{"id":"W2202019762","doi":"10.1016/j.agrformet.2015.11.003","title":"Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods","year":2015,"lang":"en","type":"article","venue":"Agricultural and Forest Meteorology","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":279,"is_retracted":false,"has_abstract":false,"ca_institutions":"Statistics Canada; University of Victoria; Pacific Institute for Climate Solutions; Agriculture and Agri-Food Canada; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Aeronautics and Space Administration","keywords":"Normalized Difference Vegetation Index; Moderate-resolution imaging spectroradiometer; Enhanced vegetation index; Environmental science; Vegetation (pathology); Crop yield; Linear regression; Leaf area index; Mathematics; Statistics; Satellite; Vegetation Index; Agronomy","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004723656,0.0001826414,0.0001732295,0.00002362022,0.0005524278,0.00009178404,0.00009889869,0.0001619212,0.00001173037],"category_scores_gemma":[0.0006278185,0.00008366689,0.00002533282,0.0001774464,0.0003094805,0.0001409769,0.00008151377,0.0003487358,0.00001941299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008200769,"about_ca_system_score_gemma":0.000009387449,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.07562934,"about_ca_topic_score_gemma":0.422098,"domain_scores_codex":[0.9987796,0.0002972827,0.0001547654,0.0002961112,0.0001584538,0.0003137729],"domain_scores_gemma":[0.9991821,0.0003852426,0.0001176431,0.00007709947,0.0000230743,0.0002148252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002880575,0.00009811312,0.494032,0.00006492458,0.0002939439,0.0001300413,0.03495343,0.01734534,0.104404,0.00304918,0.07268578,0.2726552],"study_design_scores_gemma":[0.0003722825,0.0006607885,0.956475,0.000028861,0.00006277169,0.0007077964,0.0009820843,0.008572171,0.001495583,0.001679009,0.02854658,0.0004171397],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9865864,0.0003265975,0.00003802511,0.006214429,0.0001065755,0.0001882591,0.000002247644,0.00003154052,0.006505913],"genre_scores_gemma":[0.9952667,0.00001739821,0.003279615,0.0006299473,0.00005270592,0.000002006405,0.00002665921,0.000006723666,0.0007181995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4624429,"threshold_uncertainty_score":0.9305261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04092730642546493,"score_gpt":0.2379158111462246,"score_spread":0.1969885047207597,"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."}}