{"id":"W2802920593","doi":"10.1016/j.isprsjprs.2018.03.026","title":"Mapping permafrost landscape features using object-based image classification of multi-temporal SAR images","year":2018,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de la Recherche Scientifique; Center for Northern Studies","funders":"Bayerische Forschungsallianz","keywords":"Permafrost; Thermokarst; Remote sensing; Arctic; Land cover; Synthetic aperture radar; Vegetation (pathology); Physical geography; Satellite imagery; Geology; Environmental science; Land use; Geography; Ecology","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":[0.0006401655,0.000190388,0.0003567968,0.0003858207,0.0002566324,0.0001199999,0.0001152372,0.0001222505,0.0001741255],"category_scores_gemma":[0.00008510417,0.0001487763,0.0001458602,0.0004135908,0.0003211316,0.0002303026,0.00001297654,0.0002689354,0.000003781244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007477534,"about_ca_system_score_gemma":0.00006827592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003648134,"about_ca_topic_score_gemma":0.002787115,"domain_scores_codex":[0.9986041,0.0001382146,0.0004886835,0.000189953,0.0002806355,0.0002983935],"domain_scores_gemma":[0.9986755,0.0001500563,0.0005478406,0.0001445713,0.0003230166,0.000159008],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002710304,0.00003072384,0.1366712,0.0001488912,0.00005663966,0.0001189433,0.001531774,0.00003172705,0.7204173,1.828439e-7,0.0001619624,0.1405596],"study_design_scores_gemma":[0.00213902,0.0005600604,0.4966251,0.0009160259,0.0001360657,0.001684007,0.00667444,0.3697858,0.1196251,0.00006427208,0.001246717,0.0005434563],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746919,0.001704588,0.02231897,0.0001084242,0.0005220548,0.0001069102,0.0002828006,0.00001201125,0.0002523369],"genre_scores_gemma":[0.9602253,0.0001448331,0.0388919,0.0001327757,0.0004647167,2.049504e-9,0.0001181025,0.000009238599,0.00001308639],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6007922,"threshold_uncertainty_score":0.6066921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04290707876221269,"score_gpt":0.2823867283843765,"score_spread":0.2394796496221638,"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."}}