{"id":"W4388141454","doi":"10.2166/hydro.2023.122","title":"A methodology for integrating time-lagged rainfall and river flow data into machine learning models to improve prediction of quality parameters of raw water supplying a treatment plant","year":2023,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Turbidity; Water quality; Environmental science; Watershed; Hydrology (agriculture); Rank correlation; Environmental engineering; Statistics; Machine learning; Computer science; Mathematics; Engineering; Ecology","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":[],"consensus_categories":[],"category_scores_codex":[0.003135978,0.0001427999,0.0004830437,0.000129372,0.0000942164,0.00001707747,0.0002550696,0.00007541509,0.00001672038],"category_scores_gemma":[0.00087778,0.00008829089,0.00008478783,0.0001291999,0.0001266871,0.0004350958,0.000329502,0.0001708941,0.000005370295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001142824,"about_ca_system_score_gemma":0.00001528015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002315077,"about_ca_topic_score_gemma":0.00002818306,"domain_scores_codex":[0.9981085,0.0001839105,0.001068385,0.0001290647,0.0002791955,0.0002309313],"domain_scores_gemma":[0.9983274,0.0007307889,0.0006001921,0.000215066,0.0000226107,0.0001038838],"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":[0.0002919986,0.00004829448,0.0005705375,0.0001051322,0.00008587362,0.000002979995,0.02506815,0.8775083,0.08493903,0.000006063891,0.0001053567,0.0112683],"study_design_scores_gemma":[0.0007319027,0.001369537,0.00006225103,0.00006051446,0.0000715013,0.0000361947,0.0003296544,0.9854041,0.01027705,0.001444904,0.0001318842,0.00008051128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708873,0.000007242043,0.02844895,0.0001456518,0.0000675129,0.0002785472,0.0001081655,0.00001616701,0.00004049356],"genre_scores_gemma":[0.7339584,0.00001755551,0.2658275,0.00004861644,0.00001377366,0.000004563843,0.00009314981,0.000009857318,0.00002658875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2373786,"threshold_uncertainty_score":0.3600398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1692428248558538,"score_gpt":0.3211880442691362,"score_spread":0.1519452194132824,"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."}}