{"id":"W4414998383","doi":"10.1016/j.jece.2025.119673","title":"Application of novel deep learning model for high-frequency water quality prediction in multi-station river networks","year":2025,"lang":"en","type":"article","venue":"Journal of environmental chemical engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Prince Edward Island","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Water quality; Mean squared error; Mean absolute percentage error; Deep learning; Artificial neural network; Watershed; Convolutional neural network; Water resources; Approximation error","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001819419,0.00009417343,0.0001535091,0.0001299266,0.00001061721,0.000004627785,0.00007876031,0.00008576975,0.000001532403],"category_scores_gemma":[0.00001365913,0.00009155664,0.00005737644,0.00005359458,0.00001618224,0.0001492841,0.00001920389,0.0002015533,1.746346e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002039549,"about_ca_system_score_gemma":0.000001641552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002236956,"about_ca_topic_score_gemma":3.692967e-7,"domain_scores_codex":[0.9992537,0.000004183369,0.0004481737,0.00008000522,0.00009632244,0.0001175886],"domain_scores_gemma":[0.9998187,0.0000242574,0.00005982922,0.000061313,0.000008311934,0.00002756917],"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":[0.000008781108,0.00004616708,0.0002415869,0.00004959781,0.00001841249,9.184786e-8,0.00005685496,0.6178146,0.3795757,0.0001167225,0.000009346769,0.002062131],"study_design_scores_gemma":[0.0007872171,0.00001254685,0.003995892,0.00003795294,0.00001990357,8.047922e-7,0.00001338115,0.9514771,0.04353097,0.00002841185,0.00002890224,0.0000668848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1805867,0.00006288865,0.8190134,0.000008242402,0.00007293883,0.0001270728,0.000006392718,0.0001101086,0.00001229743],"genre_scores_gemma":[0.9556792,0.00005444961,0.04416246,0.000007061045,0.0000242237,0.00002363713,0.00002757194,0.00001398958,0.000007385899],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7750925,"threshold_uncertainty_score":0.3733571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00823486197017627,"score_gpt":0.2158357249502539,"score_spread":0.2076008629800777,"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."}}