{"id":"W4387233192","doi":"10.20944/preprints202309.2161.v1","title":"New Graph-Based and Transformers Deep Learning Models for River Dissolved Oxygen Forecasting","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Mean squared error; Watershed; Benchmarking; Water quality; Transformer; Graph; Computer science; Environmental science; Eutrophication; Machine learning; Data mining; Hydrology (agriculture); Statistics; Mathematics; Engineering; Ecology; Nutrient","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001114921,0.0005385219,0.0005537461,0.0001238842,0.0004074959,0.00005142852,0.0006094301,0.0004919436,0.0006175874],"category_scores_gemma":[0.0005961088,0.0005331555,0.0003121765,0.0003059281,0.0003556479,0.0001765208,0.001331259,0.001011742,0.0003354416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000223977,"about_ca_system_score_gemma":0.00005248371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001367562,"about_ca_topic_score_gemma":0.0001680049,"domain_scores_codex":[0.9963719,0.0001263663,0.0005783364,0.001619811,0.0004727412,0.0008308127],"domain_scores_gemma":[0.9984167,0.0003396147,0.0003063349,0.0005103952,0.00003018589,0.000396766],"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":[0.0001021026,0.00003532375,0.126984,0.0001259789,0.00006130664,0.000009114653,0.001427903,0.8581807,0.001525623,0.00002203543,0.00003558829,0.01149027],"study_design_scores_gemma":[0.0008408486,0.00008505811,0.06516556,0.0002181618,0.0001443901,0.000005043189,0.00004058428,0.8980438,0.001466084,0.03225809,0.0009317757,0.0008006406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.848269,0.00002865288,0.1475575,0.0004419764,0.0002728697,0.00110478,0.00001839299,0.0005082943,0.001798546],"genre_scores_gemma":[0.9839445,0.00003502201,0.01422096,0.0001155005,0.00008753343,0.0002028506,0.00008635537,0.000115686,0.001191618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1356754,"threshold_uncertainty_score":0.999712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2063031539348977,"score_gpt":0.3128636964566238,"score_spread":0.1065605425217261,"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."}}