{"id":"W2150219928","doi":"10.1139/cjfr-2013-0401","title":"Mapping attributes of Canada’s forests at moderate resolution through <i>k</i>NN and MODIS imagery","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Forest Research","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":319,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Forest Service; Natural Resources Canada","funders":"Canadian Forest Service; Natural Resources Canada; U.S. Forest Service","keywords":"Forest inventory; Scale (ratio); Sampling (signal processing); Remote sensing; Land cover; Environmental science; Biomass (ecology); Geospatial analysis; Pixel; Forestry; Physical geography; Data set; Cartography; Geography; Forest management; Land use; Statistics; Ecology; Computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004357807,0.0004852541,0.0002879287,0.004330248,0.001382666,0.001674292,0.0006348293,0.0002173941,0.005999073],"category_scores_gemma":[0.001344073,0.0002677132,0.0004401936,0.009029666,0.000379836,0.0005227639,0.0007434509,0.0005072651,0.001210207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01019861,"about_ca_system_score_gemma":0.02021717,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9888404,"about_ca_topic_score_gemma":0.9954033,"domain_scores_codex":[0.9993081,0.00002856144,0.00003022105,0.0001024377,0.0003815909,0.0001490999],"domain_scores_gemma":[0.9984471,0.00007749425,0.000129853,0.0001032508,0.00110686,0.0001354699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002280956,0.0001450882,0.3904937,0.000891327,0.0003011804,0.0005028684,0.002634405,0.02746179,0.009285513,0.00876278,0.2686425,0.2906508],"study_design_scores_gemma":[0.00001863275,0.000009563077,0.8578263,0.0001534557,0.0000444941,0.0001151947,0.001288235,0.01332949,0.001609206,0.0009924085,0.1245237,0.00008924455],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2546273,0.001479131,0.01544717,0.000798448,0.00006670599,0.0003334869,0.6484634,0.001929919,0.07685441],"genre_scores_gemma":[0.6697598,0.001408228,0.04746734,0.0002129499,0.00002641594,0.0002775804,0.2588688,0.0005015697,0.0214772],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0111596,"threshold_uncertainty_score":0.07399642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03773142670803336,"score_gpt":0.2674499475745917,"score_spread":0.2297185208665583,"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."}}