{"id":"W4409760372","doi":"10.1371/journal.pone.0322189","title":"From blender to farm: Transforming controlled environment agriculture with synthetic data and SwinUNet for precision crop monitoring","year":2025,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Weston Family Foundation","keywords":"Segmentation; Computer science; Artificial intelligence; Synthetic data; Pattern recognition (psychology); Ripeness; Precision agriculture; Computer vision; Machine learning; Agriculture","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001138542,0.0001667637,0.0003174248,0.000009338859,0.0001950181,0.00009430441,0.0002764824,0.00008408182,0.00004063337],"category_scores_gemma":[0.00003650566,0.00004971286,0.00003645523,0.0001216465,0.00001816623,0.0001105383,0.00009769637,0.00008299936,0.000006053568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001838838,"about_ca_system_score_gemma":0.000003695387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001073488,"about_ca_topic_score_gemma":0.000185058,"domain_scores_codex":[0.9988821,0.00002571861,0.0001815134,0.000472463,0.0002187629,0.0002194043],"domain_scores_gemma":[0.9994384,0.0002875619,0.0000405508,0.0001118819,0.00003497652,0.00008664114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004372054,0.0004744688,0.002949442,0.00001918989,0.0002487688,0.000001435451,0.0001852695,0.000008312858,0.9643834,0.00001562555,0.0004590543,0.03081789],"study_design_scores_gemma":[0.00851226,0.002105721,0.187364,0.003215839,0.002328967,0.00000420493,0.004144567,0.0006984,0.7023931,0.0009765435,0.08667901,0.00157732],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944394,0.0005856253,0.0001405385,0.003128953,0.00003583017,0.001215403,0.0002132551,0.00004037514,0.0002005706],"genre_scores_gemma":[0.9959731,0.0001560745,0.001943682,0.0001410711,0.0003991066,0.0001758246,0.0001592619,0.000001338132,0.001050581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2619902,"threshold_uncertainty_score":0.2027232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03679393952764824,"score_gpt":0.2160692662475228,"score_spread":0.1792753267198746,"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."}}