{"id":"W1565635109","doi":"10.3390/rs70708489","title":"On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping","year":2015,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":596,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Computer science; Class (philosophy); Contextual image classification; Set (abstract data type); Data set; Spatial analysis; Artificial intelligence; Pattern recognition (psychology); Feature selection; Data mining; Remote sensing; Statistics; Image (mathematics); Mathematics; Geography","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":[0.001711725,0.0001149667,0.0001980747,0.00007750143,0.000107182,0.00003747395,0.0001512338,0.00004122563,0.000004632312],"category_scores_gemma":[0.0004197588,0.00009176852,0.00002108145,0.0006127255,0.00005189242,0.0001203435,0.00008298086,0.0001851537,0.000009697103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002128365,"about_ca_system_score_gemma":0.00004092897,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006474945,"about_ca_topic_score_gemma":0.06095012,"domain_scores_codex":[0.9985337,0.0002570748,0.0003974952,0.0003802479,0.0002347911,0.0001966644],"domain_scores_gemma":[0.9988139,0.0004134475,0.0001699838,0.0005344775,0.00001659435,0.00005158634],"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":[0.0006200405,0.0008822598,0.3626714,0.00009860312,0.0001129996,0.002281289,0.1381908,0.06964637,0.03640052,0.0002020804,0.001837768,0.3870559],"study_design_scores_gemma":[0.001154674,0.00003805678,0.01566391,0.00007788963,0.00000992555,0.0005677104,0.02403815,0.9576072,0.00004176726,0.0004374816,0.0002343744,0.0001288932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822368,0.000006140612,0.01469284,0.0002817774,0.00003108721,0.0005997184,0.000004444083,0.00002192835,0.002125255],"genre_scores_gemma":[0.9918444,0.000001443989,0.008055664,0.00002979544,0.00003260991,8.20589e-8,0.00001192059,0.00001362179,0.00001045042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8879608,"threshold_uncertainty_score":0.9788224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1119004036964485,"score_gpt":0.3030058956641651,"score_spread":0.1911054919677166,"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."}}