{"id":"W3168593366","doi":"10.1007/s11600-021-00617-2","title":"Integrated preprocessing techniques with linear stochastic approaches in groundwater level forecasting","year":2021,"lang":"en","type":"article","venue":"Acta Geophysica","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; Université Laval","funders":"","keywords":"Adaptive neuro fuzzy inference system; Multilayer perceptron; Akaike information criterion; Artificial neural network; Moving average; Autoregressive integrated moving average; Nonlinear system; Mean squared error; Computer science; Normalization (sociology); Statistics; Autoregressive–moving-average model; Mean absolute percentage error; Preprocessor; Time series; Autoregressive model; Data mining; Mathematics; Fuzzy logic; Artificial intelligence; Fuzzy control system","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":[0.0001863823,0.0002140705,0.0002327519,0.00003400903,0.0001319996,0.00006649949,0.00021159,0.00008628196,0.000156395],"category_scores_gemma":[0.0001517676,0.0001588772,0.00003954417,0.000623274,0.0002179747,0.0002953962,0.0002540914,0.000327482,0.00006057513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001335187,"about_ca_system_score_gemma":0.00003334023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003797619,"about_ca_topic_score_gemma":0.0001973337,"domain_scores_codex":[0.9984688,0.00006699889,0.0002143322,0.0005749838,0.0002547369,0.0004201537],"domain_scores_gemma":[0.9994515,0.00008674378,0.00008802855,0.0002856917,0.0000180587,0.00007000406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005848825,0.004065487,0.04072994,0.0002712724,0.0001528057,0.0009372475,0.009524435,0.1631702,0.2765587,0.0001787488,0.0005383626,0.503288],"study_design_scores_gemma":[0.001455029,0.001160278,0.03718311,0.001169149,0.0001183392,0.0004629504,0.0006019493,0.8460819,0.100332,0.006627327,0.002543955,0.00226398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885935,0.000005419978,0.007112636,0.0002413809,0.00001984891,0.0001537653,0.000002608537,0.0001420225,0.003728777],"genre_scores_gemma":[0.9689202,3.232932e-7,0.03036923,0.0001304221,0.00004917408,0.00003860049,0.00002161687,0.00002962869,0.0004407788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6829118,"threshold_uncertainty_score":0.6478826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09122146162597249,"score_gpt":0.2430501247458113,"score_spread":0.1518286631198388,"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."}}