{"id":"W3205105141","doi":"10.1007/s10705-021-10170-5","title":"Machine learning-based canola yield prediction for site-specific nitrogen recommendations","year":2021,"lang":"en","type":"article","venue":"Nutrient Cycling in Agroecosystems","topic":"Nitrogen and Sulfur Effects on Brassica","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; Dalhousie University; Université Laval; McGill University; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada","keywords":"Canola; Mathematics; Yield (engineering); Random forest; Environmental science; Predictive modelling; Production (economics); Crop yield; Machine learning; Agricultural engineering; Agronomy; Statistics; Computer science; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004847248,0.000697796,0.0005420521,0.0009270785,0.0002385585,0.0004393323,0.000597607,0.0006439249,0.00163835],"category_scores_gemma":[0.001007069,0.0001848626,0.0004591636,0.0006643099,0.0001055807,0.0004155361,0.0002601467,0.0005052935,0.0005804808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006330757,"about_ca_system_score_gemma":0.0006771855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01462392,"about_ca_topic_score_gemma":0.01803982,"domain_scores_codex":[0.9998708,0.00002087779,0.000009271287,0.00005333345,0.00002095741,0.00002469944],"domain_scores_gemma":[0.9995911,0.0002314073,0.00003875637,0.00002251847,0.00009335329,0.0000230082],"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":[0.0005438433,0.0006821607,0.03316011,0.0000957776,0.0001989988,0.0001148681,0.00002333054,0.6831172,0.00883305,0.0004809839,0.003671923,0.2690778],"study_design_scores_gemma":[0.000005300893,0.00002125704,0.00178011,0.000002519462,0.000011431,0.000005668634,0.000004832534,0.9970949,0.0007712824,0.0001699951,0.0001295941,0.000003070204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8510045,0.001124498,0.1381109,0.0005227578,0.00007967875,0.00008488807,0.002374807,0.002794861,0.003903069],"genre_scores_gemma":[0.9795775,0.0001436347,0.01667517,0.00005788492,0.00002209608,0.00003788547,0.001614033,0.00002431482,0.001847445],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01462392,"threshold_uncertainty_score":0.02907759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01578510559073297,"score_gpt":0.2456558468234983,"score_spread":0.2298707412327653,"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."}}