{"id":"W3023399629","doi":"10.3390/agronomy10050622","title":"Disease Risk Forecasting with Bayesian Learning Networks: Application to Grape Powdery Mildew (Erysiphe necator) in Vineyards","year":2020,"lang":"en","type":"article","venue":"Agronomy","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"Environment and Climate Change Canada; Agriculture and Agri-Food Canada; University of Victoria","funders":"","keywords":"Powdery mildew; Fungicide; Bayesian network; Host (biology); Biology; Agronomy; Environmental science; Computer science; Ecology; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001589975,0.0001868239,0.0001912043,0.00001164894,0.0002667788,0.0001138558,0.0002379535,0.00005127244,0.0001136021],"category_scores_gemma":[0.0001409414,0.00006547584,0.00007331929,0.0008182588,0.00003842463,0.0002158237,0.0001046515,0.0002923457,0.00005487375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000417324,"about_ca_system_score_gemma":0.0000128297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005806114,"about_ca_topic_score_gemma":0.0007338844,"domain_scores_codex":[0.9984941,0.00011202,0.0002239819,0.00047545,0.0002310886,0.0004633597],"domain_scores_gemma":[0.9990889,0.0001432136,0.00007546526,0.0000474628,0.00007214832,0.0005728072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003417464,0.00008594262,0.56845,0.00002522518,0.00003068807,0.00003096013,0.000611037,0.0126902,0.008085634,0.000125402,0.0008077556,0.4087154],"study_design_scores_gemma":[0.0003162859,0.0005645308,0.9388586,0.00009082838,0.00003143293,0.000003106654,0.00138109,0.03444089,0.0002904391,0.00007318204,0.02341071,0.0005388743],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917164,0.000146328,0.00071663,0.006455222,0.0000117145,0.0005507836,0.00000707067,0.00008227236,0.0003135356],"genre_scores_gemma":[0.9986351,0.00003581132,0.0002033995,0.0004751082,0.000329983,0.0001333918,0.00009982944,0.000002155521,0.0000852086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4081765,"threshold_uncertainty_score":0.2670027,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01939424266526209,"score_gpt":0.2197767964263779,"score_spread":0.2003825537611158,"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."}}