{"id":"W3174656366","doi":"10.1038/s41545-021-00125-2","title":"Forecasting point-of-consumption chlorine residual in refugee settlements using ensembles of artificial neural networks","year":2021,"lang":"en","type":"article","venue":"npj Clean Water","topic":"Water Systems and Optimization","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Centre for Global Health Research; York University","funders":"Achmea; York University; Natural Sciences and Engineering Research Council of Canada; Enhancing Learning and Research for Humanitarian Assistance; United States Agency for International Development","keywords":"Residual; Artificial neural network; Consumption (sociology); Human settlement; Point (geometry); Refugee; Chlorine; Point estimation; Environmental science; Water supply; Computer science; Environmental engineering; Engineering; Statistics; Artificial intelligence; Geography; Mathematics; Waste management; Materials science; Algorithm","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":[0.0001724414,0.00009965916,0.0001825842,0.00008629011,0.00002267866,0.0000170888,0.00004608183,0.00006595959,0.00004615298],"category_scores_gemma":[0.000008258215,0.00008727839,0.00003439523,0.00008714713,0.00001373048,0.0001355245,0.00003988743,0.00008371732,0.000001573551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003614494,"about_ca_system_score_gemma":0.000003982289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003463726,"about_ca_topic_score_gemma":0.0003033159,"domain_scores_codex":[0.9990823,0.00003564196,0.0004406033,0.000124445,0.0001039985,0.0002130482],"domain_scores_gemma":[0.9997442,0.00001255262,0.00004405298,0.00012749,0.00004883593,0.00002283344],"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":[0.00002297299,0.00001607446,0.008625975,0.000145903,0.00001834105,0.00001735793,0.000517956,0.9686898,0.01948256,0.00001455792,0.00005076075,0.00239773],"study_design_scores_gemma":[0.0002316563,0.00001355167,0.001193036,0.0001018205,0.00001082154,0.000009744479,0.00005564461,0.7722088,0.2260359,0.0000246843,0.00002520723,0.00008913908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940309,0.00004017621,0.005304206,0.00001125529,0.0004355911,0.00008450521,0.000005839438,0.00002750655,0.00006001324],"genre_scores_gemma":[0.998428,0.00000467075,0.001282045,0.000005203843,0.0001591974,0.000001939095,0.000060133,0.00002535872,0.00003346155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2065534,"threshold_uncertainty_score":0.3559109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04224455865913453,"score_gpt":0.2397618572319719,"score_spread":0.1975172985728373,"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."}}