{"id":"W4390189840","doi":"10.1109/iccvw60793.2023.00057","title":"Weed Mapping with Convolutional Neural Networks on High Resolution Whole-Field Images","year":2023,"lang":"en","type":"article","venue":"","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Weed; Convolutional neural network; Field (mathematics); Computer science; Pipeline (software); Artificial intelligence; Process (computing); Deep learning; Pixel; Precision agriculture; Remote sensing; Machine learning; Computer vision; Mathematics; Geography; 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":[0.00009946028,0.0001218992,0.0001092485,0.00001285183,0.0002537392,0.00005970123,0.0001240241,0.0000836762,0.0002733548],"category_scores_gemma":[0.00001587677,0.00003420228,0.00005204092,0.0005781443,0.00003081373,0.0001016104,0.0000424276,0.0001364293,0.0001564541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001249582,"about_ca_system_score_gemma":0.000002334132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004136456,"about_ca_topic_score_gemma":0.0003130109,"domain_scores_codex":[0.9991041,0.00003451123,0.0001162244,0.0002469184,0.0001997995,0.0002983976],"domain_scores_gemma":[0.9995984,0.0002110303,0.00003846017,0.00003630799,0.00004819775,0.00006763239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002717348,0.0001557314,0.02101309,0.000007602662,0.00006355601,0.00006100255,0.0000524209,0.006853633,0.222555,0.005854638,0.6874408,0.05567075],"study_design_scores_gemma":[0.0002190628,0.000582601,0.9505255,0.00002901428,0.00000785859,0.000009669265,0.0003430582,0.005273533,0.0009401744,0.000189328,0.04162495,0.0002552927],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756498,0.00003275082,0.00006535725,0.01969353,0.0002404712,0.0001932751,0.00001321939,0.0003656818,0.003745898],"genre_scores_gemma":[0.9932496,0.000006197086,0.00003985819,0.001428319,0.0008232441,0.00002585905,0.0002357948,6.839723e-7,0.004190433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9295124,"threshold_uncertainty_score":0.2993044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164509237785823,"score_gpt":0.1929261226298413,"score_spread":0.176475198851259,"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."}}