{"id":"W2769774644","doi":"10.3390/rs9111193","title":"Developing a Random Forest Algorithm for MODIS Global Burned Area Classification","year":2017,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universidad de Alcalá; European Space Agency","keywords":"Random forest; Remote sensing; Environmental science; Boreal; Taiga; Bidirectional reflectance distribution function; Pixel; Vegetation (pathology); Temperate rainforest; Algorithm; Computer science; Forestry; Geography; Reflectivity; Artificial intelligence; Ecosystem; Ecology; Physics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004316479,0.0001518992,0.0002057388,0.00001469551,0.0006465105,0.0001863542,0.0002186277,0.00009183623,0.000007346096],"category_scores_gemma":[0.0002928623,0.0001438193,0.0000808957,0.00006105553,0.00009524888,0.0002452455,0.000108681,0.00005770842,0.000139558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005751171,"about_ca_system_score_gemma":0.00001670152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001086023,"about_ca_topic_score_gemma":0.0007225325,"domain_scores_codex":[0.9988452,0.00004596154,0.0002116975,0.0003559717,0.0002172299,0.0003239661],"domain_scores_gemma":[0.9990632,0.0000898415,0.0002379864,0.00050958,0.00001998337,0.00007943373],"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":[0.0000251733,0.000004432986,0.0007170806,0.00001372757,0.00001191557,0.000008199586,0.00004846259,0.0001312095,0.002856319,0.00002694902,0.0002481003,0.9959084],"study_design_scores_gemma":[0.001106295,0.00001823396,0.0182147,0.00009274219,0.00001544165,0.00004150119,0.00002174014,0.9760469,0.0006152203,0.001499137,0.00213599,0.0001921127],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.277171,0.00001015256,0.7174925,0.0004924583,0.0003612778,0.0005308161,0.000006477007,0.00005338496,0.003881916],"genre_scores_gemma":[0.8108841,0.000004277973,0.1887855,0.00006364917,0.0001061471,1.801127e-7,0.000009216415,0.0000152204,0.0001316684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9957163,"threshold_uncertainty_score":0.5864781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03457994931679056,"score_gpt":0.2777452618132995,"score_spread":0.2431653124965089,"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."}}