{"id":"W3048301386","doi":"10.1016/j.wasman.2020.07.034","title":"Application of a multi-stage neural network approach for time-series landfill gas modeling with missing data imputation","year":2020,"lang":"en","type":"article","venue":"Waste Management","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Nonlinear autoregressive exogenous model; Artificial neural network; Imputation (statistics); Autoregressive model; Mean squared error; Mean absolute percentage error; Multilayer perceptron; Time series; Statistics; Data mining; Computer science; Mathematics; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002394687,0.00009084224,0.000104814,0.000009512917,0.0001064282,0.00002571372,0.000217871,0.00001816242,0.00000502459],"category_scores_gemma":[0.000007683565,0.00007946852,0.00001751179,0.0001326142,0.0000311558,0.0001848243,0.0002853964,0.00003798047,0.000004731983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002347846,"about_ca_system_score_gemma":0.000001450242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003805444,"about_ca_topic_score_gemma":0.000001674974,"domain_scores_codex":[0.9991643,0.00002109176,0.0001771429,0.0003122835,0.0001624467,0.0001627079],"domain_scores_gemma":[0.9995901,0.00001175648,0.0001046672,0.0002417264,0.000005747429,0.00004598567],"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":[0.0000618609,0.00002175791,0.0007280107,0.0001232959,0.000015613,4.258241e-7,0.0003318437,0.9587,0.0001168627,0.00006816562,0.0001071383,0.039725],"study_design_scores_gemma":[0.0002924539,0.00005604385,0.00006699654,0.0000130371,0.0000307334,3.294328e-7,0.0006269445,0.9982538,0.00006486071,0.00002240576,0.0004794238,0.00009292422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01410725,0.00001779243,0.9844283,0.0001759408,0.00001493654,0.000475073,0.00001336325,0.00004384758,0.0007235011],"genre_scores_gemma":[0.6533185,0.000002066644,0.346133,0.00005309159,0.0001004685,0.00003316506,0.0001846915,0.00001666873,0.0001583261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6392112,"threshold_uncertainty_score":0.3240632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08291405786338389,"score_gpt":0.2796796654099628,"score_spread":0.1967656075465788,"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."}}