{"id":"W4388797021","doi":"10.3389/fevo.2023.1270857","title":"Surveying wildlife and livestock in Uganda with aerial cameras: Deep Learning reduces the workload of human interpretation by over 70%","year":2023,"lang":"en","type":"article","venue":"Frontiers in Ecology and Evolution","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Sherbrooke","funders":"Fonds pour la Formation à la Recherche dans l’Industrie et dans l’Agriculture; Fonds De La Recherche Scientifique - FNRS","keywords":"Wildlife; Workload; Artificial intelligence; Computer science; Aerial survey; Situation awareness; Footprint; Aerial imagery; Computer vision; Geography; Environmental resource management; Remote sensing; Ecology; Environmental science; Archaeology; Engineering; Biology","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":[0.0005369616,0.00007142915,0.000126649,0.00007461428,0.0001705786,0.000007050877,0.00005580283,0.0001104076,0.00001633325],"category_scores_gemma":[0.00009160475,0.0000601093,0.000008346684,0.0002540653,0.0003733939,0.0001942402,0.00004853564,0.0001704011,0.000002064443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009115765,"about_ca_system_score_gemma":0.000009240453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003762141,"about_ca_topic_score_gemma":0.003132005,"domain_scores_codex":[0.9991798,0.0002587876,0.000162164,0.0001831849,0.00005706986,0.0001590375],"domain_scores_gemma":[0.9997367,0.00009926131,0.00009305316,0.00004842493,0.00000423272,0.00001832507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000127854,0.00001641986,0.9928664,0.000003652189,0.000007876555,9.85028e-7,0.001570533,0.001922932,0.0002970439,0.00001046724,0.001460927,0.001714918],"study_design_scores_gemma":[0.0004462325,0.0001595076,0.9880648,0.00002018052,0.00000749263,0.000001679125,0.001324519,0.009327868,0.00001636518,0.0005387596,0.00002677935,0.00006583882],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9988307,0.0001529912,0.0002715395,0.0002970976,0.0001926111,0.0001531085,9.846815e-7,0.00001277038,0.00008818445],"genre_scores_gemma":[0.9995677,0.0001054989,0.0001026932,0.00008304117,0.0000122608,0.00002936504,0.0000116529,0.000004363914,0.0000833588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007404936,"threshold_uncertainty_score":0.2451186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004711241555657272,"score_gpt":0.207041722357125,"score_spread":0.2023304808014677,"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."}}