{"id":"W3048911062","doi":"10.3233/sji-200663","title":"The use of combined Landsat and Radarsat data for urban ecosystem accounting in Canada","year":2020,"lang":"en","type":"article","venue":"Statistical Journal of the IAOS","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada","funders":"Canadian Space Agency; Strong","keywords":"Urban ecosystem; Remote sensing; Environmental resource management; Random forest; Ecosystem; Geospatial analysis; Environmental science; Ecosystem services; Geography; Impervious surface; Cartography; Urban planning; Computer science; Ecology; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002861543,0.00005348624,0.0001508403,0.000004050354,0.00007410274,0.00003579103,0.0004378042,0.00001264055,0.00002883038],"category_scores_gemma":[0.0002340555,0.00002522987,0.00001434582,0.00005615364,0.00001360099,0.0001472734,0.0002191273,0.00007968806,8.053483e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005908687,"about_ca_system_score_gemma":0.00008453109,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0825312,"about_ca_topic_score_gemma":0.6798446,"domain_scores_codex":[0.9992015,0.00006117635,0.0003185389,0.00007904888,0.0002186517,0.0001210728],"domain_scores_gemma":[0.9988737,0.0006990453,0.0002008388,0.0001506285,0.00001027112,0.0000655741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004606719,0.00002760017,0.9372971,0.0002570779,0.00008121412,0.00003312394,0.0003911322,0.001543542,0.0002980564,0.0003761334,0.05447935,0.004755002],"study_design_scores_gemma":[0.003811567,0.000368244,0.3464599,0.0004027659,0.0002097429,0.0000816211,0.001196308,0.4732975,0.0005465603,0.001425756,0.1718397,0.0003603007],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952247,0.00005930034,0.0006464726,0.003235481,0.0001668048,0.0001587516,0.0004911298,9.976569e-7,0.00001640149],"genre_scores_gemma":[0.9989648,0.00001633609,0.000747635,0.0002253308,0.00003614183,3.146383e-7,0.000002838388,0.000004307895,0.000002252579],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5973134,"threshold_uncertainty_score":0.9235783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03646710907137764,"score_gpt":0.2218114943780896,"score_spread":0.185344385306712,"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."}}