{"id":"W3196409416","doi":"10.1016/j.envpol.2021.118116","title":"Real-time prediction of river chloride concentration using ensemble learning","year":2021,"lang":"en","type":"article","venue":"Environmental Pollution","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; McMaster University","keywords":"Chloride; Multilayer perceptron; Water quality; Artificial neural network; Machine learning; Perceptron; Artificial intelligence; Computer science; Environmental science; Hydrology (agriculture); Statistics; Mathematics; Chemistry; Geology; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001864427,0.0001240539,0.0001378671,0.00001449203,0.0001841887,0.00001083478,0.00006324911,0.0001003814,0.002223215],"category_scores_gemma":[0.00004456356,0.0001322071,0.00006410028,0.000134676,0.0002977545,0.0002363081,0.000120252,0.0001283252,0.0003506723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004952762,"about_ca_system_score_gemma":0.000009111634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001492249,"about_ca_topic_score_gemma":0.00000175856,"domain_scores_codex":[0.9987357,0.0001250417,0.0002595395,0.0003112984,0.0003317068,0.0002366686],"domain_scores_gemma":[0.9996093,0.00002018023,0.0001483066,0.0001473991,0.000002127376,0.00007269557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001981754,0.00007121231,0.02003263,0.000002186066,0.000006720458,0.000006143953,0.0001858699,0.1362581,0.8421454,0.000008453751,0.00003686924,0.00122657],"study_design_scores_gemma":[0.0006139642,0.0001938449,0.2249454,0.00003327829,0.00005997374,0.00006526282,0.00006716661,0.2072531,0.5652711,0.0003167907,0.0009429537,0.0002371304],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950418,0.00001465128,0.001261033,0.00004227275,0.0001104583,0.0001005582,0.0000192412,0.00005447814,0.003355472],"genre_scores_gemma":[0.9966041,0.00004199561,0.002461598,0.00003463167,0.00005494605,0.000002179702,0.00007780156,0.00001448642,0.0007082791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2768743,"threshold_uncertainty_score":0.9986889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0137062472216365,"score_gpt":0.2087535356576011,"score_spread":0.1950472884359646,"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."}}