{"id":"W2056678350","doi":"10.1139/p07-037","title":"Artificial neural network forecasting of nonlinear Markov processes","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Physics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of British Columbia","keywords":"Robustness (evolution); Artificial neural network; Markov chain; Nonlinear system; Computer science; Markov process; Noise (video); Series (stratigraphy); Time series; Algorithm; Representation (politics); Machine learning; Artificial intelligence; Mathematics; Statistics; Physics","routes":{"ca_aff":false,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0005039295,0.00009919982,0.000180573,0.00003041594,0.0001296478,0.00002007253,0.0002338364,0.00005225051,0.00017848],"category_scores_gemma":[0.0003296459,0.00008684057,0.00006951596,0.0004766209,0.0002382451,0.0001415231,0.00002282319,0.0002249038,0.00001092457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001077593,"about_ca_system_score_gemma":0.0001735345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001074257,"about_ca_topic_score_gemma":0.01135634,"domain_scores_codex":[0.998848,0.000023219,0.0003995861,0.00009981192,0.0002089663,0.0004204215],"domain_scores_gemma":[0.9990296,0.0001137938,0.0003330867,0.00008694485,0.00005882885,0.0003777655],"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":[0.00006742001,0.00006068521,0.09198061,0.00004181764,0.00002863573,0.0003664427,0.0007735373,0.6582955,0.001772625,0.0001092414,0.002338549,0.2441649],"study_design_scores_gemma":[0.002679952,0.007039503,0.1411362,0.001996789,0.0007292445,0.002987783,0.0007815268,0.5617387,0.09822897,0.1074841,0.07090396,0.004293284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958609,0.00003865407,0.001621839,0.00009532864,0.0002742696,0.00004501295,0.000005106338,0.000004046582,0.00205481],"genre_scores_gemma":[0.9925203,6.179045e-7,0.006538282,0.0001440594,0.0007587809,1.432199e-7,0.000001226538,0.00001249514,0.00002403267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2398716,"threshold_uncertainty_score":0.6337106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03518432295705386,"score_gpt":0.2343695193693554,"score_spread":0.1991851964123015,"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."}}