{"id":"W4387213918","doi":"10.1007/s11119-023-10080-2","title":"WeedsNet: a dual attention network with RGB-D image for weed detection in natural wheat field","year":2023,"lang":"en","type":"article","venue":"Precision Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ministry of Education and Child Care","funders":"Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; RGB color model; Weed; Computer science; Convolutional neural network; Field (mathematics); Object detection; Pattern recognition (psychology); Feature (linguistics); Computer vision; Feature extraction; Mathematics; Agronomy","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":[0.0002691622,0.0002545082,0.000256578,0.00002836278,0.000301235,0.0001365755,0.0001738693,0.0002437481,0.00007343948],"category_scores_gemma":[0.00007243259,0.00007488719,0.0001638286,0.001595062,0.0000186047,0.0002938011,0.00006012702,0.0002818895,0.00008956922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003571186,"about_ca_system_score_gemma":0.000003924755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001609217,"about_ca_topic_score_gemma":0.005891861,"domain_scores_codex":[0.9983309,0.00007887749,0.0002832018,0.0004869402,0.0003224385,0.0004976609],"domain_scores_gemma":[0.9991441,0.0004389265,0.0001052382,0.00006520428,0.0001528779,0.00009365343],"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":[0.0003594175,0.00007658306,0.002446698,0.00001312749,0.00002433081,0.00001404268,0.00007353307,0.0001822145,0.797271,0.00002528648,0.1029654,0.09654841],"study_design_scores_gemma":[0.0009785912,0.0009092118,0.85399,0.0001845185,0.000045083,0.00004549206,0.0005869757,0.0007443276,0.01173971,0.0004588254,0.1297353,0.0005819784],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935134,0.0001469149,0.000101035,0.003829775,0.0005993869,0.001170113,0.00002918539,0.0002933407,0.0003168622],"genre_scores_gemma":[0.9948264,0.00003140964,0.0002921354,0.0003897886,0.001511796,0.000313002,0.0003954977,0.000002586721,0.00223742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8515433,"threshold_uncertainty_score":0.3287797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008659327943141941,"score_gpt":0.2135288723506323,"score_spread":0.2048695444074903,"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."}}