{"id":"W3204546865","doi":"10.1109/ijcnn52387.2021.9534388","title":"Satellite Images and Deep Learning Tools for Crop Yield Prediction and Price Forecasting","year":2021,"lang":"en","type":"article","venue":"","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Mean squared error; Gaussian process; Machine learning; Crop yield; Histogram; Dimensionality reduction; Yield (engineering); Gaussian; Pattern recognition (psychology); Statistics; Image (mathematics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000984709,0.00007368942,0.00008615557,0.000002834539,0.0002369222,0.0002039285,0.00002667719,0.00005496435,0.00007606646],"category_scores_gemma":[0.0002247048,0.00002449271,0.00002846139,0.00009979935,0.00001803107,0.0002142376,0.0000426944,0.00006205201,0.000001206704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003334378,"about_ca_system_score_gemma":0.000001390547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001600235,"about_ca_topic_score_gemma":0.0001333004,"domain_scores_codex":[0.9994791,0.00001632777,0.00009740629,0.0002041318,0.00005635113,0.0001467439],"domain_scores_gemma":[0.9993876,0.0004500314,0.00003028413,0.00001312655,0.00006722606,0.00005171604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000008869856,0.00001360553,0.02322786,0.00001341267,0.000008448137,0.000002841223,0.0001032876,0.000001855112,0.2847724,0.0001308253,0.0003121347,0.6914045],"study_design_scores_gemma":[0.0002163752,0.0004018731,0.7689996,0.00006476176,0.00003568024,0.0001133782,0.002278777,0.0006061271,0.04987952,0.0005406115,0.1765829,0.0002804101],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931022,0.001393695,0.000102224,0.001046463,0.00005331463,0.0001235957,0.000007320331,0.00005661429,0.004114606],"genre_scores_gemma":[0.9957259,0.0006287649,0.0007238499,0.0002167802,0.0003417121,0.00001334611,0.00005844265,5.7093e-7,0.002290638],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7457718,"threshold_uncertainty_score":0.1966487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03694233429901751,"score_gpt":0.2051294547510503,"score_spread":0.1681871204520328,"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."}}