{"id":"W2090018636","doi":"10.1139/l06-111","title":"Suspended sediment prediction using two different feed-forward back-propagation algorithms","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Civil Engineering","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sediment; Multilinear map; Artificial neural network; Algorithm; Streamflow; Backpropagation; Upstream (networking); Environmental science; Gradient descent; Hydrology (agriculture); Drainage basin; Computer science; Geology; Geotechnical engineering; Artificial intelligence; Mathematics; Geomorphology; Geography; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006518763,0.0001529053,0.0001758907,0.0001786332,0.0001063411,0.00004415807,0.0001687527,0.00007183276,0.001442998],"category_scores_gemma":[0.00009398749,0.0001367699,0.00007731819,0.0002227234,0.00005337538,0.0002043962,0.00002299232,0.000280877,0.00002689008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173645,"about_ca_system_score_gemma":0.00005383714,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001343253,"about_ca_topic_score_gemma":0.02338444,"domain_scores_codex":[0.9986655,0.00001830762,0.0004044686,0.0001419263,0.0003089901,0.0004607715],"domain_scores_gemma":[0.9990256,0.00003436722,0.0001455291,0.00010694,0.00002446994,0.0006631045],"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":[0.000007533422,0.00001230143,0.01279643,0.00000823043,0.00002298119,0.0001114149,0.00020799,0.9687168,0.01527912,0.00002545525,0.000256676,0.002555067],"study_design_scores_gemma":[0.001196707,0.0003528321,0.06383353,0.0002574079,0.00008333615,0.0008109058,0.00004189055,0.9161985,0.01010714,0.000296133,0.006328826,0.0004928029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8911092,0.00004679679,0.1058809,0.00007869636,0.0009254834,0.00009410763,0.00000425741,0.00001894708,0.001841624],"genre_scores_gemma":[0.9968556,0.000001556219,0.002766431,0.0000436084,0.000263796,4.037565e-7,0.000002308779,0.00002095162,0.00004534693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1057464,"threshold_uncertainty_score":0.9994698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01504355846084663,"score_gpt":0.212922999394099,"score_spread":0.1978794409332524,"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."}}