{"id":"W4361280817","doi":"10.1186/s13007-023-00996-1","title":"Cotton plant part 3D segmentation and architectural trait extraction using point voxel convolutional neural networks","year":2023,"lang":"en","type":"article","venue":"Plant Methods","topic":"Greenhouse Technology and Climate Control","field":"Agricultural and Biological Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Georgia Cotton Commission; Cotton Incorporated; National Science Foundation","keywords":"Computer science; Segmentation; Artificial intelligence; Deep learning; Convolutional neural network; Point cloud; Artificial neural network; Workflow; Pattern recognition (psychology); Inference; Trait; Machine learning","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":[0.0001987574,0.0007839398,0.0003360047,0.0009544715,0.0002002566,0.0005087303,0.0006210547,0.0004030944,0.002023153],"category_scores_gemma":[0.0004119557,0.0004003267,0.0006714832,0.0006635895,0.0002640077,0.0003819001,0.0005396247,0.0004350118,0.0007837853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005765007,"about_ca_system_score_gemma":0.0005664134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01038599,"about_ca_topic_score_gemma":0.01517525,"domain_scores_codex":[0.9998364,0.00001209513,0.000005820866,0.00007354262,0.00004973851,0.000022403],"domain_scores_gemma":[0.9998283,0.00004223054,0.00002622024,0.00003432298,0.00005622022,0.00001259365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003245432,0.00009284903,0.01053321,0.0002309363,0.000112235,0.000260887,0.000176455,0.2821855,0.1839337,0.002509925,0.005656109,0.5139837],"study_design_scores_gemma":[0.000004419008,0.00002358802,0.004146321,0.000009339119,0.00001273651,0.00004556295,0.00001871669,0.9673203,0.02589747,0.0009428405,0.00156241,0.00001634209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1779945,0.0003076066,0.8062724,0.0001384891,0.00004051702,0.00007765966,0.001892052,0.01021023,0.003066584],"genre_scores_gemma":[0.640834,0.0002235973,0.349772,0.00008311581,0.00001422771,0.0001251582,0.004273817,0.0004963749,0.004177751],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01038599,"threshold_uncertainty_score":0.0206511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06020563872532191,"score_gpt":0.3140093548360708,"score_spread":0.2538037161107489,"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."}}