{"id":"W4388844151","doi":"10.5194/gmd-2023-185","title":"Clustering analysis of very large measurement and model datasets on high performance computing platforms","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Computation; A priori and a posteriori; Parallel computing; Message Passing Interface; Grid; Cluster (spacecraft); Algorithm; Message passing; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001853118,0.001058782,0.0009861961,0.002019216,0.001040287,0.001044561,0.001589837,0.0008364039,0.001162147],"category_scores_gemma":[0.007288111,0.0005011802,0.001457648,0.003022938,0.0005252811,0.001164852,0.00115893,0.001228695,0.0005044852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001367166,"about_ca_system_score_gemma":0.00146856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01899475,"about_ca_topic_score_gemma":0.0146442,"domain_scores_codex":[0.9984475,0.0004569743,0.0001242321,0.0003350182,0.0005008945,0.0001352755],"domain_scores_gemma":[0.9964511,0.001168071,0.0002519818,0.001160062,0.0008204148,0.0001483622],"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":[0.0003173916,0.000328699,0.02328371,0.0003501054,0.0007500987,0.0004028188,0.0002547035,0.8794112,0.01360778,0.005607015,0.01163102,0.06405538],"study_design_scores_gemma":[0.00002604778,0.00004251666,0.01289502,0.000009965885,0.00002359432,0.00003964644,0.00009611149,0.9776033,0.003407599,0.003916602,0.001911724,0.00002789486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5599837,0.0006461832,0.4131862,0.001192281,0.0003823783,0.0004227657,0.00965049,0.0118168,0.002719293],"genre_scores_gemma":[0.728619,0.0002756026,0.251603,0.0001287548,0.00007976741,0.0004407852,0.01759807,0.0004348714,0.0008201959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01899475,"threshold_uncertainty_score":0.03776836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1000074199870351,"score_gpt":0.2896604514624579,"score_spread":0.1896530314754228,"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."}}