{"id":"W4404414732","doi":"10.1029/2024jh000243","title":"Using Explainable AI and Transfer Learning to Understand and Predict the Maintenance of Atlantic Blocking With Limited Observational Data","year":2024,"lang":"en","type":"article","venue":"Journal of Geophysical Research Machine Learning and Computation","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Office; Climate Extremes; Schmidt Family Foundation; National Science Foundation","keywords":"Blocking (statistics); Observational study; Transfer of learning; Observational learning; Computer science; Artificial intelligence; Psychology; Mathematics education; Mathematics; Computer network; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008950715,0.00008387391,0.0001487777,0.0001433708,0.000198532,0.0001546507,0.00007429274,0.00002556653,0.00000127656],"category_scores_gemma":[0.0001596265,0.00005527601,0.0000149376,0.0003273523,0.00008031491,0.0002423961,0.00005967672,0.0007687322,1.260992e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002239639,"about_ca_system_score_gemma":0.00004109723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001037494,"about_ca_topic_score_gemma":0.0000136959,"domain_scores_codex":[0.9990333,0.0001341474,0.0001890529,0.0001260649,0.0003462171,0.0001712557],"domain_scores_gemma":[0.999013,0.000709503,0.00002433402,0.00004336809,0.0001354788,0.00007432429],"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":[0.0001596319,0.0000167564,0.01218401,0.0004590034,0.0001436339,0.00004155525,0.00335961,0.942338,0.003704966,0.001150082,0.0000442911,0.0363984],"study_design_scores_gemma":[0.000234693,0.0003665819,0.005747949,0.0007664105,0.0000250745,0.00008932634,0.0005920978,0.9911919,0.00004108626,0.0004341767,0.0004486933,0.00006198535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911846,0.0009589233,0.1073565,0.0003688576,0.00002595695,0.0000510524,0.000001915552,0.00001724319,0.00003499512],"genre_scores_gemma":[0.9986253,0.0001969559,0.001018363,0.000008421386,0.0000996822,4.444283e-7,0.000007808268,0.00001620977,0.00002679698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1074407,"threshold_uncertainty_score":0.3339801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09927608756865201,"score_gpt":0.3485107465980402,"score_spread":0.2492346590293882,"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."}}