{"id":"W3012120688","doi":"10.1101/2020.03.12.988626","title":"Site-specific machine learning predictive fertilization models for potato crops in Eastern Canada","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Potato Plant Research","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada; Université Laval","funders":"","keywords":"Soil water; Yield (engineering); Mathematics; Fertilizer; Nutrient management; Random forest; Crop; Agricultural engineering; Predictive modelling; Agronomy; Nutrient; Machine learning; Statistics; Environmental science; Computer science; Soil science; Ecology; Biology; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004223524,0.0004361407,0.0004961683,0.00005632439,0.0002069683,0.0002274035,0.000603722,0.0003249263,0.00005427791],"category_scores_gemma":[0.0002210963,0.0002495023,0.000101825,0.0005385397,0.00004925637,0.0001364712,0.0004630834,0.0008971528,0.00001392488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004741188,"about_ca_system_score_gemma":0.0003420723,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.08413021,"about_ca_topic_score_gemma":0.09993524,"domain_scores_codex":[0.9969825,0.0002242155,0.0004755794,0.00106604,0.0005678548,0.0006838519],"domain_scores_gemma":[0.9986567,0.0002521182,0.000245126,0.0001811696,0.0003309176,0.0003338952],"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":[0.0004651316,0.000135139,0.1101111,0.0002803816,0.00007173221,0.0001366978,0.00003602514,0.008396276,0.8793452,0.0003308908,0.0006540485,0.00003731153],"study_design_scores_gemma":[0.0009326421,0.0003496283,0.5472813,0.0005992209,0.00005084628,4.480062e-8,0.00002521984,0.3686378,0.05129243,0.00003797961,0.02912035,0.001672601],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942243,0.0009387748,0.0006970087,0.0007288164,0.000264328,0.001180614,0.001768404,0.0001857421,0.00001200081],"genre_scores_gemma":[0.9987295,0.0002239451,0.0003231005,0.0001248379,0.0003017845,0.0002517499,0.00002073087,0.0000133673,0.00001097867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8280528,"threshold_uncertainty_score":0.9999957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03466532477096108,"score_gpt":0.2151787151694039,"score_spread":0.1805133903984428,"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."}}