{"id":"W4287833264","doi":"10.5194/isprs-archives-xlvi-m-2-2022-203-2022","title":"AUTOMATED RECOGNITION OF PERMAFROST DISTURBANCES USING HIGH-SPATIAL RESOLUTION SATELLITE IMAGERY AND DEEP LEARNING MODELS","year":2022,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Minnesota; National Science Foundation","keywords":"Permafrost; Satellite imagery; Landform; Computer science; Arctic; Deep learning; Artificial intelligence; Remote sensing; Satellite; Convolutional neural network; Environmental science; Physical geography; Climatology; Cartography; Geology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004020025,0.0008992734,0.0003335327,0.001381078,0.000229559,0.0006771152,0.000660682,0.0005196597,0.001065121],"category_scores_gemma":[0.0007610647,0.0002651577,0.0006137117,0.0008324522,0.0001976907,0.0007560314,0.0004830749,0.0006807733,0.00055121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008589613,"about_ca_system_score_gemma":0.0008929567,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03983213,"about_ca_topic_score_gemma":0.0567865,"domain_scores_codex":[0.9998135,0.00002422524,0.000009212446,0.00006579674,0.00004771178,0.00003969306],"domain_scores_gemma":[0.9996804,0.00006587996,0.00005227313,0.00004193504,0.0001281298,0.00003134718],"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":[0.0004334897,0.000461438,0.05472808,0.0002519642,0.0004081802,0.0003385595,0.0001041962,0.4545031,0.03547662,0.0008853134,0.01401352,0.4383955],"study_design_scores_gemma":[0.000007241602,0.00002479219,0.008914827,0.00001498366,0.00001852812,0.00002128226,0.00003780783,0.9851751,0.004868456,0.0003255012,0.0005838068,0.000007640608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8260216,0.002017294,0.1457941,0.0008053295,0.0002663273,0.0001858204,0.006004347,0.01005075,0.008854482],"genre_scores_gemma":[0.9439347,0.0002947505,0.04774289,0.0001269608,0.00003498518,0.00003463367,0.005479779,0.00007234258,0.002278995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03983213,"threshold_uncertainty_score":0.07920051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03398629179190918,"score_gpt":0.246799751564126,"score_spread":0.2128134597722168,"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."}}