{"id":"W2969834763","doi":"10.1109/access.2019.2936989","title":"A Machine Learning Metasystem for Robust Probabilistic Nonlinear Regression-Based Forecasting of Seasonal Water Availability in the US West","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Los Alamos National Laboratory; Università degli Studi di Palermo; U.S. Department of Agriculture; Simon Fraser University; Environment and Climate Change Canada; Oregon State University","keywords":"Computer science; Probabilistic logic; Machine learning; Artificial intelligence; Ensemble learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002013989,0.0001876457,0.000305577,0.00003494432,0.0001359929,0.00006394865,0.0006999527,0.00009085037,0.0007559999],"category_scores_gemma":[0.0005120682,0.00009674863,0.00010554,0.000254834,0.0001693769,0.0001884908,0.0001497986,0.0002850094,0.00007111432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103176,"about_ca_system_score_gemma":0.0000179988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005352846,"about_ca_topic_score_gemma":0.0002669716,"domain_scores_codex":[0.9980221,0.0003022355,0.0004164328,0.0004508481,0.0004012882,0.0004070449],"domain_scores_gemma":[0.998692,0.0007057787,0.0001789574,0.000345039,0.00002496925,0.00005326272],"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":[0.00008612729,0.000113324,0.2852106,0.0001376993,0.000004237956,0.000003629332,0.0001328062,0.7120696,0.001489764,0.000001643106,0.0000260881,0.0007244649],"study_design_scores_gemma":[0.0005411976,0.0001711126,0.006684443,0.0001108207,0.00001974862,0.000006694906,0.00000758157,0.9890202,0.002554943,0.0001070792,0.0006236865,0.000152526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974783,0.00001143675,0.0005413945,0.0002273339,0.0001478322,0.0009249052,0.00002150133,0.0000330958,0.0006141838],"genre_scores_gemma":[0.9969179,2.510211e-7,0.002669777,0.0001672216,0.00003846637,0.00007544602,0.00002654444,0.00001899054,0.00008537693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2785262,"threshold_uncertainty_score":0.8277669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05485155803790336,"score_gpt":0.2782628294349563,"score_spread":0.223411271397053,"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."}}