{"id":"W4402913047","doi":"10.1016/j.jhydrol.2024.132115","title":"Enhancing water quality prediction with advanced machine learning techniques: An extreme gradient boosting model based on long short-term memory and autoencoder","year":2024,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Guangxi Key Laboratory of Clean Pulp and Papermaking and Pollution Control","keywords":"Autoencoder; Gradient boosting; Extreme learning machine; Computer science; Term (time); Artificial intelligence; Boosting (machine learning); Machine learning; Long short term memory; Artificial neural network; Recurrent neural network; Random forest","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":[0.0007334525,0.0001537365,0.0002690723,0.0002427609,0.00007543147,0.00004462171,0.0000588723,0.00009399249,0.00001297977],"category_scores_gemma":[0.00001592108,0.0001047296,0.00005549425,0.00005578253,0.00002369163,0.0002644092,0.000008326407,0.0005405936,9.491143e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001000947,"about_ca_system_score_gemma":0.00001785597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007174086,"about_ca_topic_score_gemma":0.00006957334,"domain_scores_codex":[0.9988857,0.0001107849,0.0004499829,0.0001624688,0.0001773639,0.000213681],"domain_scores_gemma":[0.9996639,0.0000516299,0.00005508478,0.00009867144,0.00003961986,0.00009109359],"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":[0.0001550296,0.00001564355,0.0006075873,0.0001022666,0.00004457755,0.0000765067,0.0004944979,0.7765599,0.2105957,0.000003872258,0.000002213626,0.01134221],"study_design_scores_gemma":[0.0003589908,0.0007671276,0.0002406533,0.000186135,0.00003474922,0.0003856315,0.00004409098,0.9740821,0.02365719,0.00002135983,0.0001102101,0.000111805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7551423,0.0003474539,0.2435542,0.00007326111,0.0002678455,0.00009895231,0.000001726615,0.000250201,0.000264113],"genre_scores_gemma":[0.9985034,0.00002225656,0.00119286,0.00004472982,0.0001415554,0.00001101672,0.000003196931,0.00003425501,0.0000467552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2433611,"threshold_uncertainty_score":0.4270747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01297712571357867,"score_gpt":0.2466267340952923,"score_spread":0.2336496083817136,"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."}}