{"id":"W1992024126","doi":"10.1007/s10661-015-4489-3","title":"Land cover mapping based on random forest classification of multitemporal spectral and thermal images","year":2015,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":120,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"U.S. Geological Survey","keywords":"Random forest; Land cover; Remote sensing; Thematic map; Environmental science; Change detection; Thematic Mapper; Contextual image classification; Land use; Spectral bands; Satellite imagery; Computer science; Geography; Cartography; Artificial intelligence; Image (mathematics)","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":[0.0001501857,0.0001281906,0.0001321645,0.00005488398,0.00004019404,0.000037321,0.0000357678,0.0000430142,0.000002501814],"category_scores_gemma":[0.000006445845,0.0001220715,0.00002121135,0.00002838345,0.00006737629,0.0001119588,0.00001523231,0.0001143831,0.000002918833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001304444,"about_ca_system_score_gemma":0.000007813642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008683599,"about_ca_topic_score_gemma":1.911171e-7,"domain_scores_codex":[0.9993358,0.00003268109,0.0001640795,0.0001592218,0.0001861596,0.0001220545],"domain_scores_gemma":[0.9996802,0.00005073409,0.00005014473,0.0001376055,0.000003987539,0.00007738331],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000352098,0.00006506131,0.6975472,0.00003723828,0.00002028889,0.000003908173,0.0001490491,0.02787662,0.2647353,0.000006970169,0.00002617085,0.009496983],"study_design_scores_gemma":[0.001152983,0.00005057465,0.7703892,0.00003985828,0.000009838414,0.000001576316,0.0001472003,0.2141529,0.01375264,0.000007409367,0.0001906856,0.0001051301],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940057,0.0001149712,0.004404785,0.00006297341,0.0002066089,0.0001474966,0.000008065931,0.00004706536,0.00100237],"genre_scores_gemma":[0.9932174,0.00004021778,0.00655825,0.000002477778,0.0001007838,0.000006157401,0.00001718583,0.000021407,0.00003608247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2509826,"threshold_uncertainty_score":0.4977931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02433679457589763,"score_gpt":0.2469573695910722,"score_spread":0.2226205750151746,"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."}}