{"id":"W4321601528","doi":"10.3390/rs15051226","title":"Automated Identification of Thermokarst Lakes Using Machine Learning in the Ice-Rich Permafrost Landscape of Central Yakutia (Eastern Siberia)","year":2023,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"Université Paris-Saclay; Agence Nationale de la Recherche","keywords":"Thermokarst; Permafrost; Arctic; Physical geography; Geology; Tundra; Precipitation; Holocene; Environmental science; Oceanography; Geography; Meteorology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000567065,0.0001147257,0.0001945842,0.0001593006,0.0001131285,0.00004693913,0.0001270032,0.00006221805,0.0001201416],"category_scores_gemma":[0.00005495984,0.00008750272,0.00005154204,0.0006965497,0.00005531473,0.0001028014,0.00001491467,0.0001383663,0.00003203599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004421779,"about_ca_system_score_gemma":0.00002403185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002558269,"about_ca_topic_score_gemma":0.007787467,"domain_scores_codex":[0.998733,0.0001959751,0.0003567679,0.0001747153,0.0002483079,0.0002911844],"domain_scores_gemma":[0.9993607,0.0001867748,0.0002055425,0.000172496,0.00004246262,0.00003203147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005600725,0.00001095625,0.6430866,0.0001376565,0.00002139875,0.00004618582,0.01099622,0.02448785,0.3091237,0.000001173771,0.00003106831,0.01200129],"study_design_scores_gemma":[0.0001271139,0.00001408363,0.3106556,0.00006339238,0.00001362346,0.00002259269,0.001229073,0.6869624,0.0008118757,0.00001234403,0.00002093056,0.00006699421],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985214,0.000261471,0.00002923559,0.0001211445,0.0001921579,0.0001234873,0.000347645,0.00007537177,0.0003281222],"genre_scores_gemma":[0.9982875,0.000110565,0.00004737577,0.0000292057,0.0000703071,3.840734e-9,0.001413639,0.000007033361,0.00003437647],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6624745,"threshold_uncertainty_score":0.434559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04156887596458405,"score_gpt":0.2635609157917952,"score_spread":0.2219920398272111,"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."}}