{"id":"W4402535636","doi":"10.1016/j.envres.2024.120015","title":"Enhanced predictive modeling of dissolved oxygen concentrations in riverine systems using novel hybrid temporal pattern attention deep neural networks","year":2024,"lang":"en","type":"article","venue":"Environmental Research","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Environmental science; Artificial neural network; Computer science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002762967,0.0003970745,0.0003808732,0.0002523096,0.0001949893,0.0005041997,0.000711802,0.0004983423,0.0007204322],"category_scores_gemma":[0.0006735569,0.0002790627,0.000367947,0.0003228401,0.0002189403,0.0006961441,0.0004936876,0.000711529,0.0001111104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005153359,"about_ca_system_score_gemma":0.0005248077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02031038,"about_ca_topic_score_gemma":0.02005363,"domain_scores_codex":[0.9999317,0.000009896773,0.00000406989,0.00002356113,0.00001496683,0.00001577998],"domain_scores_gemma":[0.9998054,0.00008852952,0.00002574322,0.0000137148,0.00005407672,0.00001256946],"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":[0.00004843246,0.00005042788,0.001607049,0.00001572342,0.00003683652,0.00002990541,0.00001515291,0.971103,0.002305744,0.0008715159,0.0003554225,0.02356083],"study_design_scores_gemma":[6.180877e-7,0.000001591868,0.00008104242,2.191648e-7,9.929504e-7,6.81648e-7,4.553218e-7,0.9997208,0.00007425036,0.000105417,0.00001344047,4.975566e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5190009,0.0008907513,0.473594,0.0006412608,0.0001901755,0.00002943579,0.0003442766,0.0007208579,0.004588313],"genre_scores_gemma":[0.9899825,0.00009247709,0.008668179,0.00004125444,0.00002896534,0.00001345812,0.0001108312,0.0000134518,0.001048915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02031038,"threshold_uncertainty_score":0.04038429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0558563803721759,"score_gpt":0.3099414843660763,"score_spread":0.2540851039939004,"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."}}