{"id":"W3107089401","doi":"10.1121/1.5147442","title":"A convolutional neural network applied to Arctic acoustic recordings to identify soundscape components","year":2020,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Underwater; Soundscape; Convolutional neural network; Arctic; Acoustics; Computer science; Geology; The arctic; Oceanography; Sound (geography); Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000522403,0.0007249449,0.0002553186,0.000429546,0.0003894422,0.0004604593,0.000540685,0.0005433565,0.001274763],"category_scores_gemma":[0.0008706806,0.0002274572,0.000411073,0.0005404645,0.0001996021,0.0004159804,0.0004646159,0.0007023796,0.0005423519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007845755,"about_ca_system_score_gemma":0.0009589137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04257865,"about_ca_topic_score_gemma":0.05115424,"domain_scores_codex":[0.999861,0.00001800078,0.000006515896,0.0000471569,0.00002690673,0.00004034974],"domain_scores_gemma":[0.9997305,0.00007882142,0.0000135167,0.00002800819,0.0001325795,0.00001661961],"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":[0.0003796884,0.000366206,0.01427493,0.0000849122,0.0002097894,0.0002772352,0.0001483118,0.4016169,0.04346613,0.002090367,0.007238613,0.529847],"study_design_scores_gemma":[0.000003769602,0.0000259172,0.001897934,0.000005758836,0.00001429086,0.00001287839,0.00001560824,0.9926215,0.004572954,0.0002788214,0.0005445163,0.000006131629],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5792568,0.0008684969,0.4043115,0.0006151193,0.0004248251,0.0001420736,0.001631038,0.004010967,0.008739286],"genre_scores_gemma":[0.8797745,0.0002580162,0.1085527,0.0001188755,0.0000546493,0.0000817555,0.002381785,0.00008982614,0.008687943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04257865,"threshold_uncertainty_score":0.0846616,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03350104523432114,"score_gpt":0.2693106087726578,"score_spread":0.2358095635383367,"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."}}