{"id":"W4379383191","doi":"10.1016/j.scitotenv.2023.164660","title":"Machine and deep learning for modelling heat-health relationships","year":2023,"lang":"en","type":"article","venue":"The Science of The Total Environment","topic":"Climate Change and Health Impacts","field":"Environmental Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institut National de Santé Publique du Québec; Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut National de Santé Publique du Québec","keywords":"Generalized additive model; Distributed lag; Multilayer perceptron; Linear model; Population; Decision tree; Gradient boosting; Random forest; Environmental science; Machine learning; Generalized linear model; Artificial intelligence; Statistics; Computer science; Mathematics; Artificial neural network; Environmental health; Medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001195527,0.0008177496,0.0009774729,0.0004925911,0.0003775958,0.000950437,0.001211199,0.00187304,0.002493179],"category_scores_gemma":[0.004201111,0.0005277047,0.0007254508,0.000707985,0.0008154717,0.001095479,0.001040194,0.002131511,0.0002657981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001383177,"about_ca_system_score_gemma":0.00107297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02004079,"about_ca_topic_score_gemma":0.01681348,"domain_scores_codex":[0.9997485,0.00009514869,0.00001556933,0.00005789842,0.00003939197,0.0000433011],"domain_scores_gemma":[0.9981543,0.001457691,0.0001202857,0.0000708324,0.0001386518,0.00005821693],"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":[0.00002431128,0.00002675179,0.0006329233,0.00003015781,0.00003042964,0.00002039933,0.00001208111,0.9782284,0.0001806882,0.005847872,0.0006262147,0.01433965],"study_design_scores_gemma":[0.000001204621,0.000002333881,0.00004789085,0.000002004888,0.000001602264,0.000001291053,0.000001048985,0.9960278,0.00002831476,0.003810952,0.00007448933,0.000001010469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08421857,0.003546675,0.9048317,0.002342566,0.000275574,0.00004962083,0.0007768277,0.0006809238,0.003277569],"genre_scores_gemma":[0.9175238,0.00105134,0.07290319,0.0003692382,0.0002098565,0.0001516178,0.0006130633,0.0000717783,0.007106096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02004079,"threshold_uncertainty_score":0.03984827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08721781408738608,"score_gpt":0.2924135081437363,"score_spread":0.2051956940563502,"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."}}