{"id":"W4292775020","doi":"10.31223/x55m05","title":"Köppen meets Neural Network: Revision of the Köppen Climate Classification by Neural Networks","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Climate variability and models","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Environment Research Council; U.S. Department of Energy","keywords":"Climate change; Land cover; Pixel; Geography; Longitude; Artificial neural network; Climatology; Convolutional neural network; Computer science; Latitude; Climate zones; Remote sensing; Environmental science; Data mining; Meteorology; Artificial intelligence; Physical geography; Land use; Geology; Ecology","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":[0.003180439,0.001440913,0.00104167,0.003008506,0.0009195501,0.002404344,0.002593857,0.001939639,0.004112374],"category_scores_gemma":[0.009637088,0.0005824951,0.001210219,0.003551306,0.002045723,0.005721641,0.001828423,0.003965092,0.002457303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00243806,"about_ca_system_score_gemma":0.002305013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01256617,"about_ca_topic_score_gemma":0.006627628,"domain_scores_codex":[0.9980762,0.0004890524,0.0002246331,0.0005400951,0.000581998,0.00008796573],"domain_scores_gemma":[0.9972656,0.0007988355,0.0001328118,0.0003188158,0.001392451,0.00009151665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001735831,0.00005194739,0.001486739,0.000391947,0.0002049849,0.0002562083,0.0002115339,0.126308,0.001705029,0.2650783,0.03612724,0.5680045],"study_design_scores_gemma":[0.00001894057,0.00004811135,0.0009552781,0.0001826441,0.0000602007,0.000189597,0.00005038714,0.7065609,0.002787736,0.1898487,0.09919521,0.0001023385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00495462,0.006077267,0.9717501,0.003031464,0.003414695,0.0001306517,0.0006030353,0.0007051172,0.009332889],"genre_scores_gemma":[0.1435312,0.01261366,0.8073002,0.001664446,0.005170195,0.0005759415,0.001476647,0.0007373119,0.02693036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01256617,"threshold_uncertainty_score":0.02498609,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03575925213457617,"score_gpt":0.2715729293644835,"score_spread":0.2358136772299073,"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."}}