{"id":"W4386047269","doi":"10.1016/j.coastaleng.2023.104381","title":"Improving WAVEWATCH III hindcasts with machine learning","year":2023,"lang":"en","type":"article","venue":"Coastal Engineering","topic":"Ocean Waves and Remote Sensing","field":"Earth and Planetary Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"BGC Engineering (Canada)","funders":"Centro de Investigación e Innovación en Energía Marina","keywords":"Hindcast; Significant wave height; Mean squared error; Computer science; Artificial neural network; Wind wave; Wave height; Meteorology; Environmental science; Artificial intelligence; Machine learning; Geology; Mathematics; Statistics; Physics","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":[0.0001361462,0.0001433556,0.0001328641,0.00008569811,0.000133569,0.00006626494,0.00007884528,0.0000406769,0.0001001775],"category_scores_gemma":[0.00002520192,0.0001103745,0.00003527269,0.0003734072,0.00001876527,0.0001365654,0.00002541023,0.0002457738,0.0001091664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002942444,"about_ca_system_score_gemma":0.00001582294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001157368,"about_ca_topic_score_gemma":0.0004434628,"domain_scores_codex":[0.9991137,0.000009087928,0.0001178985,0.0001977897,0.0001749357,0.0003865549],"domain_scores_gemma":[0.9996832,0.00005726907,0.0000319896,0.00009559403,0.0000160511,0.0001158721],"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":[0.0000208104,0.000002340654,0.00855394,0.00005721817,0.00002018483,0.0002195359,0.0003098054,0.8629408,0.001424324,0.00001010199,0.0000287004,0.1264122],"study_design_scores_gemma":[0.0002328476,0.00007448285,0.01999809,0.0000399751,0.000006610617,0.00006550898,0.0001403133,0.9771213,0.000311253,0.000002904204,0.001823244,0.0001834687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939399,0.0001241491,0.00274625,0.00006387618,0.000345397,0.00008449229,0.00001363415,0.0004933143,0.002188964],"genre_scores_gemma":[0.9964058,0.00001868835,0.001822743,0.00001187744,0.0001471065,1.238776e-8,0.0001045553,0.00001356402,0.001475593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1262287,"threshold_uncertainty_score":0.450094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005319426876982544,"score_gpt":0.1566037988184221,"score_spread":0.1512843719414395,"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."}}