{"id":"W2950398529","doi":"10.1145/3485128","title":"Tackling Climate Change with Machine Learning","year":2022,"lang":"en","type":"preprint","venue":"ACM Computing Surveys","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Pacific Northwest National Laboratory; Lawrence Livermore National Laboratory; University of California, Davis; Universitetet i Oslo; Carnegie Mellon University; University College London; Eidgenössische Technische Hochschule Zürich; Dalhousie University; National Science Foundation; Imperial College London; Natural Sciences and Engineering Research Council of Canada; DeepMind; Université du Québec à Rimouski; University of Colorado Boulder; Universität Zürich; University of Pennsylvania; Yale University; U.S. Department of Energy","keywords":"Climate change; Wonder; Computer science; Artificial intelligence; Greenhouse gas; Humanity; Machine learning; Data science; Political science; Psychology","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.006457798,0.0004124514,0.0004394734,0.00006777236,0.0009735124,0.000127335,0.001017338,0.0001451404,0.0005903584],"category_scores_gemma":[0.0004076403,0.0004000985,0.0001115751,0.0002978211,0.0001159726,0.00008623245,0.01003405,0.001985494,0.0001088357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003105157,"about_ca_system_score_gemma":0.00001424894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004439126,"about_ca_topic_score_gemma":0.0001009766,"domain_scores_codex":[0.9956644,0.0016044,0.0004209916,0.0009165811,0.0006658567,0.0007278355],"domain_scores_gemma":[0.9979274,0.0005893267,0.0005025484,0.0008402296,0.00001500241,0.0001254406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008753197,0.00003788833,0.7812269,0.00008336979,0.00002445958,0.00003453082,0.001833919,0.1399725,0.00001238797,0.000005243063,0.00002559114,0.07673444],"study_design_scores_gemma":[0.0005449411,0.0003223459,0.7500509,0.0006050249,0.00007212527,0.00003765328,0.0004755004,0.2415737,0.00005672484,0.0002525845,0.00440255,0.001605924],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9887103,0.0001969959,0.005443333,0.0002001349,0.001202705,0.0003765002,0.00003562455,0.0005899025,0.003244474],"genre_scores_gemma":[0.9873968,0.00004131343,0.01144269,0.00006825268,0.0005066094,0.0000284493,0.0002026422,0.0000903633,0.0002228408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1016012,"threshold_uncertainty_score":0.9998451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06174498602231311,"score_gpt":0.292308745863756,"score_spread":0.2305637598414429,"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."}}