{"id":"W1969391747","doi":"10.2166/hydro.2008.006","title":"Improving groundwater level forecasting with a feedforward neural network and linearly regressed projected precipitation","year":2008,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Groundwater; Groundwater recharge; Aquifer; Precipitation; Feedforward neural network; Surface runoff; Artificial neural network; Environmental science; Feed forward; Hydrology (agriculture); Component (thermodynamics); Meteorology; Geology; Computer science; Engineering; Geography; Machine learning; Geotechnical engineering; Ecology","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":[0.0005504142,0.0001765417,0.0002690755,0.00006263561,0.0002897172,0.00007940148,0.0001721749,0.00007512608,0.00002844535],"category_scores_gemma":[0.000230204,0.0001135732,0.00005488479,0.0002759195,0.0002127995,0.001092046,0.0001090587,0.000356495,0.000009039126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009837232,"about_ca_system_score_gemma":0.00002971374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004621308,"about_ca_topic_score_gemma":0.00002243625,"domain_scores_codex":[0.9983271,0.00004343155,0.0006734433,0.0001025543,0.0004933508,0.0003600962],"domain_scores_gemma":[0.9987774,0.000112745,0.0008099838,0.0001167074,0.0000441953,0.0001390057],"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":[0.0004831969,0.0001196726,0.06755643,0.000104095,0.00007073199,0.0002378856,0.008622224,0.9022704,0.0009546106,0.000007135613,0.001470076,0.0181035],"study_design_scores_gemma":[0.0007858082,0.001274142,0.01522191,0.00009460817,0.00004034843,0.0042958,0.00005519193,0.9776304,0.0001194891,0.0001084546,0.0001850408,0.0001887738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953976,0.00001684556,0.003617424,0.0001235368,0.00008954449,0.0001695608,0.000001091872,0.00002621237,0.0005581668],"genre_scores_gemma":[0.925458,0.000005745667,0.07417194,0.0001372027,0.000117079,0.00000177578,0.000002177356,0.00001562512,0.00009048091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07536001,"threshold_uncertainty_score":0.463138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04257155452134622,"score_gpt":0.2179054728547558,"score_spread":0.1753339183334096,"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."}}