{"id":"W4409537335","doi":"10.1371/journal.pwat.0000307","title":"Training for the test: Using multi-objective training to improve ANN ensemble forecasts of household residual chlorine in emergencies","year":2025,"lang":"en","type":"article","venue":"PLOS Water","topic":"Water Systems and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Achmea; Grand Challenges Canada; Natural Sciences and Engineering Research Council of Canada; Enhancing Learning and Research for Humanitarian Assistance","keywords":"Training (meteorology); Residual; Test (biology); Training set; Artificial intelligence; Machine learning; Computer science; Statistics; Mathematics; Meteorology; Algorithm; Geology; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001947819,0.00124123,0.0007172191,0.0004489177,0.0002550441,0.0005984502,0.000711374,0.0008079492,0.0008373329],"category_scores_gemma":[0.004350762,0.0003563065,0.0005929554,0.0003375375,0.0002600696,0.000878571,0.0005993516,0.001045174,0.0001778274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004738136,"about_ca_system_score_gemma":0.0006794105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01099315,"about_ca_topic_score_gemma":0.009050494,"domain_scores_codex":[0.9997137,0.0001089476,0.00001925755,0.00006923136,0.00004483536,0.00004391729],"domain_scores_gemma":[0.9986696,0.0007512351,0.000126032,0.0001153892,0.0002913485,0.00004643243],"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":[0.00008913207,0.0000721596,0.002495751,0.0000220444,0.00004835611,0.00002078793,0.00001981671,0.9602119,0.00112535,0.0001520852,0.0003287125,0.03541387],"study_design_scores_gemma":[0.000003959632,0.00003386376,0.0003712302,0.000003607177,0.000004906879,0.000002258206,0.000003343624,0.9988698,0.0005493167,0.00009693738,0.00005793841,0.000002811797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6616944,0.000751292,0.3304703,0.0005479014,0.000123639,0.0001082589,0.0002669895,0.001715479,0.004321784],"genre_scores_gemma":[0.9608613,0.00008084489,0.03780957,0.0001151636,0.00001868949,0.00003988624,0.000266848,0.00004959531,0.0007581841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01099315,"threshold_uncertainty_score":0.02185833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09134220930533829,"score_gpt":0.2589263150914314,"score_spread":0.1675841057860931,"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."}}