{"id":"W3128744684","doi":"10.2166/hydro.2021.093","title":"Ensemble-based machine learning approach for improved leak detection in water mains","year":2021,"lang":"en","type":"article","venue":"Journal of Hydroinformatics","topic":"Water Systems and Optimization","field":"Engineering","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"FedDev Ontario","keywords":"False positive paradox; Gradient boosting; Ensemble learning; Boosting (machine learning); Computer science; Artificial intelligence; Leak; Classifier (UML); Binary classification; Decision tree; Machine learning; Pattern recognition (psychology); Leak detection; Support vector machine; Random forest; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001888139,0.000787973,0.001363376,0.001285077,0.0004342261,0.0006639463,0.0008363728,0.0006982401,0.0008896967],"category_scores_gemma":[0.002533918,0.0003187432,0.0007814115,0.0008582809,0.0002066271,0.000825672,0.0007517461,0.0009717168,0.0003444264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004339282,"about_ca_system_score_gemma":0.0005374569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00344749,"about_ca_topic_score_gemma":0.003919428,"domain_scores_codex":[0.9993107,0.0002094846,0.00004522401,0.0001420057,0.0002085509,0.00008395343],"domain_scores_gemma":[0.9986926,0.0004888838,0.0001134882,0.0001175139,0.0005375281,0.00005002525],"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":[0.0001846852,0.0002574454,0.006604156,0.00005757553,0.0002061883,0.0001002985,0.00006858743,0.5963517,0.01032306,0.00127445,0.002002366,0.3825695],"study_design_scores_gemma":[0.000001698789,0.00002012699,0.0004075746,0.000002064399,0.000008618774,0.000007555312,0.000004368965,0.9982334,0.0008796696,0.0002728649,0.0001591284,0.000002769339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09044963,0.0004886856,0.9056275,0.0002164426,0.00007624932,0.00004692171,0.0001116223,0.001543597,0.001439263],"genre_scores_gemma":[0.8387553,0.0001708885,0.1589916,0.0001017295,0.00007645814,0.00006357818,0.0003039087,0.00005830224,0.0014783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00344749,"threshold_uncertainty_score":0.009985566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007588827226263526,"score_gpt":0.1823657255013359,"score_spread":0.1747768982750724,"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."}}