{"id":"W3210959000","doi":"10.3390/rs13214294","title":"Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps","year":2021,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Helmholtz-Gemeinschaft; Brandenburger Staatsministerium für Wissenschaft, Forschung und Kultur; European Space Agency; National Science Foundation","keywords":"Permafrost; Arctic; Physical geography; Transferability; Geology; Environmental science; Remote sensing; Computer science; Machine learning; Oceanography; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002750769,0.0001406787,0.0001985151,0.00006144377,0.0004891358,0.0001632711,0.00004377146,0.00007733894,0.00003784178],"category_scores_gemma":[0.0003946286,0.0001375968,0.00004100213,0.0002941198,0.00004362059,0.0001104714,0.00002645255,0.0001741438,0.000006168269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007536693,"about_ca_system_score_gemma":0.00004485453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003875475,"about_ca_topic_score_gemma":0.0007675201,"domain_scores_codex":[0.9988963,0.00006961636,0.000180025,0.0003439639,0.0001265324,0.0003835747],"domain_scores_gemma":[0.9991984,0.0004059178,0.00009077843,0.00009746714,0.0001230116,0.00008444073],"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":[0.00001398236,0.000001947107,0.07317252,0.0002422982,0.00002807929,0.0001199204,0.001983918,0.001358569,0.004745355,0.00001088824,0.00002052699,0.918302],"study_design_scores_gemma":[0.0002333342,0.00002481925,0.0185861,0.0002242693,0.00001759832,0.0004703747,0.003682949,0.9745204,0.0005114112,0.000312832,0.001156206,0.0002597113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8660619,0.003407758,0.1199035,0.0003091755,0.000233151,0.0002261676,0.00005150096,0.0001082592,0.00969857],"genre_scores_gemma":[0.5869257,0.0001977159,0.4109414,0.0003772179,0.0005090018,1.574972e-8,0.0009243209,0.00001464351,0.0001099451],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9731618,"threshold_uncertainty_score":0.5611033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08744869101697116,"score_gpt":0.2598352129646498,"score_spread":0.1723865219476787,"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."}}