{"id":"W1983218766","doi":"10.5558/tfc84221-2","title":"Towards automated segmentation of forest inventory polygons on high spatial resolution satellite imagery","year":2008,"lang":"en","type":"article","venue":"The Forestry Chronicle","topic":"Remote Sensing and LiDAR Applications","field":"Environmental Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Sport Centre Pacific; Natural Resources Canada; University of Calgary; Island Health","funders":"Canadian Forest Service; Natural Sciences and Engineering Research Council of Canada; U.S. Forest Service; University of Calgary","keywords":"Panchromatic film; Automation; Satellite imagery; Computer science; Segmentation; Pixel; Remote sensing; Forest inventory; Satellite; Key (lock); Image resolution; Geospatial analysis; Spatial analysis; Artificial intelligence; Computer vision; Geography; Forest management; Forestry; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"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":[0.001934374,0.0007866683,0.000756382,0.002496873,0.0006929411,0.002807214,0.001335066,0.001046495,0.001443057],"category_scores_gemma":[0.004372158,0.0006298507,0.0006704556,0.001951282,0.0008235356,0.001452849,0.0009155418,0.0008010932,0.001636447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005580934,"about_ca_system_score_gemma":0.001300208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004768732,"about_ca_topic_score_gemma":0.008171855,"domain_scores_codex":[0.9987609,0.0003960828,0.00008172369,0.0002011642,0.0004898934,0.00007026121],"domain_scores_gemma":[0.9967462,0.001689605,0.0002819341,0.0005277341,0.0007040738,0.00005052593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002542674,0.0001845382,0.005875566,0.0004555164,0.00008889404,0.0003369759,0.001279839,0.09380574,0.1062052,0.007408672,0.005015282,0.7790895],"study_design_scores_gemma":[0.00007802578,0.0001852539,0.01343138,0.0001173293,0.00007067128,0.0006657559,0.0008277395,0.8786433,0.07378397,0.01212635,0.01999679,0.00007342164],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02776615,0.0001700896,0.9678504,0.000101793,0.00001290919,0.0001653754,0.0001484162,0.002303252,0.00148167],"genre_scores_gemma":[0.04835105,0.0001800257,0.9502562,0.00004301408,0.00001697751,0.00006160454,0.0004107172,0.0001658824,0.0005144566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004768732,"threshold_uncertainty_score":0.01023012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01481362525732691,"score_gpt":0.2409515625523983,"score_spread":0.2261379372950714,"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."}}