{"id":"W4381433429","doi":"10.3389/fpls.2023.1173036","title":"A transformer-based approach for early prediction of soybean yield using time-series images","year":2023,"lang":"en","type":"article","venue":"Frontiers in Plant Science","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Agriculture, Food and Rural Affairs; Agriculture and Agri-Food Canada","funders":"","keywords":"Transformer; Computer science; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Machine learning; Data mining; Engineering; Voltage","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":[0.0004303698,0.00008862776,0.0001478332,0.00005964021,0.0001973672,0.00004043857,0.0002681946,0.00005346449,0.000006234668],"category_scores_gemma":[0.00004458823,0.00003459771,0.00005666926,0.001198991,0.0002194738,0.0003207852,0.0000127468,0.00005429581,0.000001307575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002065643,"about_ca_system_score_gemma":0.00002339864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007215873,"about_ca_topic_score_gemma":0.00001040166,"domain_scores_codex":[0.9990253,0.00001235681,0.0001665631,0.0002574143,0.0002430431,0.0002952518],"domain_scores_gemma":[0.9997668,0.00005415979,0.00005222005,0.00003576064,0.00004046567,0.00005055876],"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":[0.0000817052,0.00005966178,0.06084517,0.00002252672,0.000004715399,0.00000147698,0.0002123189,0.000354466,0.9264225,0.00002411617,0.009212318,0.002759058],"study_design_scores_gemma":[0.0005448685,0.0009957713,0.5331881,0.0001741016,0.00003789432,0.00001135683,0.002787313,0.07248826,0.385908,0.0006169502,0.002732896,0.0005144555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942725,0.00003120793,0.003578328,0.0001895268,0.0003327174,0.0003748317,0.0006249791,0.00007148076,0.0005244818],"genre_scores_gemma":[0.9895484,0.000009320139,0.009913496,0.00003203038,0.0001102235,0.00002722391,0.0001579892,8.428617e-7,0.0002004318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5405144,"threshold_uncertainty_score":0.1518009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02468175956661435,"score_gpt":0.2024413844055812,"score_spread":0.1777596248389668,"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."}}