{"id":"W4200540997","doi":"10.5194/nhess-21-3679-2021","title":"Applying machine learning for drought prediction in a perfect model framework using data from a large ensemble of climate simulations","year":2021,"lang":"en","type":"article","venue":"Natural hazards and earth system sciences","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Leibniz-Rechenzentrum; Leibniz-Gemeinschaft; Environment and Climate Change Canada; Bayerische Akademie der Wissenschaften","keywords":"Context (archaeology); Climatology; Precipitation; Computer science; Index (typography); Machine learning; Climate model; Artificial intelligence; Class (philosophy); Predictive modelling; Artificial neural network; Meteorology; Environmental science; Climate change; Geography; Geology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001950956,0.0005554797,0.0006826929,0.0006474492,0.0004027468,0.0008130923,0.0005320198,0.0007024716,0.0005462577],"category_scores_gemma":[0.004395248,0.0003008004,0.0006252966,0.0005450888,0.000385711,0.0009598768,0.0005054404,0.0006182044,0.00007375376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178696,"about_ca_system_score_gemma":0.000796289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02102068,"about_ca_topic_score_gemma":0.01559711,"domain_scores_codex":[0.9995273,0.0002721397,0.00002545666,0.00009675875,0.00004098415,0.00003733315],"domain_scores_gemma":[0.9985642,0.000904763,0.0001284217,0.0002058164,0.0001394769,0.00005729569],"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":[0.0000387613,0.00002145294,0.004594566,0.000009682186,0.00006724962,0.00002036868,0.000008178036,0.9916233,0.0001173268,0.0003613998,0.00009042739,0.003047292],"study_design_scores_gemma":[0.000002289911,0.000008464864,0.0008950733,9.977316e-7,0.000005089195,0.000001889913,0.000003530795,0.9985838,0.00006900627,0.0003957819,0.00003182638,0.000002158142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9382157,0.0002915914,0.05914577,0.0003339901,0.00005360131,0.00002384424,0.0005191965,0.0002832301,0.001133072],"genre_scores_gemma":[0.9951493,0.00003432311,0.004443182,0.00001425354,0.00001261941,0.000009023634,0.0002023389,0.000007374941,0.0001276317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02102068,"threshold_uncertainty_score":0.04179662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02958964400634552,"score_gpt":0.2950341582704469,"score_spread":0.2654445142641014,"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."}}