{"id":"W3009328342","doi":"10.1007/s00521-020-04800-2","title":"Prediction of actual evapotranspiration by artificial neural network models using data from a Bowen ratio energy balance station","year":2020,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of the Environment, Conservation and Parks; University of Guelph","funders":"","keywords":"Sigmoid function; Mean squared error; Artificial neural network; Evapotranspiration; Activation function; Energy balance; Coefficient of determination; Correlation coefficient; Wind speed; Generalization; Approximation error; Computer science; Mathematics; Artificial intelligence; Algorithm; Statistics; Meteorology; Physics; Mathematical analysis","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009987161,0.0001071407,0.0001266595,0.000007623503,0.0002598585,0.00004187375,0.0002021652,0.00005590344,0.00002433926],"category_scores_gemma":[0.00001805499,0.0001064315,0.00001789549,0.0002258187,0.0001038159,0.000246298,0.0001405277,0.0001080306,0.00000251414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001939193,"about_ca_system_score_gemma":0.000006352329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000402742,"about_ca_topic_score_gemma":0.00001885925,"domain_scores_codex":[0.9988707,0.00007081245,0.0002963206,0.0004225467,0.0001795573,0.0001600433],"domain_scores_gemma":[0.9994619,0.00008722567,0.0001566438,0.0002016187,0.0000117131,0.00008088953],"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":[0.00001501066,0.0000219524,0.0009332494,0.000002917614,0.000003968362,1.412296e-7,0.000142356,0.9410055,0.04103031,0.00009104294,0.0003836121,0.01636991],"study_design_scores_gemma":[0.0001149697,0.00005078625,0.0004873418,0.000005471496,0.00002262014,0.000001019146,0.0000065483,0.9972895,0.0004962484,0.00103182,0.0004137949,0.00007987703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6156001,0.00003081472,0.3836592,0.0002690263,0.00002432275,0.0001170522,0.0001919909,0.00006059247,0.00004686396],"genre_scores_gemma":[0.995337,0.000003704969,0.003257517,0.000415094,0.0002477455,0.000005500813,0.0007215529,0.000009889972,0.000001964224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3804017,"threshold_uncertainty_score":0.4340149,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1104974546948484,"score_gpt":0.2734038011234458,"score_spread":0.1629063464285974,"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."}}