{"id":"W2057582245","doi":"10.1016/j.rse.2012.07.005","title":"Detecting rock glacier flow structures using Gabor filters and IKONOS imagery","year":2012,"lang":"en","type":"article","venue":"Remote Sensing of Environment","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":55,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; International Development Research Centre","keywords":"Terrain; Receiver operating characteristic; Geology; Support vector machine; Artificial intelligence; Random forest; Glacier; Pattern recognition (psychology); Remote sensing; Rock glacier; Texture (cosmology); Gabor filter; Elevation (ballistics); Computer science; Geomorphology; Feature extraction; Mathematics; Cartography; Image (mathematics); Geography; Geometry; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001661699,0.0001338017,0.0001612699,0.00005065546,0.0001297222,0.0000224554,0.00003910756,0.00005530218,0.0007072908],"category_scores_gemma":[0.00001730094,0.0001179376,0.00004260267,0.00004168804,0.00005756073,0.0001368216,0.00002236699,0.00008971156,0.0000244417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001063246,"about_ca_system_score_gemma":0.000005336216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001216027,"about_ca_topic_score_gemma":0.0001162128,"domain_scores_codex":[0.9991325,0.00004548814,0.0001741149,0.0001647862,0.0001642561,0.0003188362],"domain_scores_gemma":[0.9995421,0.00008836446,0.00009200112,0.0001504742,0.000004329277,0.0001227512],"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":[0.00007440714,0.00001359404,0.2020594,0.0001251908,0.00005656815,0.00002427384,0.003147074,0.02305269,0.1448556,4.475473e-7,0.00006625482,0.6265244],"study_design_scores_gemma":[0.0003123683,0.00006589598,0.4481994,0.00008218944,0.00007478761,0.000195282,0.0007690602,0.5300962,0.01794305,0.00008030688,0.001784718,0.0003967215],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969406,0.0009696693,0.001459525,0.00003310108,0.0002268891,0.00008135769,0.00008423408,0.000009472975,0.000195206],"genre_scores_gemma":[0.9825424,0.0001692095,0.01689767,0.0001012268,0.0002118176,3.511307e-9,0.00004891212,0.000006601126,0.00002217876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6261277,"threshold_uncertainty_score":0.7744338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03329147924264924,"score_gpt":0.2250859986345272,"score_spread":0.191794519391878,"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."}}