{"id":"W4387803799","doi":"10.1109/igarss52108.2023.10281408","title":"The Influence of Input Image Scale on Deep Learning-Based Beluga Whale Detection from Aerial Remote Sensing Imagery","year":2023,"lang":"en","type":"article","venue":"","topic":"Water Quality Monitoring Technologies","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Beluga Whale; Remote sensing; Aerial imagery; Whale; Scale (ratio); Aerial image; Artificial intelligence; Aerial survey; Computer science; Geology; Image (mathematics); Computer vision; Geography; Cartography; Oceanography; Fishery","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":[0.0004803829,0.0001257405,0.0001227496,0.00004149287,0.0003000208,0.00006518363,0.0002786067,0.00009335735,0.00002626362],"category_scores_gemma":[0.0004920221,0.00009449737,0.00005157679,0.0004001918,0.0004558877,0.000160176,0.0002973208,0.0002336789,0.0005377898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001206124,"about_ca_system_score_gemma":0.000005217011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004157387,"about_ca_topic_score_gemma":0.0004478108,"domain_scores_codex":[0.9987049,0.0001331904,0.0002339726,0.000297639,0.0003512799,0.0002789953],"domain_scores_gemma":[0.99902,0.0003810297,0.0001106218,0.0004412866,0.00001399596,0.00003307719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006579282,0.00001042287,0.002940751,0.000004902352,0.000005981979,0.000007692454,0.0001861398,0.0565781,0.8569491,8.636657e-7,0.0000898838,0.08316036],"study_design_scores_gemma":[0.0001730106,0.00008230087,0.08590837,0.00002391728,0.000005806519,6.994196e-7,0.0002171487,0.02929476,0.8826265,0.001163571,0.0003738213,0.0001300475],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954102,0.000002387249,0.002877375,0.0004591983,0.000205134,0.0001207656,0.000001869029,0.0006356252,0.000287421],"genre_scores_gemma":[0.9948916,0.000009836588,0.00485285,0.00002830418,0.00004838514,0.000001223342,0.000002731785,0.00001593934,0.0001490971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08303032,"threshold_uncertainty_score":0.691238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01290439447136928,"score_gpt":0.2388260911871307,"score_spread":0.2259216967157614,"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."}}