{"id":"W4282579090","doi":"10.3390/rs14122747","title":"Accuracy, Efficiency, and Transferability of a Deep Learning Model for Mapping Retrogressive Thaw Slumps across the Canadian Arctic","year":2022,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; National Aeronautics and Space Administration","keywords":"Transferability; Computer science; Arctic; Artificial intelligence; Landform; Deep learning; Machine learning; Data mining; Geology; Geomorphology; Oceanography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001785831,0.00117839,0.0004322024,0.0006407336,0.0006956573,0.001098086,0.001075131,0.0006367077,0.0007038396],"category_scores_gemma":[0.003625339,0.0003135665,0.0005234243,0.0005451143,0.0009608769,0.0007236931,0.0008681034,0.00093223,0.0002053829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004770943,"about_ca_system_score_gemma":0.003908724,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5449589,"about_ca_topic_score_gemma":0.4528162,"domain_scores_codex":[0.9994937,0.00007143044,0.00002392839,0.000169782,0.0001041353,0.0001369744],"domain_scores_gemma":[0.9989111,0.0004480453,0.00006179942,0.00013894,0.0003582237,0.00008187249],"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":[0.0002306929,0.00004084919,0.009901473,0.00003486919,0.00005231945,0.00005140894,0.00007455208,0.9485828,0.006036077,0.0004140493,0.0007400709,0.03384087],"study_design_scores_gemma":[0.00001117231,0.00002522862,0.004657255,0.000009352387,0.00001824387,0.00001101465,0.00004091392,0.9893086,0.005392948,0.0003027318,0.0002090688,0.00001349734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9650663,0.0003112617,0.02866113,0.0003331469,0.00004637495,0.00005063714,0.0006034632,0.001404665,0.003522982],"genre_scores_gemma":[0.9909113,0.0000677481,0.007304361,0.00004242945,0.000004396389,0.00001112113,0.0006755664,0.00005683403,0.0009263062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4550411,"threshold_uncertainty_score":0.9154418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04260812803956852,"score_gpt":0.26297101356198,"score_spread":0.2203628855224115,"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."}}