{"id":"W3203095355","doi":"10.1007/s00521-021-06550-1","title":"Hybrid models for suspended sediment prediction: optimized random forest and multi-layer perceptron through genetic algorithm and stochastic gradient descent methods","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Random forest; Algorithm; Perceptron; Computer science; Sediment; Multilayer perceptron; Genetic algorithm; Environmental science; Machine learning; Geology; Artificial neural network; Geomorphology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.002390305,0.0009803417,0.001867805,0.0008930439,0.000500749,0.001080825,0.001925942,0.001613946,0.001147136],"category_scores_gemma":[0.002777843,0.0006144019,0.00126149,0.001264337,0.0004928591,0.001804114,0.0006397972,0.001255898,0.0003855367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008952052,"about_ca_system_score_gemma":0.001179205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02123355,"about_ca_topic_score_gemma":0.02068743,"domain_scores_codex":[0.9994517,0.0002178799,0.00003950139,0.0001240175,0.0001040668,0.000062803],"domain_scores_gemma":[0.9988696,0.0006479708,0.00009893604,0.00005747041,0.0002823187,0.00004366722],"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":[0.00009207614,0.00006310198,0.0005492529,0.00002722184,0.00006930264,0.00001851569,0.0000128987,0.9744055,0.0003886614,0.001289933,0.000329027,0.02275452],"study_design_scores_gemma":[0.000003391214,0.000006342997,0.00004484789,0.000001075018,0.00000382281,0.000001475422,6.854901e-7,0.9996117,0.00005834632,0.0002442288,0.00002227153,0.000001957706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07428118,0.001140589,0.9214354,0.000241926,0.0001567235,0.0000484906,0.0001850052,0.0009511885,0.00155953],"genre_scores_gemma":[0.768808,0.0004603998,0.2260131,0.0001470827,0.0001194477,0.0001507259,0.0003521372,0.0001438721,0.003805147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02123355,"threshold_uncertainty_score":0.04221994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05147506452192749,"score_gpt":0.3185403581455952,"score_spread":0.2670652936236677,"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."}}