{"id":"W4386122623","doi":"10.1007/s00190-023-01768-4","title":"Combining ERA5 data and CYGNSS observations for the joint retrieval of global significant wave height of ocean swell and wind wave: a deep convolutional neural network approach","year":2023,"lang":"en","type":"article","venue":"Journal of Geodesy","topic":"Soil Moisture and Remote Sensing","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Natural Science Foundation of China","keywords":"Swell; Significant wave height; Convolutional neural network; Support vector machine; Remote sensing; Correlation coefficient; Wind wave; Computer science; Meteorology; Artificial intelligence; Environmental science; Geology; Machine learning; 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":[0.0009021309,0.0000990784,0.0002385205,0.00001887787,0.0001711436,0.0000239119,0.0001543469,0.00005288633,0.000003282219],"category_scores_gemma":[0.0001366578,0.00006468453,0.00006207353,0.0002836585,0.0003582641,0.0001529586,0.0002386627,0.0001479249,2.19292e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004190216,"about_ca_system_score_gemma":0.00003108312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005856969,"about_ca_topic_score_gemma":0.00003654945,"domain_scores_codex":[0.9988214,0.00005616077,0.0004361008,0.000157605,0.0003335276,0.0001951928],"domain_scores_gemma":[0.9990253,0.0002891654,0.0003702544,0.0001924248,0.00004463,0.00007819405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002163774,0.0005799371,0.6429659,0.0003383178,0.001213521,0.0001264963,0.005749126,0.2387242,0.02720552,0.002349144,0.03600422,0.04257984],"study_design_scores_gemma":[0.0005891022,0.0001229636,0.6537513,0.00003329688,0.00009536605,0.000170818,0.0005816118,0.343154,0.00007111293,0.001093274,0.0002659864,0.00007112078],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996043,0.0004140107,0.002039711,0.0008832787,0.0001974037,0.0001779483,0.00002835893,0.000004643331,0.0002116501],"genre_scores_gemma":[0.9953831,0.00009356606,0.004258486,0.00008352938,0.0001356895,5.156359e-8,0.0000171447,0.000007079872,0.00002134052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1044298,"threshold_uncertainty_score":0.2637759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08011520504126929,"score_gpt":0.2552877797372266,"score_spread":0.1751725746959573,"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."}}