{"id":"W2015037454","doi":"10.1016/j.agrformet.2010.11.012","title":"Crop yield forecasting on the Canadian Prairies using MODIS NDVI data","year":2011,"lang":"en","type":"article","venue":"Agricultural and Forest Meteorology","topic":"Remote Sensing in Agriculture","field":"Environmental Science","cited_by":508,"is_retracted":false,"has_abstract":false,"ca_institutions":"Natural Resources Canada; University of Manitoba","funders":"","keywords":"Normalized Difference Vegetation Index; Moderate-resolution imaging spectroradiometer; Environmental science; Crop yield; Advanced very-high-resolution radiometer; Spectroradiometer; Remote sensing; Growing season; Yield (engineering); Linear regression; Mathematics; Leaf area index; Geography; Agronomy; Statistics; Reflectivity","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":[0.0002076708,0.0001925026,0.0001589801,0.00001900583,0.0006367431,0.00005432756,0.0004577517,0.0001521767,0.0001864259],"category_scores_gemma":[0.0001886292,0.00008299012,0.00003229978,0.0001859886,0.0004071673,0.0002328887,0.0003400305,0.0002466366,0.00007969746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008457541,"about_ca_system_score_gemma":0.00001242635,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.242095,"about_ca_topic_score_gemma":0.7560141,"domain_scores_codex":[0.9987769,0.00007149068,0.0001609616,0.0004052774,0.000150466,0.0004348676],"domain_scores_gemma":[0.9992774,0.0001169588,0.00008594736,0.0003437028,0.00001502922,0.0001610129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002822477,0.0003103782,0.6364496,0.00004943096,0.00055301,0.0004787904,0.02364947,0.008027152,0.030965,0.02427191,0.2232679,0.05169505],"study_design_scores_gemma":[0.0001088142,0.0001694931,0.9863661,0.00001942186,0.00006007535,0.000586233,0.0004257792,0.004961221,0.000288662,0.001390692,0.005301946,0.0003215912],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9752991,0.00003439193,0.00001193134,0.001991345,0.0001733456,0.0002054057,0.00001647793,0.00002557891,0.02224238],"genre_scores_gemma":[0.997179,0.000005931361,0.001641196,0.0007060907,0.00009605368,0.000001616477,0.00003010649,0.000006985993,0.0003329969],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5139191,"threshold_uncertainty_score":0.762952,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1255570229242833,"score_gpt":0.2233313764835892,"score_spread":0.09777435355930589,"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."}}