{"id":"W4391138050","doi":"10.1007/s11042-024-18142-x","title":"An automatic ensemble machine learning for wheat yield prediction in Africa","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Gradient boosting; Computer science; Food security; Machine learning; Support vector machine; Random forest; Agriculture; Ensemble forecasting; Usability; Artificial intelligence; Boosting (machine learning); Lasso (programming language); Productivity; Feature selection; Regression; Feature engineering; Crop yield; Decision tree; Agricultural engineering; Statistics; Mathematics; Deep learning; Agronomy; 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":[0.0001125355,0.00008373566,0.00009060821,0.00001282497,0.0001539334,0.0001332452,0.00006983535,0.000067455,0.00007839172],"category_scores_gemma":[0.00002133123,0.00003263108,0.00003435713,0.0002288994,0.00001720986,0.000158189,0.00001320633,0.00009892446,0.00002166692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013225,"about_ca_system_score_gemma":0.000003354781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005660321,"about_ca_topic_score_gemma":0.0002913612,"domain_scores_codex":[0.9994001,0.00001451236,0.0001356448,0.0002325298,0.00006337377,0.000153791],"domain_scores_gemma":[0.9995114,0.0003561208,0.00001696648,0.0000320605,0.00001800824,0.00006543066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002900857,0.00007102704,0.002537248,0.00002066684,0.000005015653,5.010683e-7,0.0002487845,0.000021131,0.1874913,0.0003006065,0.001158708,0.8081421],"study_design_scores_gemma":[0.000216339,0.0003478455,0.1398367,0.0001092933,0.00004273933,0.000009385623,0.000590853,0.2643822,0.00313646,0.001169411,0.5898462,0.0003125113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862521,0.002624067,0.002153507,0.003526385,0.0001616503,0.002025586,0.0004453798,0.0006557064,0.002155649],"genre_scores_gemma":[0.9970442,0.00007820385,0.0005835001,0.00003979568,0.0004307905,0.0008395027,0.0004733004,0.000001259877,0.0005094581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8078296,"threshold_uncertainty_score":0.1330657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03218447165590507,"score_gpt":0.2400707143767903,"score_spread":0.2078862427208852,"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."}}