{"id":"W4213443330","doi":"10.1139/cjes-2021-0117","title":"Permafrost thaw sensitivity prediction using surficial geology, topography, and remote-sensing imagery: a data-driven neural network approach","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Earth Sciences","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Geological Survey of Canada; Natural Resources Canada","funders":"Natural Resources Canada; Nunavut Arctic College","keywords":"Permafrost; Geology; Sensitivity (control systems); Terrain; Remote sensing; Cartography; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0003463089,0.0006050175,0.0003707227,0.0005008462,0.0002270596,0.0005113225,0.0006486854,0.0007082516,0.0004516362],"category_scores_gemma":[0.0008405741,0.0003303045,0.0003240603,0.0003100602,0.0002398588,0.0003809498,0.0002736606,0.0004887205,0.00008167759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016734,"about_ca_system_score_gemma":0.0006872074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02283805,"about_ca_topic_score_gemma":0.02862187,"domain_scores_codex":[0.9999239,0.00001427586,0.000003891483,0.00002690042,0.00001200864,0.0000189098],"domain_scores_gemma":[0.999739,0.0001219477,0.0000337422,0.00001195273,0.00007054504,0.00002278763],"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":[0.00009547926,0.0001976666,0.01423603,0.00001543579,0.0000495716,0.00006379078,0.00002689384,0.9493921,0.002577366,0.0001460886,0.0003024594,0.0328972],"study_design_scores_gemma":[0.000001646798,0.000006080827,0.0007346898,7.259042e-7,0.000001765146,0.00000128324,0.000003938395,0.9989719,0.0002072549,0.00005996172,0.000009598184,0.000001121851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423608,0.0001300956,0.05564236,0.0002286472,0.0000180085,0.00005211898,0.0002352676,0.0003150064,0.001017731],"genre_scores_gemma":[0.9872938,0.00002918568,0.01168991,0.00003903383,0.00001223972,0.00003325,0.0002815278,0.000008378919,0.0006127551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02283805,"threshold_uncertainty_score":0.04541028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07255783072271008,"score_gpt":0.247212891215428,"score_spread":0.1746550604927179,"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."}}