{"id":"W4313897362","doi":"10.1007/s10661-022-10870-7","title":"Prediction of water quality extremes with composite quantile regression neural network","year":2023,"lang":"en","type":"article","venue":"Environmental Monitoring and Assessment","topic":"Hydrological Forecasting Using AI","field":"Environmental Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"WSP (Canada)","funders":"Water Research Foundation","keywords":"Quantile regression; Quantile; Statistics; Turbidity; Regression; Linear regression; Water quality; Predictability; Regression analysis; Artificial neural network; Environmental science; Econometrics; Mathematics; Computer science; Machine learning; Geology","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":[0.0003477174,0.0001572469,0.000176113,0.00002010673,0.0002402823,0.00002119032,0.00009075339,0.00005398674,0.0001319697],"category_scores_gemma":[0.000002252474,0.00009871555,0.00003340584,0.00009040517,0.0002169472,0.0001267159,0.0002674773,0.0001584426,0.00003394976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009529723,"about_ca_system_score_gemma":0.00000147206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007076022,"about_ca_topic_score_gemma":7.850871e-7,"domain_scores_codex":[0.9986085,0.0001030638,0.0002375605,0.0003274565,0.0004066757,0.0003167021],"domain_scores_gemma":[0.9996003,0.0000489886,0.00008268999,0.0001778065,0.000001007961,0.00008923232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002598855,0.00005969977,0.7986959,0.000007939082,0.000009907486,0.000007173222,0.0001301147,0.03904328,0.1565986,0.000002332861,0.00004992085,0.005369151],"study_design_scores_gemma":[0.0002885146,0.0002374945,0.9764993,0.00005461718,0.00001538173,0.000005902863,0.00008234773,0.00818984,0.01395857,0.00006308758,0.0004814905,0.0001235046],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989325,0.00002368169,0.00005740709,0.00009959748,0.0002196687,0.0001251242,0.00001010551,0.00009187949,0.0004399823],"genre_scores_gemma":[0.9975449,0.00004202027,0.002031153,0.0000079283,0.00009581215,0.00001549543,0.00003120241,0.00001531792,0.0002161463],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1778034,"threshold_uncertainty_score":0.4025503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04599524938881236,"score_gpt":0.2913978143730039,"score_spread":0.2454025649841915,"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."}}