{"id":"W4389559997","doi":"10.3390/environments10120217","title":"New Graph-Based and Transformer Deep Learning Models for River Dissolved Oxygen Forecasting","year":2023,"lang":"en","type":"article","venue":"Environments","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakes Environmental (Canada); University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Benchmarking; Mean squared error; Water quality; Watershed; Computer science; Transformer; Environmental science; Artificial neural network; STREAMS; Data mining; Machine learning; Hydrology (agriculture); Statistics; Mathematics; Engineering; Ecology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004805262,0.0005530313,0.000469706,0.0005340714,0.0001861478,0.0005765296,0.001043665,0.0005600784,0.001184114],"category_scores_gemma":[0.001229415,0.0002393827,0.0005348899,0.0005820608,0.0003355441,0.0008458936,0.0005933772,0.0008969423,0.0001600717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001005511,"about_ca_system_score_gemma":0.0007055041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02155342,"about_ca_topic_score_gemma":0.02288207,"domain_scores_codex":[0.9998851,0.00002362659,0.000007739885,0.0000339743,0.00002797874,0.00002157204],"domain_scores_gemma":[0.9996332,0.0001748114,0.00003806886,0.00001976716,0.0001126789,0.00002142033],"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":[0.00002077248,0.00002306358,0.0008793088,0.00001049937,0.00001695368,0.00001500718,0.00001153964,0.9788603,0.0003789519,0.001723957,0.0003676655,0.01769197],"study_design_scores_gemma":[6.988008e-7,0.00000295715,0.00005108369,5.380689e-7,0.000001451645,9.982139e-7,9.132971e-7,0.9994096,0.0000503372,0.0004476399,0.00003317597,7.487465e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689314,0.0006066728,0.8236957,0.0004452104,0.0001091485,0.00004612056,0.0004234542,0.0009810457,0.004761189],"genre_scores_gemma":[0.9569145,0.0002348817,0.03906449,0.0001076247,0.00002208617,0.00004322329,0.0004771808,0.00002922306,0.003106758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02155342,"threshold_uncertainty_score":0.04285592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04237375490471945,"score_gpt":0.2281837506993397,"score_spread":0.1858099957946203,"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."}}