{"id":"W4319440180","doi":"10.1002/for.2956","title":"Using a machine learning approach and big data to augment WASDE forecasts: Empirical evidence from US corn yield","year":2023,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Climate change impacts on agriculture","field":"Agricultural and Biological Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Yield (engineering); Computer science; Machine learning; Agriculture; Econometrics; Economics; Geography","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":[0.00106382,0.0001927599,0.000344242,0.00005258692,0.0002661595,0.0002067322,0.0004891723,0.00009860023,0.00004904093],"category_scores_gemma":[0.002213059,0.00007137268,0.0000750935,0.0007711896,0.00002935455,0.0003918188,0.0006183055,0.0004195382,0.000004732884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007554871,"about_ca_system_score_gemma":0.00001547962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005575506,"about_ca_topic_score_gemma":0.0006197842,"domain_scores_codex":[0.9982573,0.00009407978,0.0004759413,0.0003260502,0.0004467812,0.0003998197],"domain_scores_gemma":[0.9981112,0.0009431246,0.0004188748,0.00008658558,0.0001304555,0.0003097635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002956977,0.0001064656,0.2371841,0.00005873305,0.0001107157,0.0002423953,0.002279511,0.001976169,0.471929,8.435457e-7,0.004281299,0.2815351],"study_design_scores_gemma":[0.0009227681,0.002658181,0.4921993,0.004309275,0.0003526848,0.002543025,0.009100562,0.4714475,0.004067425,0.0001859802,0.01093449,0.001278828],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970146,0.0005799275,0.0001156746,0.001686673,0.0002447652,0.0001517631,0.0001315948,0.00003843147,0.00003653305],"genre_scores_gemma":[0.9942588,0.0001705041,0.003711907,0.0002293659,0.001501596,0.000001580766,0.00008172325,0.000003312989,0.00004117104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4694713,"threshold_uncertainty_score":0.2910494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6783027688674481,"score_gpt":0.3642247543382261,"score_spread":0.314078014529222,"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."}}