{"id":"W4390848532","doi":"10.1016/j.compag.2024.108617","title":"Quantifying consistency of crop establishment using a lightweight U-Net deep learning architecture and image processing techniques","year":2024,"lang":"en","type":"article","venue":"Computers and Electronics in Agriculture","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Consistency (knowledge bases); Row crop; Hough transform; Crop; Artificial intelligence; Field (mathematics); Computer science; Statistics; Mathematics; Pattern recognition (psychology); Image (mathematics); Agronomy; Geography","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":[0.0001889306,0.0002364797,0.0002910944,0.00004104499,0.0002135454,0.000310209,0.0001298605,0.0001619206,0.000006124917],"category_scores_gemma":[0.00001136709,0.00008458816,0.00006712576,0.000596456,0.00007992185,0.0002022898,0.0001097065,0.0004838524,3.237923e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004412961,"about_ca_system_score_gemma":0.00001529616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007388471,"about_ca_topic_score_gemma":0.0004338119,"domain_scores_codex":[0.9987125,0.00006284995,0.000271076,0.0004299776,0.0001578233,0.0003657285],"domain_scores_gemma":[0.9996439,0.0001031719,0.00008248976,0.00003304678,0.00006436864,0.00007299207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001589974,0.00006548376,0.002372052,0.0002593875,0.00003307229,0.00003571942,0.001057155,0.00005924983,0.6779731,0.001243903,0.0004830349,0.316402],"study_design_scores_gemma":[0.001596491,0.004447356,0.1010658,0.01090953,0.0006352382,0.003162933,0.006721839,0.05000031,0.1971021,0.01002114,0.6087633,0.00557403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960506,0.0374646,0.0004647651,0.000805447,0.0000879028,0.0002563159,0.000004597823,0.0001354684,0.0002749015],"genre_scores_gemma":[0.9945645,0.001561394,0.003465279,0.000075153,0.000241749,0.000008690038,0.00003655052,0.00000250828,0.00004413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6082802,"threshold_uncertainty_score":0.3449405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01202027243861776,"score_gpt":0.233052237595663,"score_spread":0.2210319651570453,"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."}}