{"id":"W4319828669","doi":"10.1080/07011784.2022.2160660","title":"Performance of automated geoprocessing methods for culvert detection in remote Forest environments","year":2023,"lang":"en","type":"article","venue":"Canadian Water Resources Journal / Revue canadienne des ressources hydriques","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Culvert; Geoprocessing; Digital elevation model; Remote sensing; Geocoding; Levee; Computer science; Hydrology (agriculture); Environmental science; Geology; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002155601,0.0009625042,0.0008624931,0.002369865,0.000377743,0.001301168,0.001071252,0.0006380205,0.001489788],"category_scores_gemma":[0.005646528,0.0003732045,0.0004660213,0.001393455,0.0003244989,0.0008884921,0.0005920291,0.0002477631,0.000687454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005443321,"about_ca_system_score_gemma":0.0006967816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0116021,"about_ca_topic_score_gemma":0.008682366,"domain_scores_codex":[0.9986026,0.0003072813,0.0001387353,0.0004760268,0.0003620555,0.0001134241],"domain_scores_gemma":[0.9948404,0.0030352,0.0003952833,0.0004792977,0.001126052,0.0001237886],"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":[0.005072762,0.0007071621,0.05051548,0.0003296161,0.000310639,0.0003997078,0.0007327624,0.1025745,0.05649867,0.0007108506,0.002921003,0.7792269],"study_design_scores_gemma":[0.000263906,0.0010103,0.09369128,0.00004697193,0.0001609644,0.0003786872,0.0003366786,0.8360329,0.06430492,0.0007475387,0.0029159,0.0001099182],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.908277,0.0003688642,0.08427686,0.00005055191,0.00004089682,0.0001683088,0.0005590459,0.004644412,0.001614039],"genre_scores_gemma":[0.8337178,0.00014994,0.1636054,0.0000411408,0.00001623159,0.00009341951,0.001245491,0.0002000031,0.0009305277],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0116021,"threshold_uncertainty_score":0.02306914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01453092465659763,"score_gpt":0.2455620753165775,"score_spread":0.2310311506599799,"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."}}