{"id":"W2804999555","doi":"10.1016/j.atmosres.2018.05.012","title":"Input selection and data-driven model performance optimization to predict the Standardized Precipitation and Evaporation Index in a drought-prone region","year":2018,"lang":"en","type":"article","venue":"Atmospheric Research","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; University of Toronto","funders":"World Meteorological Organization","keywords":"Evapotranspiration; Mean squared error; Precipitation; Environmental science; Linear regression; Support vector machine; Regression; Aridity index; Index (typography); Computer science; Statistics; Meteorology; Mathematics; Machine learning; Geography; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001583292,0.00008284416,0.0001052308,0.00001483107,0.0004069384,0.00006375184,0.0002042053,0.00008576856,0.00007519184],"category_scores_gemma":[0.0001680126,0.00006345873,0.000007257627,0.001061714,0.0002997356,0.000718431,0.0003259735,0.0001933616,0.00001956334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001411382,"about_ca_system_score_gemma":0.00003734031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004622939,"about_ca_topic_score_gemma":0.001509683,"domain_scores_codex":[0.9984418,0.0002847034,0.00017663,0.0004257705,0.0004292126,0.0002419236],"domain_scores_gemma":[0.9994578,0.00007170784,0.0000457902,0.0003046433,0.00005672127,0.00006337555],"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":[0.0002551997,0.00002454958,0.1664017,0.000005400572,0.000009386637,5.747585e-7,0.00166513,0.8182182,0.0001758618,0.000012107,0.0008395992,0.01239235],"study_design_scores_gemma":[0.0003022898,0.0002097936,0.06500805,0.000008708756,0.000008293747,0.000003273575,0.00007246427,0.9338034,0.00004040047,0.0002313656,0.0002477051,0.00006419821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8757915,0.00002330276,0.1219089,0.0008717342,0.00001424187,0.0004488624,0.000001314168,0.00001552686,0.0009245432],"genre_scores_gemma":[0.9882995,0.0001840438,0.01099368,0.00006588856,0.0000428489,0.00006008923,0.00001853846,0.000008743055,0.0003266297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1155853,"threshold_uncertainty_score":0.3129882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03993720631370232,"score_gpt":0.3255809127824364,"score_spread":0.285643706468734,"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."}}