{"id":"W2000299034","doi":"10.1080/01431160310001642296","title":"Contextual classification of Landsat TM images to forest inventory cover types","year":2004,"lang":"en","type":"article","venue":"International Journal of Remote Sensing","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Smoothing; Random forest; Spatial contextual awareness; Pattern recognition (psychology); Pixel; Spatial analysis; Computer science; Classifier (UML); Statistics; Land cover; Remote sensing; Artificial intelligence; Mathematics; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002406688,0.0001037033,0.000158784,0.00009592629,0.00003090151,0.00003858261,0.0002369043,0.00005869453,0.00003620137],"category_scores_gemma":[0.0002443581,0.00008111296,0.0001001422,0.0001242455,0.00009335251,0.0002073573,0.00007507043,0.0001581259,0.0000978649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003799516,"about_ca_system_score_gemma":0.00003082229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002578808,"about_ca_topic_score_gemma":0.0001562776,"domain_scores_codex":[0.9986604,0.00003525646,0.000392184,0.0001270866,0.0006647086,0.0001202906],"domain_scores_gemma":[0.9991533,0.0000411966,0.000399709,0.0001047889,0.0002113139,0.00008974368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002885136,0.00008714201,0.00537423,0.000008104445,0.000175141,0.0002866166,0.001857058,0.09950702,0.669193,0.0001093026,0.006509616,0.2166042],"study_design_scores_gemma":[0.006036137,0.0009185983,0.6142223,0.002091717,0.0002001292,0.00675923,0.001476743,0.0356894,0.2331804,0.01188473,0.08638088,0.001159668],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9664762,0.00002953923,0.02536042,0.002421433,0.0008025776,0.00007027484,0.000002853187,0.000009683037,0.004826994],"genre_scores_gemma":[0.965274,0.00001800249,0.03392676,0.0003078449,0.0002610573,3.316493e-9,0.000003040172,0.00001023333,0.0001990543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6088482,"threshold_uncertainty_score":0.3307691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01361122644622987,"score_gpt":0.2542831986349662,"score_spread":0.2406719721887364,"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."}}