{"id":"W2914396090","doi":"10.1016/j.compenvurbsys.2019.01.007","title":"Classification of impervious land-use features using object-based image analysis and data fusion","year":2019,"lang":"en","type":"article","venue":"Computers Environment and Urban Systems","topic":"Land Use and Ecosystem Services","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Impervious surface; Watershed; Land cover; Land use; Urbanization; Computer science; Environmental science; Remote sensing; Workflow; Data mining; Geography; Machine learning; Database; Civil engineering; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002324915,0.0001487292,0.0002915023,0.00007272328,0.00007805665,0.00009478195,0.0002293947,0.00006966009,0.00005738542],"category_scores_gemma":[0.000001417538,0.0001158374,0.00003818777,0.000135717,0.00003571646,0.0003288496,0.0003429749,0.00004961852,0.00002237148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004455008,"about_ca_system_score_gemma":0.000003542914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001366807,"about_ca_topic_score_gemma":0.00006246982,"domain_scores_codex":[0.998827,0.00008015638,0.0002468976,0.0004672438,0.0002211877,0.000157489],"domain_scores_gemma":[0.9990466,0.00006117918,0.0001827514,0.000627341,0.00000249387,0.00007964716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001514653,0.00003000794,0.9858868,0.00008392934,0.00007142212,0.000001599685,0.0001267247,0.003216834,0.01012728,0.000002055496,0.0002202238,0.0002179545],"study_design_scores_gemma":[0.0003185036,0.00003775994,0.608053,0.00003549265,0.0001568123,0.000003594898,0.00004802902,0.3902534,0.0001041315,8.240224e-7,0.0008562728,0.0001321519],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996793,0.0004417268,0.002230067,0.0000192796,0.0001113593,0.0002796399,0.00005031739,0.00001558349,0.00005902814],"genre_scores_gemma":[0.998849,0.00007960597,0.0008109842,0.00002297495,0.00003090937,0.000002629106,0.0001485409,0.00001023408,0.00004509405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3870365,"threshold_uncertainty_score":0.4723714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01743906079876563,"score_gpt":0.2155856142747997,"score_spread":0.1981465534760341,"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."}}