{"id":"W4404769381","doi":"10.1016/j.dche.2024.100202","title":"Exploring spatial and temporal importance of input features and the explainability of machine learning-based modelling of water distribution systems","year":2024,"lang":"en","type":"article","venue":"Digital Chemical Engineering","topic":"Water Systems and Optimization","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Distribution (mathematics); Artificial intelligence; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001286321,0.0001143959,0.0002317982,0.00003487168,0.000009099263,0.00003894706,0.00004237069,0.00004481899,3.56995e-7],"category_scores_gemma":[0.00002979617,0.00007608434,0.00004233051,0.00006935785,0.00004675171,0.0002135528,0.00002678669,0.0001159924,5.131648e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002148281,"about_ca_system_score_gemma":0.000003442964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006307462,"about_ca_topic_score_gemma":0.000001023372,"domain_scores_codex":[0.9993623,0.00000532686,0.0003072905,0.0001114213,0.000105087,0.0001085902],"domain_scores_gemma":[0.9997665,0.00006608095,0.00002452781,0.00008285439,0.00003062625,0.00002940029],"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":[0.00002030666,0.00000443719,0.001198626,0.001902862,0.00002438675,8.89243e-7,0.0003125947,0.9930494,0.003213233,0.0001894297,0.00000171844,0.00008212963],"study_design_scores_gemma":[0.0002002422,0.00001009482,0.00004461767,0.0002075396,0.00001000716,0.000004158122,0.00002134313,0.9273511,0.07202928,0.00001040177,0.00003555103,0.0000756638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.768993,0.001281195,0.2294002,0.000007226757,0.00008116441,0.0001057052,0.00004236288,0.0000711636,0.00001791971],"genre_scores_gemma":[0.9997483,0.00001618191,0.0000732284,1.659415e-7,0.00003083711,0.00001626333,0.00009293641,0.00001855294,0.000003549557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2307553,"threshold_uncertainty_score":0.3102629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0130145493800979,"score_gpt":0.1665687759123022,"score_spread":0.1535542265322043,"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."}}