{"id":"W2147478967","doi":"10.1659/mrd-journal-d-12-00011.1","title":"Improving the Accuracy of Vegetation Classifications in Mountainous Areas","year":2013,"lang":"en","type":"article","venue":"Mountain Research and Development","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Ministerio de Ciencia e Innovación","keywords":"Thematic Mapper; Random forest; Thematic map; Vegetation (pathology); Remote sensing; Ancillary data; Computer science; Environmental science; Cartography; Geography; Satellite imagery; Artificial intelligence","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":[0.0008115286,0.000077081,0.00007653992,0.00006240405,0.0002319787,0.00007744017,0.0001905295,0.00004672751,0.00009164749],"category_scores_gemma":[0.0002766353,0.00004707061,0.000008658632,0.0003765479,0.000260644,0.0001735357,0.0001984058,0.0002185837,0.0001872636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003259682,"about_ca_system_score_gemma":0.0000605133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002845281,"about_ca_topic_score_gemma":0.0009336324,"domain_scores_codex":[0.9986455,0.0001119334,0.0002212945,0.0002146667,0.0005031181,0.0003034599],"domain_scores_gemma":[0.9993477,0.0002876227,0.00005588174,0.0001813418,0.00005898535,0.0000684561],"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":[0.00003200795,0.0003809424,0.3024791,0.0001019844,0.00002414252,0.00001022534,0.01721505,0.001022827,0.229439,0.001161443,0.005147505,0.4429857],"study_design_scores_gemma":[0.0001396888,0.00002608255,0.9870933,0.00002025863,5.551301e-7,0.000004857413,0.001983128,0.001649676,0.005735051,0.0008161955,0.002453988,0.00007718641],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9947703,0.00006315183,0.0002496288,0.0008939706,0.00001621739,0.0005638056,2.442202e-7,0.000009459256,0.003433154],"genre_scores_gemma":[0.9954683,0.00002249488,0.004025872,0.00004998152,0.000009650325,0.00003898848,0.000005464851,0.000005240326,0.0003740536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6846142,"threshold_uncertainty_score":0.4301233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03867402581085289,"score_gpt":0.2898924991394962,"score_spread":0.2512184733286433,"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."}}