{"id":"W4410862684","doi":"10.1121/10.0036773","title":"Predicting transmission loss in underwater acoustics using continual learning with range-dependent conditional convolutional neural networks","year":2025,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Underwater Acoustics Research","field":"Earth and Planetary Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bathymetry; Computer science; Convolutional neural network; Underwater; Deep learning; Benchmark (surveying); Artificial intelligence; Range (aeronautics); Machine learning; Geology; Engineering; Oceanography","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":[0.001018404,0.0001576097,0.0003141847,0.00005355388,0.0003732345,0.00004067151,0.000511062,0.00009673342,0.0001958998],"category_scores_gemma":[0.00008920894,0.00008073663,0.0001716989,0.0003977581,0.001032686,0.0001324897,0.00006159751,0.001170708,8.243441e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005396475,"about_ca_system_score_gemma":0.00025509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003516336,"about_ca_topic_score_gemma":0.00001476591,"domain_scores_codex":[0.9976805,0.000405407,0.0005174245,0.0001284964,0.0008597951,0.0004083679],"domain_scores_gemma":[0.9979351,0.001295449,0.0003003266,0.0001211417,0.0002518077,0.00009623059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004003052,0.00004005103,0.09149431,0.0000315455,0.0001093785,0.000006200921,0.0002491337,0.9042303,0.001298828,4.923799e-7,0.0001849066,0.001954574],"study_design_scores_gemma":[0.0008424459,0.0002049533,0.03569818,0.0001326464,0.0001706701,0.0001145052,0.001292353,0.961017,0.00007656241,0.0003263661,0.00003598768,0.00008832088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1588987,0.0002164595,0.8394198,0.001130685,0.000113778,0.0001412467,0.00001701749,0.000006845893,0.00005544499],"genre_scores_gemma":[0.987729,0.0001251209,0.01152686,0.000386811,0.0001268285,2.513892e-7,0.000005119217,0.000006460209,0.00009362484],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8288302,"threshold_uncertainty_score":0.5086211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393685845428605,"score_gpt":0.2525412034248964,"score_spread":0.2386043449706104,"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."}}