{"id":"W2116208828","doi":"10.1007/s11269-012-9992-5","title":"River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia","year":2012,"lang":"en","type":"article","venue":"Water Resources Management","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":78,"is_retracted":false,"has_abstract":false,"ca_institutions":"Golder Associates (Canada)","funders":"Universiti Teknologi Petronas","keywords":"Conjugate gradient method; Algorithm; Gradient descent; Multilayer perceptron; Artificial neural network; Convergence (economics); Training (meteorology); Sediment; Levenberg–Marquardt algorithm; Hydrogeology; Computer science; Machine learning; Geology; Geomorphology; Geotechnical engineering; Meteorology; Geography","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":[0.0009514758,0.0005571715,0.0004300997,0.0003985133,0.0004177377,0.0006729711,0.0006286756,0.0008420869,0.0004914304],"category_scores_gemma":[0.001597301,0.0003222002,0.0004631759,0.000545089,0.0003504732,0.0007204074,0.0003112835,0.0004900392,0.0001028976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001373476,"about_ca_system_score_gemma":0.0008561772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08899198,"about_ca_topic_score_gemma":0.06927977,"domain_scores_codex":[0.9997883,0.00007007431,0.00002101209,0.00004574265,0.000032928,0.00004192881],"domain_scores_gemma":[0.9989582,0.0006049036,0.00009172157,0.00005422701,0.0002444974,0.00004649956],"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":[0.0004434671,0.0004031156,0.0565351,0.00009202011,0.00009568786,0.0008416816,0.0001845933,0.8962569,0.002756752,0.000648989,0.0005469896,0.04119468],"study_design_scores_gemma":[0.00001446912,0.00008001831,0.008605081,0.000004855692,0.00002114019,0.00002738931,0.0001171706,0.9890307,0.001870934,0.0001178369,0.0000984795,0.00001196863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948215,0.00005050806,0.004197735,0.00007406363,0.000005703233,0.00001187789,0.00006181523,0.00006384696,0.0007128705],"genre_scores_gemma":[0.9957402,0.0000405182,0.003377802,0.000005011574,0.000001873692,0.000005218528,0.00006114414,0.000005176219,0.0007631732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08899198,"threshold_uncertainty_score":0.176948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04421302975557186,"score_gpt":0.2608464373813931,"score_spread":0.2166334076258213,"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."}}