{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003425035,0.00009379645,0.0002002091,0.0001552151,0.00003784748,0.00005567958,0.00005761669,0.00006553093,0.000004032569],"category_scores_gemma":[0.0000293412,0.00007069162,0.0000836666,0.00009175782,0.000004341989,0.0002986797,0.000008744569,0.0002148023,0.000001540483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008818563,"about_ca_system_score_gemma":0.00001981926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002289211,"about_ca_topic_score_gemma":0.0001047467,"domain_scores_codex":[0.9991111,0.00001695726,0.0005714416,0.00003375516,0.00009672974,0.0001700565],"domain_scores_gemma":[0.9996876,0.00001943796,0.0001063324,0.00007002024,0.00007475058,0.00004190161],"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":[0.00001644732,0.00001523196,0.00003411351,0.000256838,0.00001871321,0.000002771507,0.0005431376,0.9899884,0.008423352,0.000002935419,0.00004793173,0.0006500538],"study_design_scores_gemma":[0.0009381579,0.00007524403,0.00001180052,0.00003200913,0.00001416074,0.00009278317,0.0001231851,0.9296972,0.06679722,0.00001630832,0.002114758,0.00008714241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.138267,0.0000735135,0.8600997,0.00003298249,0.0002795027,0.0001403839,0.000001913581,0.00002972689,0.001075264],"genre_scores_gemma":[0.9792369,0.00001466509,0.02046465,0.0000220924,0.00007930709,0.000004291309,0.00002764756,0.00001967801,0.0001307869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8409699,"threshold_uncertainty_score":0.2882721,"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."}}