003916788,0.001967899,0.0001016098,0.001443631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05230559,"threshold_uncertainty_score":0.1040022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03758490845801541,"score_gpt":0.2567410741519116,"score_spread":0.2191561656938962,"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."}}