{"id":"W4392165840","doi":"10.1007/s10666-024-09957-x","title":"Forecasting Methane Data Using Multivariate Long Short-Term Memory Neural Networks","year":2024,"lang":"en","type":"article","venue":"Environmental Modeling & Assessment","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Canada First Research Excellence Fund","keywords":"Greenhouse gas; Methane; Environmental science; Wind speed; Climate change; Artificial neural network; Meteorology; Time series; Multivariate statistics; Variance (accounting); Global warming; Climatology; Methane emissions; Econometrics; Atmospheric sciences; Computer science; Mathematics; Business; Geography; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000681135,0.0006055977,0.0003968842,0.0000264866,0.0003507976,0.0001819107,0.0009152842,0.0001941122,0.001340082],"category_scores_gemma":[0.000005948013,0.0005878697,0.0001657448,0.0001916566,0.0002833691,0.001189013,0.002644841,0.0007015408,0.00006190431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001543823,"about_ca_system_score_gemma":0.00001726779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003875293,"about_ca_topic_score_gemma":0.0000227866,"domain_scores_codex":[0.9959097,0.000137917,0.0006837908,0.001510601,0.0008428979,0.0009151276],"domain_scores_gemma":[0.9983842,0.00007830355,0.00009278085,0.001127189,0.000001068007,0.0003164151],"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":[0.00001416651,0.0001437354,0.0264061,0.00001603381,0.00007783475,0.0001817932,0.0001246341,0.916276,0.003899053,0.000003453944,0.00001567627,0.05284152],"study_design_scores_gemma":[0.0002545784,0.00006318205,0.006170731,0.00006245673,0.0001868108,0.0001300405,0.0002451382,0.9921172,0.00002937372,0.00004985747,0.00005146486,0.0006391946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5490192,0.0004407239,0.4492278,0.00003540427,0.0004859615,0.0003272081,0.00002090207,0.0001122029,0.0003306317],"genre_scores_gemma":[0.9352182,0.0001528889,0.0635534,0.000139405,0.0002393058,0.00002832556,0.0002820686,0.0001460996,0.0002403494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.386199,"threshold_uncertainty_score":0.9996573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06145766940766023,"score_gpt":0.3026813504188567,"score_spread":0.2412236810111965,"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."}}