{"id":"W2986154667","doi":"10.3389/fpls.2019.01422","title":"Weed Detection in Perennial Ryegrass With Deep Learning Convolutional Neural Network","year":2019,"lang":"en","type":"article","venue":"Frontiers in Plant Science","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":154,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Perennial plant; Weed; Weed control; Cirsium arvense; Convolutional neural network; Agronomy; Artificial intelligence; Computer science; Biology","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":[0.0003721836,0.000109836,0.00014749,0.00003663781,0.0001951524,0.000067628,0.0002690331,0.00005970228,0.00003567322],"category_scores_gemma":[0.00002198241,0.00003962616,0.0000249184,0.001196443,0.0001419835,0.000306125,0.00004453619,0.0002453138,0.00001380956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007559192,"about_ca_system_score_gemma":0.00001434884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003263465,"about_ca_topic_score_gemma":0.003010249,"domain_scores_codex":[0.9987063,0.00004842952,0.0001384283,0.0003530521,0.0003177948,0.0004359875],"domain_scores_gemma":[0.9997634,0.00005353697,0.00005800547,0.00003049198,0.00002925957,0.000065292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008690381,0.00002263478,0.9441049,0.000001652535,0.000001685877,0.000008260522,0.00007412503,0.004932976,0.03637215,0.00003784688,0.000243664,0.01411318],"study_design_scores_gemma":[0.0002046339,0.0002017411,0.9721308,0.00002495572,0.000001802901,0.00002006348,0.0005635802,0.02331824,0.0003151121,0.00007315516,0.002987903,0.0001579814],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981186,0.00009532808,0.00004338498,0.0001226443,0.0008390438,0.0001980968,0.000003669304,0.00003018411,0.0005490143],"genre_scores_gemma":[0.99927,0.000007342043,0.0002836939,0.00006822741,0.0001916128,0.00001294381,0.00002205926,4.757175e-7,0.0001436253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03605703,"threshold_uncertainty_score":0.167979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005057183436819375,"score_gpt":0.165768131393649,"score_spread":0.1607109479568296,"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."}}