{"id":"W3168112912","doi":"10.5194/egusphere-egu21-1305","title":"Applying machine learning for drought prediction using a large ensemble of climate simulations","year":2021,"lang":"en","type":"article","venue":"","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Preparedness; Precipitation; Climate change; Summer camp; Machine learning; Climate model; Artificial intelligence; Climatology; Environmental science; Computer science; Meteorology; Geography; Ecology; Political science; Psychology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001355813,0.0006476488,0.0007493807,0.0007859943,0.0003587368,0.0006761103,0.0005760753,0.000628135,0.0005919404],"category_scores_gemma":[0.00337884,0.0003396437,0.0006248311,0.0006217367,0.0001980155,0.0005375412,0.0004636887,0.0008844875,0.0001651566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008466602,"about_ca_system_score_gemma":0.0007285356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02532087,"about_ca_topic_score_gemma":0.01623204,"domain_scores_codex":[0.9996976,0.000130156,0.00001994782,0.0000721193,0.0000376018,0.00004268516],"domain_scores_gemma":[0.9988901,0.0007260854,0.00007456666,0.0001134154,0.000141635,0.00005426599],"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":[0.00004165065,0.00003571614,0.003808721,0.000008296491,0.00005693235,0.00001425675,0.00001167269,0.9808964,0.0002262187,0.0001390683,0.0002114366,0.01454967],"study_design_scores_gemma":[0.000001796871,0.000005269958,0.0005520992,9.361691e-7,0.000003150012,9.289493e-7,0.000002169703,0.999186,0.00008654047,0.0001214059,0.00003802365,0.000001672803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8672606,0.0006249828,0.1272383,0.0004078432,0.0001215797,0.00008285217,0.0007555095,0.0009792486,0.002529034],"genre_scores_gemma":[0.9846266,0.00008494828,0.01425644,0.00002756203,0.0000329525,0.00003642121,0.0005828057,0.00001812421,0.0003341977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02532087,"threshold_uncertainty_score":0.05034697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01591585389906568,"score_gpt":0.2646188451175894,"score_spread":0.2487029912185237,"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."}}