{"id":"W4322212235","doi":"10.5194/egusphere-egu23-16656","title":"Optimizing chlorination for water safety and acceptability in emergency water supplies in humanitarian crises using a deep composite neural network","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research; York University","funders":"","keywords":"Refugee; Human settlement; Population; Water treatment; Water supply; Environmental science; Groundwater; Water resource management; Environmental engineering; Business; Geography; Environmental health; Engineering; Waste management; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005069074,0.00096899,0.0005434932,0.0004106001,0.0003566808,0.000734993,0.0008022151,0.001212098,0.001467737],"category_scores_gemma":[0.001701112,0.0004701039,0.000608802,0.0002734353,0.0004546441,0.000666291,0.0006790963,0.001331979,0.0001964945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001448117,"about_ca_system_score_gemma":0.00150748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03085737,"about_ca_topic_score_gemma":0.03121082,"domain_scores_codex":[0.9998203,0.00003915117,0.000009413402,0.00005784843,0.0000216883,0.00005163722],"domain_scores_gemma":[0.9995931,0.0002162288,0.00004273337,0.00001093574,0.0001036719,0.00003335189],"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":[0.000177698,0.0001903115,0.004994749,0.00005386073,0.00004999045,0.00008923105,0.000043446,0.9538285,0.001828489,0.0002853306,0.001128272,0.03733015],"study_design_scores_gemma":[0.000005382828,0.00002816438,0.0003877888,0.000003999308,0.000005282975,0.000002952073,0.00001377974,0.998861,0.0004045359,0.0002199946,0.00006387164,0.000003275891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7524152,0.0008591728,0.234474,0.001510036,0.0001474,0.0001960522,0.0005731102,0.002032204,0.00779276],"genre_scores_gemma":[0.9735551,0.0001171904,0.02287469,0.0002674889,0.00001738636,0.00008917329,0.0004182494,0.00003334775,0.002627452],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03085737,"threshold_uncertainty_score":0.06135547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05472478728018954,"score_gpt":0.3180183931314852,"score_spread":0.2632936058512956,"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."}}