{"id":"W2342006272","doi":"10.1016/j.jvolgeores.2016.04.014","title":"Principal component analysis vs. self-organizing maps combined with hierarchical clustering for pattern recognition in volcano seismic spectra","year":2016,"lang":"en","type":"article","venue":"Journal of Volcanology and Geothermal Research","topic":"Seismology and Earthquake Studies","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Principal component analysis; Cluster analysis; Hierarchical clustering; Pattern recognition (psychology); Spectrogram; Volcano; Artificial intelligence; Computer science; Geology; Data set; A priori and a posteriori; Self-organizing map; Set (abstract data type); Data mining; Seismology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001921177,0.0001369457,0.0004195177,0.0008563716,0.0002210956,0.00004130992,0.0004196818,0.0001308581,0.00002336677],"category_scores_gemma":[0.0001336641,0.00008716527,0.00008042769,0.000555389,0.0002957833,0.0002527757,0.000201966,0.0004963708,0.000007224455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008283462,"about_ca_system_score_gemma":0.0001355407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006277199,"about_ca_topic_score_gemma":0.0003899404,"domain_scores_codex":[0.9979933,0.0004400166,0.0003970666,0.0003003232,0.0003026424,0.0005666545],"domain_scores_gemma":[0.9983456,0.0008885161,0.0001593128,0.0001917993,0.0002973406,0.0001174917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006790855,0.0009619697,0.5734006,0.0001941237,0.003741747,0.0013334,0.006882621,0.0007219887,0.004323581,0.001584618,0.0004163908,0.3996481],"study_design_scores_gemma":[0.007587718,0.00643688,0.9505398,0.0002368398,0.0001510939,0.0007410157,0.000265207,0.02241898,0.00163578,0.007738575,0.0018475,0.0004005712],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.856871,0.0001468353,0.1323756,0.01026339,0.00009537959,0.0001662722,0.000004868685,0.00001682242,0.00005980902],"genre_scores_gemma":[0.9951013,0.0002156251,0.00425591,0.0002466821,0.00009382425,0.00001144688,0.000001093734,0.000009474447,0.00006460671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3992476,"threshold_uncertainty_score":0.3554496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03482769413617868,"score_gpt":0.2893917758105673,"score_spread":0.2545640816743886,"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."}}