{"id":"W4382468059","doi":"10.1109/access.2023.3290907","title":"Soil Surface Texture Classification Using RGB Images Acquired Under Uncontrolled Field Conditions","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Soil texture; Artificial intelligence; Computer science; Texture (cosmology); Pattern recognition (psychology); Convolutional neural network; Local binary patterns; Image texture; Computer vision; Pixel; RGB color model; Texture filtering; Process (computing); Contextual image classification; Image segmentation; Segmentation; Environmental science; Soil science; Soil water; Image (mathematics); Histogram","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001816596,0.0004873558,0.0003293894,0.001206723,0.0001626263,0.0004861885,0.0002978224,0.0003269123,0.001366029],"category_scores_gemma":[0.000427168,0.0001204891,0.0003684507,0.0007473977,0.0002128569,0.0003945451,0.0002427526,0.0002539861,0.0004561621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003120554,"about_ca_system_score_gemma":0.0002932009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006286005,"about_ca_topic_score_gemma":0.01058259,"domain_scores_codex":[0.999826,0.00001088758,0.000008516523,0.000048026,0.00006860538,0.00003797246],"domain_scores_gemma":[0.9997609,0.00003270412,0.00004224892,0.00004304693,0.00009859941,0.00002257709],"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":[0.001232281,0.0005000656,0.04584576,0.0006384087,0.0001882463,0.0007998494,0.0002361455,0.0355107,0.4967106,0.0005991543,0.005274372,0.4124645],"study_design_scores_gemma":[0.00007491941,0.0004362047,0.2695164,0.00008748272,0.0001673971,0.0006687143,0.0005148735,0.509652,0.2119642,0.0008255098,0.005992319,0.00009991126],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9255655,0.0004055315,0.06256822,0.00009329341,0.00009751076,0.0001347819,0.002445231,0.002771902,0.005917876],"genre_scores_gemma":[0.9645827,0.00024613,0.03164748,0.00005820603,0.00001670897,0.00003875971,0.001955083,0.00009655185,0.001358481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006286005,"threshold_uncertainty_score":0.0124988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06898209234676538,"score_gpt":0.3158056257087619,"score_spread":0.2468235333619965,"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."}}