{"id":"W2901098095","doi":"10.4095/297517","title":"Influence of sample distribution and prior probability adjustment on land cover classification","year":2016,"lang":"en","type":"report","venue":"","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Land cover; Cover (algebra); Sample (material); Distribution (mathematics); Environmental science; Statistics; Probability distribution; Geography; Physical geography; Mathematics; Land use; Ecology; Biology; Engineering; Physics","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":[0.0003674717,0.0002377489,0.0003153055,0.00006387196,0.00003084732,0.00002161715,0.00008369421,0.0002801374,0.00001992882],"category_scores_gemma":[0.0008257592,0.000184287,0.00005117981,0.00009308445,0.0001033246,0.0001116961,0.00002410657,0.0001679993,0.00002480079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008245078,"about_ca_system_score_gemma":0.0001653867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000847616,"about_ca_topic_score_gemma":0.00001322284,"domain_scores_codex":[0.9984789,0.00003653804,0.0004935559,0.0003529971,0.0004674239,0.0001705297],"domain_scores_gemma":[0.9985014,0.0002276805,0.000214513,0.000572326,0.0004212309,0.00006289662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002375498,0.0005659753,0.0527082,0.01066777,0.0006169021,0.000005305174,0.0002403868,0.04398443,0.07374185,0.002190376,0.0527789,0.7622623],"study_design_scores_gemma":[0.0003432168,0.00007776028,0.9294618,0.0006343819,0.00008666322,0.00001079432,0.000002947244,0.01002149,0.006772103,0.0004353644,0.05173749,0.0004160161],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388449,0.0003421228,0.03964483,0.0001909786,0.000591822,0.001735768,0.001159722,0.0005044254,0.01698541],"genre_scores_gemma":[0.9963537,0.001323182,0.0009700259,0.000005809861,0.0001209837,0.00002200025,0.0005761721,0.00004105314,0.0005870981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8767536,"threshold_uncertainty_score":0.7515006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03717087840950935,"score_gpt":0.2684320110992333,"score_spread":0.2312611326897239,"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."}}