{"id":"W4309788022","doi":"10.3390/agronomy12112889","title":"Development of Weed Detection Method in Soybean Fields Utilizing Improved DeepLabv3+ Platform","year":2022,"lang":"en","type":"article","venue":"Agronomy","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Weed; Computer science; Pattern recognition (psychology); Segmentation; Artificial intelligence; Feature (linguistics); Transformer; Pixel; Feature extraction; Agronomy; Voltage","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002491107,0.000958705,0.0004795282,0.0005744811,0.0002361043,0.0004718931,0.001334215,0.000540942,0.002040231],"category_scores_gemma":[0.0003992616,0.0003503908,0.0006124556,0.0003920412,0.000169019,0.001016497,0.0005579829,0.0006316939,0.0007700352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006957568,"about_ca_system_score_gemma":0.0009556627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01543348,"about_ca_topic_score_gemma":0.01729676,"domain_scores_codex":[0.9998811,0.000007377369,0.000004630834,0.00004506666,0.00003680539,0.00002489779],"domain_scores_gemma":[0.9999138,0.00001537336,0.000009552974,0.00001237036,0.00003680045,0.00001207303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002766771,0.0002410692,0.005493551,0.0002362222,0.0001485044,0.0002078965,0.0001124464,0.1522234,0.1140083,0.002023793,0.01257124,0.7124568],"study_design_scores_gemma":[0.00001593049,0.00005878073,0.001069371,0.000006528782,0.00002177158,0.00004410424,0.00001966588,0.9810053,0.01512289,0.0008079207,0.001815386,0.00001234765],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1312359,0.0008463216,0.8339779,0.0003292499,0.0001349091,0.0001666695,0.001063913,0.02735371,0.004891494],"genre_scores_gemma":[0.6776304,0.0005680742,0.3080702,0.000460691,0.00003215496,0.0002384939,0.003212578,0.0005238801,0.009263551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01543348,"threshold_uncertainty_score":0.03068733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02421193319795134,"score_gpt":0.2281000883286806,"score_spread":0.2038881551307293,"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."}}